Commit Graph

47 Commits

Author SHA1 Message Date
daymade
143995b213 refactor: rename markdown-tools → doc-to-markdown (v2.0.0)
- Rename skill to better reflect its purpose (document-to-markdown conversion)
- Update SKILL.md name, description, and trigger keywords
- Add benchmark reference (2026-03-22)
- Update marketplace.json entry (name, skills path, version 2.0.0)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 00:06:30 +08:00
daymade
639a6d303e feat(transcript-fixer): native AI correction as default mode (v1.3.0)
Claude IS the AI — when running inside Claude Code, use Claude's own
language understanding for Stage 2 corrections instead of calling an
external API. No API key needed by default.

New capabilities in native mode:
- Intelligent paragraph breaks at logical topic transitions
- Filler word reduction (excessive repetition removal)
- Interactive review with confidence-level tables
- Context-aware judgment using full document context

API mode (GLM) remains available for batch/automation use cases.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 23:40:38 +08:00
daymade
2192458ef7 release: add scrapling-skill and fix script compatibility
- add scrapling-skill with validated CLI workflow, diagnostics, packaging, and docs integration
- fix skill-creator package_skill.py so direct script invocation works from repo root
- fix continue-claude-work extract_resume_context.py typing compatibility for local python3
- bump marketplace to 1.39.0 and updated skill versions
2026-03-18 23:08:55 +08:00
daymade
c49e23e7ef release: v1.38.0 with continue-claude-work and skill-creator enhancements
## New Skill: continue-claude-work (v1.1.0)
- Recover actionable context from local `.claude` session artifacts
- Compact-boundary-aware extraction (reads Claude's own compaction summaries)
- Subagent workflow recovery (reports completed vs interrupted subagents)
- Session end reason detection (clean exit, interrupted, error cascade, abandoned)
- Size-adaptive strategy for small/large sessions
- Noise filtering (skips 37-53% of session lines)
- Self-session exclusion, stale index fallback, MEMORY.md integration
- Bundled Python script (no external dependencies)
- Security scan passed, argument-hint added

## Skill Updates
- **skill-creator** (v1.5.0): Complete rewrite with evaluation framework
  - Added agents/ (analyzer, comparator, grader)
  - Added eval-viewer/ (generate_review.py, viewer.html)
  - Added scripts/ (run_eval, aggregate_benchmark, improve_description, run_loop)
  - Added references/schemas.md (eval/benchmark schemas)
  - Expanded SKILL.md with inline vs fork guidance, progressive disclosure patterns
  - Enhanced package_skill.py and quick_validate.py

- **transcript-fixer** (v1.2.0): CLI improvements and test coverage
  - Enhanced argument_parser.py and commands.py
  - Added correction_service.py improvements
  - Added test_correction_service.py

- **tunnel-doctor** (v1.4.0): Quick diagnostic script
  - Added scripts/quick_diagnose.py
  - Enhanced SKILL.md with 5-layer conflict model

- **pdf-creator** (v1.1.0): Auto DYLD_LIBRARY_PATH + rendering fixes
  - Auto-detect and set DYLD_LIBRARY_PATH for weasyprint
  - Fixed list rendering and CSS improvements

- **github-contributor** (v1.0.3): Enhanced project evaluation
  - Added evidence-loop, redaction, and merge-ready PR guidance

## Documentation
- Updated marketplace.json (v1.38.0, 42 skills)
- Updated CHANGELOG.md with v1.38.0 entry
- Updated CLAUDE.md (skill count, marketplace version, #42 description)
- Updated README.md (badges, skill section #42, use case, requirements)
- Updated README.zh-CN.md (badges, skill section #42, use case, requirements)
- Fixed absolute paths in continue-claude-work/references/file_structure.md

