transcript-fixer
Corrects speech-to-text transcription errors in meeting notes, lectures, and interviews using dictionary rules and AI. Learns patterns to build personalized correction databases. Use when working with transcripts containing ASR/STT errors, homophones, or Chinese/English mixed content requiring cleanup.
Install with Tessl CLI
npx tessl i github:fernandezbaptiste/claude-code-skills --skill transcript-fixer94
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It clearly specifies concrete capabilities (transcription error correction, pattern learning, dictionary rules), includes excellent trigger terms covering both technical and natural language variations, and has an explicit 'Use when...' clause with specific trigger conditions. The focus on ASR/STT transcription errors and multilingual content makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Corrects speech-to-text transcription errors', 'using dictionary rules and AI', 'Learns patterns to build personalized correction databases'. Covers specific document types (meeting notes, lectures, interviews). | 3 / 3 |
Completeness | Clearly answers both what (corrects transcription errors using dictionary rules and AI, learns patterns) AND when (explicit 'Use when...' clause specifying transcripts with ASR/STT errors, homophones, or mixed language content). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'transcription errors', 'meeting notes', 'lectures', 'interviews', 'ASR/STT errors', 'homophones', 'Chinese/English mixed content', 'transcripts', 'cleanup'. Includes both technical (ASR/STT) and natural language terms. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on speech-to-text transcription correction. The combination of ASR/STT errors, homophones, and Chinese/English mixed content creates distinct triggers unlikely to conflict with general text editing or translation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and progressive disclosure. The workflow is clear with proper validation checkpoints and the example session effectively demonstrates the correction pipeline. Minor verbosity in some sections (installation, repeated emphasis on saving corrections) prevents a perfect conciseness score.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some redundancy (e.g., explaining uv installation twice conceptually, repeating 'MUST save corrections' emphasis). The stages table and some explanatory text could be tightened. | 2 / 3 |
Actionability | Provides fully executable commands throughout, concrete examples with actual Chinese text showing before/after corrections, and copy-paste ready bash commands. The example session clearly demonstrates the pipeline's behavior. | 3 / 3 |
Workflow Clarity | Clear multi-stage pipeline with explicit numbered steps, validation command (--validate), and feedback loops (review-learned → approve pattern). The AI fallback strategy includes explicit recovery steps. | 3 / 3 |
Progressive Disclosure | Excellent structure with quick start upfront, detailed references clearly organized by use case (Critical, Getting started, Daily use, Advanced, Operations). One-level-deep references with clear signaling throughout. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.