feat(autoresearch-agent): fix critical bugs, package as plugin with 5 slash commands

**Bug fixes (run_experiment.py):**
- Fix broken revert logic: was saving HEAD as pre_commit (no-op revert),
  now uses git reset --hard HEAD~1 for correct rollback
- Remove broken --loop mode (agent IS the loop, script handles one iteration)
- Fix shell injection: all git commands use subprocess list form
- Replace shell tail with Python file read

**Bug fixes (other scripts):**
- setup_experiment.py: fix shell injection in git branch creation,
  remove dead --skip-baseline flag, fix evaluator docstring parsing
- log_results.py: fix 6 falsy-zero bugs (baseline=0 treated as None),
  add domain_filter to CSV/markdown export, move import time to top
- evaluators: add FileNotFoundError handling, fix output format mismatch
  in llm_judge_copy, add peak_kb on macOS, add ValueError handling

**Plugin packaging (NEW):**
- plugin.json, settings.json, CLAUDE.md for plugin registry
- 5 slash commands: /ar:setup, /ar:run, /ar:loop, /ar:status, /ar:resume
- /ar:loop supports user-selected intervals (10m, 1h, daily, weekly, monthly)
- experiment-runner agent for autonomous loop iterations
- Registered in marketplace.json as plugin #20

**SKILL.md rewrite:**
- Replace ambiguous "Loop Protocol" with clear "Agent Protocol"
- Add results.tsv format spec, strategy escalation, self-improvement
- Replace "NEVER STOP" with resumable stopping logic

**Docs & sync:**
- Codex (157 skills), Gemini (229 items), convert.sh all pick up the skill
- 6 new MkDocs pages, mkdocs.yml nav updated
- Counts updated: 17 agents, 22 slash commands

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Reza Rezvani
2026-03-13 14:38:59 +01:00
parent 6dc25df8fa
commit 7911cf957a
39 changed files with 1779 additions and 234 deletions

View File

@@ -1,6 +1,6 @@
site_name: Agent Skills — Skills, Agents & Personas for AI Coding Tools
site_url: https://alirezarezvani.github.io/claude-skills/
site_description: "177 production-ready skills, 16 agents, 3 personas, and an orchestration protocol for 11 AI coding tools. Reusable expertise for engineering, product, marketing, compliance, and more."
site_description: "177 production-ready skills, 17 agents, 3 personas, and an orchestration protocol for 11 AI coding tools. Reusable expertise for engineering, product, marketing, compliance, and more."
site_author: Alireza Rezvani
repo_url: https://github.com/alirezarezvani/claude-skills
repo_name: alirezarezvani/claude-skills
@@ -162,6 +162,12 @@ nav:
- "Tech Stack Evaluator": skills/engineering-team/tech-stack-evaluator.md
- Engineering - POWERFUL:
- Overview: skills/engineering/index.md
- "Autoresearch Agent": skills/engineering/autoresearch-agent.md
- "Autoresearch /ar:setup": skills/engineering/autoresearch-agent-setup.md
- "Autoresearch /ar:run": skills/engineering/autoresearch-agent-run.md
- "Autoresearch /ar:loop": skills/engineering/autoresearch-agent-loop.md
- "Autoresearch /ar:status": skills/engineering/autoresearch-agent-status.md
- "Autoresearch /ar:resume": skills/engineering/autoresearch-agent-resume.md
- "Agent Designer": skills/engineering/agent-designer.md
- "Agent Workflow Designer": skills/engineering/agent-workflow-designer.md
- "API Design Reviewer": skills/engineering/api-design-reviewer.md