## Validation
- All skills passed quick_validate.py
- continue-claude-work passed security_scan.py
- marketplace.json validated (valid JSON)
- Cross-checked version consistency across all docs
2026-03-07 14:54:33 +08:00
daymade
b675ac6fee docs(github-contributor): add evidence-loop, redaction, and merge-ready PR guidance 2026-03-05 20:34:10 +08:00
daymade
4f07976825 release: prepare v1.37.0 with excel-automation and capture-screen 2026-03-02 20:01:18 +08:00
daymade
2896870061 feat: add financial-data-collector skill for US equity data collection
New skill that collects real financial data for any US publicly traded company
via yfinance. Outputs structured JSON with market data, historical financials,
WACC inputs, and analyst estimates. Includes 9-check validation script and
reference docs for yfinance pitfalls (NaN years, field aliases, FCF mismatch).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 19:40:52 +08:00
daymade
26aef9ceb2 chore: sync versioned marketplace updates for 1.34.1 2026-02-23 16:21:56 +08:00
daymade
72d879e609 Update skill docs and resources 2026-02-23 16:16:58 +08:00
daymade
830fc8f90f ⬆️ feat: upgrade tunnel-doctor to v1.2.0 with Layer 4 SSH ProxyCommand diagnostics
Add fourth conflict layer: SSH ProxyCommand double tunneling causing
intermittent git push/pull failures when Shadowrocket TUN is active.

Structural improvements per skill best practices:
- Eliminate content duplication between SKILL.md and reference
- Rename proxy_fixes.md → proxy_conflict_reference.md for clarity
- Trim SKILL.md from 534 to 487 lines (under 500 limit)
- Shorten YAML description from 910 to 661 characters
- Fix "apply all four" listing 5 items (separate anti-pattern)
- Clarify Layer 4's relationship to Tailscale theme

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-17 20:03:25 +08:00
daymade
1a5c8d7931 ⬆️ feat: upgrade tunnel-doctor to v1.1.0 with SSH tunnel SOP and Makefile patterns
Add remote development SOP: proxy-safe Makefile patterns (--noproxy localhost),
SSH tunnel targets (tunnel/tunnel-bg with autossh), multi-port tunnels, and
end-to-end workflow with pre-flight checklist. Add diagnostic steps 2D (auth
redirect via SSH forwarding) and 2E (localhost proxy interception). Fix step
ordering, third-person description, and replace hardcoded IPs with placeholders.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 02:27:07 +08:00
daymade
abd0dbe066 feat: strengthen claude-md-progressive-disclosurer anti-deletion safeguards (v1.2.0)
- Add "move as-is, no compression" iron rule to prevent info loss during Level 2 migration
- Add anti-patterns 6 (compression during move) and 7 (disguising loss as "intentional deletion")
- Enhance Step 5 verification with 3 sub-checks: file existence, content completeness, no line counting
- Ban `wc -l` and line count mentions throughout the workflow
- Add real-world case studies 8 and 9 to principles reference
- Bump skill version to 1.2.0, marketplace to 1.32.1

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 05:37:32 +08:00
daymade
08324f8ebe fix: bump claude-md-progressive-disclosurer to v1.1.0 and add version bump rule
- Bump claude-md-progressive-disclosurer 1.0.1 → 1.1.0 (missed in previous commit)
- Add mandatory "Updating Existing Skills" rule to CLAUDE.md: any commit
  that modifies a skill's files MUST bump that skill's version in marketplace.json

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 04:48:53 +08:00
daymade
e481958195 Release v1.32.0: Add windows-remote-desktop-connection-doctor skill
- Add windows-remote-desktop-connection-doctor v1.0.0 for diagnosing AVD/W365
  connection quality issues with transport protocol analysis and log parsing
- Update claude-md-progressive-disclosurer SKILL.md and references
- Update marketplace to v1.32.0 (37 skills)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 04:45:31 +08:00
daymade
b0a630390f Release v1.31.0: Add tunnel-doctor skill
- Add tunnel-doctor v1.0.0: diagnose and fix Tailscale + proxy/VPN route conflicts on macOS
- 6-step diagnostic workflow, per-tool fix guides (Shadowrocket/Clash/Surge)
- Tailscale SSH ACL config and WSL snap vs apt guidance
- Update marketplace to v1.31.0, skills count 35 → 36

