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>
This commit is contained in:
daymade
2025-10-28 13:16:37 +08:00
parent d1041ac203
commit bd0aa12004
44 changed files with 7432 additions and 8 deletions

View File

@@ -0,0 +1,89 @@
#!/usr/bin/env python3
"""
Argument Parser - CLI Argument Configuration
SINGLE RESPONSIBILITY: Configure command-line argument parsing
"""
from __future__ import annotations
import argparse
def create_argument_parser() -> argparse.ArgumentParser:
"""
Create and configure the argument parser for transcript-fixer CLI.
Returns:
Configured ArgumentParser instance
"""
parser = argparse.ArgumentParser(
description="Transcript Fixer - Iterative correction tool",
formatter_class=argparse.RawDescriptionHelpFormatter
)
# Setup commands
parser.add_argument(
"--init",
action="store_true",
help="Initialize ~/.transcript-fixer/"
)
# Correction management
parser.add_argument(
"--add",
nargs=2,
metavar=("FROM", "TO"),
dest="add_correction",
help="Add correction"
)
parser.add_argument(
"--list",
action="store_true",
dest="list_corrections",
help="List all corrections"
)
# Correction workflow
parser.add_argument(
"--input", "-i",
help="Input file"
)
parser.add_argument(
"--output", "-o",
help="Output directory"
)
parser.add_argument(
"--stage", "-s",
type=int,
choices=[1, 2, 3],
default=3,
help="Run stage (1=dict, 2=AI, 3=full)"
)
parser.add_argument(
"--domain", "-d",
default="general",
help="Correction domain"
)
# Learning commands
parser.add_argument(
"--review-learned",
action="store_true",
help="Review learned suggestions"
)
parser.add_argument(
"--approve",
nargs=2,
metavar=("FROM", "TO"),
help="Approve suggestion"
)
# Utility commands
parser.add_argument(
"--validate",
action="store_true",
help="Validate configuration and JSON files"
)
return parser