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-08 00:26:36 +08:00
daymade
104e431574 Release v1.30.0: Add competitors-analysis skill
- Add competitors-analysis skill for evidence-based competitor tracking
  - Pre-analysis checklist to ensure repositories are cloned locally
  - Forbidden patterns to prevent assumptions and speculation
  - Required patterns for source citation (file:line_number format)
  - Tech stack analysis guides for Node.js, Python, Rust
  - Bundled references: profile_template.md, analysis_checklist.md
  - Management script: update-competitors.sh
- Update marketplace version from 1.29.0 to 1.30.0
- Update skills count from 34 to 35
- Update README.md and README.zh-CN.md (badges, skill section, use case)
- Update CLAUDE.md (skill count, available skills list)
- Update marketplace.json (metadata + new plugin entry)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 00:01:57 +08:00
daymade
9106f8a0e1 Release v1.29.0: Enhance skill-creator with comprehensive YAML frontmatter documentation
- Bump skill-creator from v1.3.0 to v1.4.0
- Add complete YAML frontmatter reference table with all available fields
- Document `context: fork` for subagent-accessible skills (PR #6 by @costa-marcello)
- Add invocation control comparison table
- Document $ARGUMENTS placeholder with usage examples
- Add allowed-tools wildcard syntax examples
- Add hooks field inline example
- Update init_skill.py template with all optional fields

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-29 20:20:08 +08:00
daymade
1d49e3e377 Release v1.28.0: Enhance meeting-minutes-taker with speaker identification
Add speaker identification and pre-processing pipeline:
- Speaker identification via feature analysis (word count, segment count,
  filler ratio, speaking style) with context.md team directory mapping
- New context_file_template.md for team directory configuration
- Intelligent file naming pattern: YYYY-MM-DD-<topic>-<type>.md
- Pre-processing pipeline with markdown-tools and transcript-fixer
- Transcript quality assessment workflow

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-25 21:57:01 +08:00
daymade
3f15b8942c Release v1.27.0: Enhance markdown-tools with Heavy Mode
Add multi-tool orchestration for best-quality document conversion:
- Dual mode: Quick (fast) and Heavy (best quality, multi-tool merge)
- New convert.py - main orchestrator with tool selection matrix
- New merge_outputs.py - segment-level multi-tool output merger
- New validate_output.py - quality validation with HTML reports
- Enhanced extract_pdf_images.py - metadata (page, position, dimensions)
- PyMuPDF4LLM integration for LLM-optimized PDF conversion
- pandoc integration for DOCX/PPTX structure preservation
- Quality metrics: text/table/image retention with pass/warn/fail
- New references: heavy-mode-guide.md, tool-comparison.md

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-25 21:36:08 +08:00
daymade
114c355aa8 Release v1.26.0: Add deep-research skill 2026-01-25 15:45:29 +08:00
daymade
8d7d9e049a chore: Update marketplace config for v1.25.0
- Bump marketplace version: 1.24.0 → 1.25.0
- Bump skill-creator version: 1.2.2 → 1.3.0 (sanitization step)
- Add meeting-minutes-taker plugin entry
- Update skill count: 32 → 33 in all docs
- Update badges in README.md and README.zh-CN.md
- Add skill sections and use cases in both READMEs
- Update CLAUDE.md available skills list

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-24 23:07:35 +08:00
daymade
35872b9e77 Release v1.24.0: Add claude-skills-troubleshooting
- Add claude-skills-troubleshooting v1.0.0
  - Plugin installation and enablement debugging
  - Diagnostic scripts for installed vs enabled mismatch
  - Known GitHub issues tracking (#17832, #19696, #17089, #13543, #16260)
  - Skills vs Commands architecture documentation
  - Batch enable script for missing plugins

- Add i18n-expert v1.0.0
  - Complete i18n/l10n setup for React/Next.js/Vue
  - Key architecture and locale file organization
  - Translation generation strategy (AI, professional, manual)
  - Key parity validation between en-US and zh-CN
  - Bundled i18n_audit.py script

- Update marketplace to v1.24.0 (32 skills)
- Update README.md badges (skills count, version)
- Update README.zh-CN.md badges (skills count, version)
- Update CLAUDE.md skills count and Available Skills list
- Update youtube-downloader with PO token enhancements

Co-Authored-By: Claude <noreply@anthropic.com>
2026-01-22 22:05:14 +08:00
daymade
8363750c13 Release v1.22.0: Add skill-reviewer and github-contributor
- Add skill-reviewer v1.0.0 for reviewing Claude Code skills against best practices
  - Self-review mode: validate your own skills before publishing
  - External review mode: evaluate others' skill repositories
  - Auto-PR mode: fork, improve, submit PRs with additive-only changes
  - Auto-install dependencies: automatically installs skill-creator if missing

- Add github-contributor v1.0.0 for strategic open-source contribution
  - Four contribution types: Documentation, Code Quality, Bug Fixes, Features
  - Project selection criteria and red flags
  - PR excellence workflow and reputation building ladder
  - GitHub CLI commands and conventional commit format

- Update marketplace to v1.22.0 with 30 skills
- Update documentation (README, README.zh-CN, CLAUDE.md, CHANGELOG)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-15 23:02:40 +08:00
daymade
484255aa73 Release v1.21.1: Update macos-cleaner to v1.1.0
Major improvements based on real-world usage experience:

- Add "Value Over Vanity" principle - prioritize identifying truly useless
  items over maximizing cleanup numbers
- Add "Network Environment Awareness" - consider slow internet when
  recommending cache deletion
- Add "Impact Analysis Required" - every recommendation must explain
  consequences
- Add comprehensive "Anti-Patterns" section documenting what NOT to delete
- Add "Multi-Layer Deep Exploration" guide with complete tmux + Mole TUI
  navigation workflow
- Add "High-Quality Report Template" with proven 3-tier classification
  (🟢/🟡/🔴)
- Add "Report Quality Checklist" for verification before presenting findings
- Add explicit prohibition of `docker volume prune -f`
- Update safety principles to emphasize cache value over cleanup metrics

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-11 17:50:50 +08:00
daymade
4d6ed53c1e Release v1.21.0: Add macos-cleaner skill
- Add macos-cleaner v1.0.0 - Intelligent macOS disk space recovery
- Safety-first philosophy with risk categorization (Safe/Caution/Keep)
- Smart analysis: caches, app remnants, large files, dev environments
- Interactive cleanup with explicit user confirmation
- Bundled scripts: analyze_caches, analyze_dev_env, analyze_large_files,
  find_app_remnants, safe_delete, cleanup_report
- Comprehensive references: cleanup_targets, mole_integration, safety_rules
- Update marketplace to v1.21.0
- Update all documentation (README.md, README.zh-CN.md, CHANGELOG.md, CLAUDE.md)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-11 15:59:13 +08:00
daymade
3f2f8f02ca Release v1.20.0: Add twitter-reader skill
- Add twitter-reader v1.0.0 for Twitter/X content fetching via Jina.ai API
- Implement secure API key management using environment variables
- Support individual and batch tweet fetching with bundled scripts
- Include Python (fetch_tweet.py) and Bash (fetch_tweets.sh) scripts
- Update marketplace to v1.20.0 (26 → 27 skills)
- Update all documentation (README.md, README.zh-CN.md, CLAUDE.md)
- Security: Remove hardcoded API keys, enforce HTTPS, add validation

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-11 15:41:13 +08:00
daymade
7ba893d837 feat: add fact-checker skill v1.0.0
Add comprehensive fact-checking skill that verifies claims using web search
and official sources, then proposes corrections with user confirmation.

Features:
- 5-step workflow: identify → search → compare → report → apply
- Supports AI model specs, technical docs, statistics, general facts
- Source evaluation framework prioritizing official documentation
- Auto-correction with mandatory user approval gates
- Temporal context to prevent information decay

Real-world usage:
- Successfully updated AI model specs (Claude, GPT, Gemini)
- Corrected outdated version numbers and context windows
- Added temporal markers for time-sensitive information

Marketplace updates:
- Bumped version to 1.19.0
- Added fact-checker to plugins list
- Updated metadata description

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-05 23:31:44 +08:00
daymade
80cd0fe7e1 Update claude-md-progressive-disclosurer v1.0.1 with safety features
Enhanced workflow to prevent information loss and ensure optimization quality:
- Added mandatory backup step (Step 0)
- Added pre-execution verification checklist (Step 3.5)
- Added post-optimization testing (Step 5)
- Added exception criteria for safety-critical/high-frequency sections
- Added project-level vs user-level CLAUDE.md guidance
- Updated references with verification methods

Updated marketplace configuration:
- Bumped claude-md-progressive-disclosurer from 1.0.0 to 1.0.1
- Updated CHANGELOG.md with v1.18.2 entry

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-05 23:27:30 +08:00
daymade
8233430cf2 Release v1.18.1: Enhance markdown-tools with PDF image extraction
- Add extract_pdf_images.py script using PyMuPDF
- Refactor SKILL.md for clearer workflow documentation
- Update installation to use markitdown[pdf] extra
- Update marketplace version to 1.18.1
- Update markdown-tools version to 1.1.0
- Update README/README.zh-CN with new features
- Update QUICKSTART docs with in-app install instructions

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-28 18:46:15 +08:00
daymade
4e3a54175e Release v1.18.0: Add iOS-APP-developer and promptfoo-evaluation skills
### Added
- **New Skill**: iOS-APP-developer v1.1.0 - iOS development with XcodeGen, SwiftUI, and SPM
  - XcodeGen project.yml configuration
  - SPM dependency resolution
  - Device deployment and code signing
  - Camera/AVFoundation debugging
  - iOS version compatibility handling
  - Library not loaded @rpath framework error fixes
  - State machine testing patterns for @MainActor classes
  - Bundled references: xcodegen-full.md, camera-avfoundation.md, swiftui-compatibility.md, testing-mainactor.md

- **New Skill**: promptfoo-evaluation v1.0.0 - LLM evaluation framework using Promptfoo
  - Promptfoo configuration (promptfooconfig.yaml)
  - Python custom assertions
  - llm-rubric for LLM-as-judge evaluations
  - Few-shot example management
  - Model comparison and prompt testing
  - Bundled reference: promptfoo_api.md

### Changed
- Updated marketplace version from 1.16.0 to 1.18.0
- Updated marketplace skills count from 23 to 25
- Updated skill-creator to v1.2.2:
  - Fixed best practices documentation URL (platform.claude.com)
  - Enhanced quick_validate.py to exclude file:// prefixed paths from validation
- Updated marketplace.json metadata description to include new skills

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-20 17:23:08 +08:00
daymade
b1a21dc05b feat: Add skills-search skill for CCPM registry
- Add skills-search v1.0.0: Search, discover, install, and manage Claude Code skills from CCPM registry
- Track docs-cleaner skill that was already in marketplace.json
- Update marketplace version from 1.15.0 to 1.16.0
- Update skill count from 22 to 23 across all documentation
- Add skills-search section to README.md and README.zh-CN.md
- Add CCPM CLI to requirements section
- Add use case section for skill discovery & management

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-11 20:53:31 +08:00
daymade
d0042ffc7a feat: Add claude-md-progressive-disclosurer skill
- Add skill for optimizing user CLAUDE.md files
- Apply progressive disclosure principles to reduce context overhead
- Include workflow for auditing, classifying, and refactoring sections
- Add reference doc for token economics and best practices
- Update marketplace to v1.15.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-11 20:20:41 +08:00
daymade
ec3141b8ef feat: Add pdf-creator skill for markdown to PDF conversion
- Add pdf-creator skill with Chinese font support (weasyprint)
- Include md_to_pdf.py for single file conversion
- Include batch_convert.py for multiple files
- Support formal documents: legal filings, reports, trademark applications
- Update marketplace to v1.14.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-11 20:04:33 +08:00
daymade
1d237fc3be feat: Update skill-creator and transcript-fixer
skill-creator v1.2.0 → v1.2.1:
- Add critical warning about not editing skills in cache directory
- Cache location (~/.claude/plugins/cache/) is read-only
- Changes there are lost on cache refresh

transcript-fixer v1.0.0 → v1.1.0:
- Add Chinese/Japanese/Korean domain name support (火星加速器, 具身智能)
- Add [CLAUDE_FALLBACK] signal for Claude Code to take over when GLM unavailable
- Add Prerequisites section requiring uv for Python execution
- Add Critical Workflow section for dictionary iteration
- Add AI Fallback Strategy and Database Operations sections
- Add Stages table (Dictionary → AI → Full pipeline)
- Add ensure_deps.py script for shared virtual environment
- Add database_schema.md and iteration_workflow.md references
- Update domain validation from whitelist to pattern matching
- Update tests for Chinese domains and security bypass attempts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-11 13:04:27 +08:00
daymade
31a535b409 feat(skill-creator): Add path reference validation
- Add find_path_references() to scan SKILL.md for bundled resource paths
- Add validate_path_references() to verify referenced files exist
- Smart filtering for example/documentation contexts
- Update SKILL.md Step 6 with validation details
- Bump version to 1.2.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-01 20:33:15 +08:00
daymade
adc4072f02 feat(youtube-downloader): Add HLS streaming support v1.1.0
- Add comprehensive HLS stream download support (m3u8 format)
- Add support for Mux, Vimeo, and other HLS-based services
- Add ffmpeg-based workflow with authentication headers
- Add Referer header configuration for protected streams
- Add protocol whitelisting guidance
- Add separate audio/video stream handling and merging
- Add troubleshooting for 403 errors, stuck cookie extraction, expired signatures
- Update skill description and triggers to include HLS streams

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-19 01:21:25 +08:00
daymade
df2e654b1d Release v1.11.0: Add prompt-optimizer skill with EARS methodology
Add new prompt-optimizer skill (v1.1.0) for transforming vague prompts into
precise EARS specifications:

New Features:
- EARS (Easy Approach to Requirements Syntax) transformation with 5 patterns
- 6-step optimization workflow (analyze, transform, theories, examples, enhance, present)
- Domain theory grounding (40+ frameworks across 10 domains)
- Role/Skills/Workflows/Examples/Formats prompt enhancement framework
- Progressive disclosure with 4 bundled reference files

Skill Improvements (v1.0.0 → v1.1.0):
- Reduced SKILL.md from 369 to 195 lines (47% reduction)
- Added advanced_techniques.md (325 lines) for complex scenarios
- Added 4th complete example (password reset security)
- Added attribution to 阿星AI工作室 (A-Xing AI Studio)
- Enhanced reference loading guidance

Marketplace Updates:
- Updated marketplace to v1.11.0 (17 → 18 skills)
- Updated all documentation (README.md, README.zh-CN.md, CLAUDE.md)
- Added Chinese and English descriptions with attribution

🤖 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-16 23:41:14 +08:00
daymade
15582e2538 Release v1.10.0: Add qa-expert skill and improve SOP
## New Skill: qa-expert (v1.0.0)

Comprehensive QA testing infrastructure with autonomous LLM execution:
- One-command QA project initialization with complete templates
- Google Testing Standards (AAA pattern, 90% coverage targets)
- Autonomous LLM-driven test execution via master prompts (100x speedup)
- OWASP Top 10 security testing (90% coverage target)
- Bug tracking with P0-P4 severity classification
- Quality gates enforcement (100% execution, ≥80% pass rate, 0 P0 bugs)
- Ground Truth Principle for preventing doc/CSV sync issues
- Day 1 onboarding guide (5-hour timeline)
- 30+ ready-to-use LLM prompts for QA tasks
- Bundled scripts: init_qa_project.py, calculate_metrics.py

## Documentation Updates

- Updated marketplace to v1.10.0 (16 → 17 skills)
- Updated CHANGELOG.md with v1.10.0 entry
- Updated README.md (EN) with qa-expert skill section
- Updated README.zh-CN.md (ZH) with skills 11-16 and qa-expert
- Updated CLAUDE.md with qa-expert in available skills list
- Updated marketplace.json with qa-expert plugin entry

## SOP Improvements

Enhanced "Adding a New Skill to Marketplace" workflow:
- Added mandatory Step 7: Update README.zh-CN.md
- Added 6 new Chinese documentation checklist items
- Added Chinese documentation to Common Mistakes (#2, #3, #4, #5, #7, #8)
- Updated File Update Summary Template (7 files including zh-CN)
- Added verification commands for EN/ZH sync
- Made Chinese documentation updates MANDATORY

Total: 17 production-ready skills

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-10 01:48:37 +08:00
daymade
9b724f33e3 Release v1.9.0: Add video-comparer skill and enhance transcript-fixer
## New Skill: video-comparer v1.0.0
- Compare original and compressed videos with interactive HTML reports
- Calculate quality metrics (PSNR, SSIM) for compression analysis
- Generate frame-by-frame visual comparisons (slider, side-by-side, grid)
- Extract video metadata (codec, resolution, bitrate, duration)
- Multi-platform FFmpeg support with security features

## transcript-fixer Enhancements
- Add async AI processor for parallel processing
- Add connection pool management for database operations
- Add concurrency manager and rate limiter
- Add audit log retention and database migrations
- Add health check and metrics monitoring
- Add comprehensive test suite (8 new test files)
- Enhance security with domain and path validators

## Marketplace Updates
- Update marketplace version from 1.8.0 to 1.9.0
- Update skills count from 15 to 16
- Update documentation (README.md, CLAUDE.md, CHANGELOG.md)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-30 00:23:12 +08:00
daymade
bd0aa12004 Release v1.8.0: Add transcript-fixer skill
## New Skill: transcript-fixer v1.0.0

Correct speech-to-text (ASR/STT) transcription errors through dictionary-based rules and AI-powered corrections with automatic pattern learning.

**Features:**
- Two-stage correction pipeline (dictionary + AI)
- Automatic pattern detection and learning
- Domain-specific dictionaries (general, embodied_ai, finance, medical)
- SQLite-based correction repository
- Team collaboration with import/export
- GLM API integration for AI corrections
- Cost optimization through dictionary promotion

**Use cases:**
- Correcting meeting notes, lecture recordings, or interview transcripts
- Fixing Chinese/English homophone errors and technical terminology
- Building domain-specific correction dictionaries
- Improving transcript accuracy through iterative learning

**Documentation:**
- Complete workflow guides in references/
- SQL query templates
- Troubleshooting guide
- Team collaboration patterns
- API setup instructions

**Marketplace updates:**
- Updated marketplace to v1.8.0
- Added transcript-fixer plugin (category: productivity)
- Updated README.md with skill description and use cases
- Updated CLAUDE.md with skill listing and counts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-28 13:16:37 +08:00
daymade
8a4c7cfb10 Release v1.7.0: Add repomix-safe-mixer skill
Add new security-focused skill for safely packaging codebases with repomix
by automatically detecting and removing hardcoded credentials.

New skill: repomix-safe-mixer
- Detects 20+ credential patterns (AWS, Supabase, Stripe, OpenAI, etc.)
- Scan → Report → Pack workflow with automatic blocking
- Standalone security scanner for pre-commit hooks
- Environment variable replacement guidance
- JSON output for CI/CD integration

Also updates:
- skill-creator: Simplified path resolution best practices
- marketplace.json: Version 1.7.0, added repomix-safe-mixer plugin
- README.md: Updated to 14 skills, added repomix-safe-mixer documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 16:48:52 +08:00
daymade
974a93cb3a Release v1.6.0: Add youtube-downloader skill
- Add youtube-downloader v1.0.0
- Update marketplace to v1.6.0
- Comprehensive YouTube video/audio downloading with yt-dlp
- Android client workaround for nsig extraction issues
- Audio-only MP3 conversion
- Format selection and network error handling
- Demo GIF and comprehensive documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 14:56:00 +08:00
daymade
061f1a74f3 Release v1.5.0: Add ppt-creator skill to marketplace
New skill:
- ppt-creator v1.0.0: Professional presentation creation with dual-path PPTX generation
  - Structured content using Pyramid Principle and assertion-evidence framework
  - Data-driven charts with automatic synthesis and matplotlib rendering
  - Dual-path PPTX output (Marp CLI + document-skills:pptx)
  - Comprehensive documentation (4,916 lines across 13 files)
  - End-to-end orchestration mode for complete deliverables

Marketplace changes:
- Version: 1.4.0 → 1.5.0 (new skill added)
- Updated description to include presentation creation
- Added ppt-creator plugin entry with proper metadata

SKILL.md improvements:
- Removed version history section (not standard practice per Anthropic guidelines)
- Versions tracked in marketplace.json only
- SKILL.md reduced from 179 to 170 lines

Documentation:
- Added release workflow to CLAUDE.md for future reference

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 08:37:56 +08:00
daymade
524bb1ebfe Release v1.4.0: Add Cloudflare troubleshooting and UI design system extraction skills
This release adds two new professional skills to the marketplace:

1. cloudflare-troubleshooting - API-driven Cloudflare diagnostics
   - Investigate SSL errors, DNS issues, redirect loops
   - Systematic investigation using Cloudflare API
   - Bundled scripts for config checking and SSL mode fixes

2. ui-designer - Design system extraction from UI mockups
   - Extract color palettes, typography, spacing from screenshots
   - Generate design system documentation
   - Create implementation-ready UI design prompts

Changes:
- Updated marketplace.json to register 2 new skills (now 11 total)
- Bumped version from 1.3.0 to 1.4.0
- Enhanced .gitignore patterns for archives and build artifacts
- Updated metadata description to include new capabilities

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-25 15:32:24 +08:00
daymade
8c8d19013f Add cli-demo-generator skill (9th skill)
- Created comprehensive CLI demo generation skill with VHS automation
- Three approaches: automated, batch, and interactive recording
- Smart timing based on command complexity
- Complete documentation with VHS syntax reference and best practices
- Templates and examples for quick start
- Updated marketplace.json to v1.3.0
- Updated README.md and README.zh-CN.md with new skill
- Added to CHANGELOG.md

Skill features:
- auto_generate_demo.py: Automated generation from command lists
- batch_generate.py: Batch processing with YAML/JSON configs
- record_interactive.sh: Interactive recording with asciinema
- VHS tape file templates and examples
- 346-line SKILL.md following Anthropic best practices
- Grade A- in best practices review

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 19:38:58 +08:00
daymade
fd94d1b62e Release v1.3.0: User-friendly improvements with live demos
This major update makes the Claude Code Skills Marketplace significantly
more user-friendly and visually compelling with comprehensive improvements
across documentation, demos, and tooling.

## 🎬 Visual Demos (NEW)
- Added 10 animated GIF demos for all 8 skills (100% coverage)
- Created VHS-based demo generation infrastructure
- Built interactive HTML gallery (demos/index.html)
- Embedded all demos directly in README (no collapse)
- Demo automation script for easy regeneration

## 📚 Documentation
- Complete Chinese translation (README.zh-CN.md)
- Added CLAUDE.md for AI-assisted development
- Created QUICKSTART.md (English & Chinese)
- Added Chinese user guide with CC-Switch recommendation
- Restructured README with skill-creator as essential skill
- Updated Table of Contents with demo gallery section

## 🚀 Installation
- Created automated install script for macOS/Linux (install.sh)
- Created PowerShell install script for Windows (install.ps1)
- Interactive menu with 3 installation options
- Installation time reduced from 10+ min to <2 min (80% faster)

## 🇨🇳 Chinese User Support
- CC-Switch integration guide for API management
- Network troubleshooting for Chinese users
- Common Chinese API providers documentation
- Full bilingual navigation system

## 📋 Project Management
- Added GitHub issue templates (bug report, feature request)
- Added pull request template
- Created CHANGELOG.md following "Keep a Changelog"
- Added IMPLEMENTATION_SUMMARY.md
- Added RELEASE_NOTES_v1.3.0.md

## 🔧 Configuration
- Reordered marketplace.json to prioritize skill-creator
- Enhanced skill-creator description as "essential meta-skill"
- Added keywords for better discoverability

## 📊 Statistics
- Files Created: 37
- Files Modified: 2
- Demo GIFs: 10 (1.56 MB total)
- Languages: English + 简体中文
- Demo Coverage: 100% (8/8 skills)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 13:47:10 +08:00
daymade
94b40e0833 Initial release: Professional Claude Code Skills Marketplace
8 production-ready skills for enhanced Claude Code workflows:

1. github-ops - Comprehensive GitHub operations via gh CLI and API
   - PR/issue management, workflow automation, API interactions

2. markdown-tools - Document conversion to markdown
   - PDF/Word/PowerPoint/Confluence → Markdown with WSL support

3. mermaid-tools - Mermaid diagram generation
   - Extract and render diagrams from markdown to PNG/SVG

4. statusline-generator - Claude Code statusline customization
   - Multi-line layouts, cost tracking, git status, colors

5. teams-channel-post-writer - Microsoft Teams communication
   - Adaptive Cards, formatted announcements, corporate standards

6. repomix-unmixer - Repomix file extraction
   - Extract from XML/Markdown/JSON formats with auto-detection

7. skill-creator - Skill development toolkit
   - Init, validation, packaging scripts with privacy best practices

8. llm-icon-finder - AI/LLM brand icon finder
   - 100+ AI model icons in SVG/PNG/WEBP formats

Features:
- Individual skill installation (install only what you need)
- Progressive disclosure design (optimized context usage)
- Privacy-safe examples (no personal/company information)
- Comprehensive documentation with references
- Production-tested workflows

Installation:
/plugin marketplace add daymade/claude-code-skills
/plugin marketplace install daymade/claude-code-skills#<skill-name>

Version: 1.2.0
License: See individual skill licenses

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-22 23:42:29 +08:00