openai-whisper

Local speech-to-text with the Whisper CLI (no API key).

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/openai-whisper/SKILL.md

The canonical home for this skill is openai-whisper in openclaw/openclaw

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplar of lean, executable guidance: two ready-to-run commands plus genuinely non-obvious operational notes, with no wasted tokens. The only gap is minor markdown structure — section labels are plain text rather than headed sections.

Suggestions

Format 'Quick start' and 'Notes' as markdown headers (e.g. '## Quick start', '## Notes') to formalize the section structure.

Optionally note how to verify output succeeded (e.g. check the generated .txt/.srt file in --output_dir) for users running unattended.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — a one-line purpose, two copy-paste commands, and three non-obvious notes (cache path, default model, speed/accuracy tradeoff) with no padding or explanation of what Whisper is, matching the 'every token earns its place' anchor.	5 / 5
Actionability	Both Quick start bullets are fully executable commands with real flags, output formats, and example file paths covering the common transcription and translation cases, matching 'copy-paste ready commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	This is a simple single-purpose skill whose action (invoke whisper with these flags) is unambiguous; transcription is non-destructive so the destructive/batch validation cap does not apply, and the simple-skill exception permits a 5.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references (no references/scripts/assets bundles exist), it is well organized into purpose, Quick start, and Notes; held at 4 rather than 5 because 'Quick start' and 'Notes' are plain text rather than proper markdown section headers, a minor organization gap.	4 / 5
	Total	19 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly distinguishes the skill's niche, but it omits any 'Use when...' trigger guidance and lacks common synonyms like 'transcribe' or audio file extensions. This caps completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to transcribe or translate audio files locally without an API key.'

Include natural trigger terms users actually say, such as 'transcribe', 'audio', 'subtitles', and file extensions like '.mp3', '.m4a', '.srt'.

Optionally mention translation as a second concrete capability to lift specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	Names the domain ("speech-to-text") and tool ("Whisper CLI") with one concrete action plus the distinguishing "(no API key)" detail, but does not enumerate multiple actions like translation or subtitle export, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It gives a clear 'what' (local speech-to-text via Whisper CLI, no API key) but has no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap completeness cannot exceed 3; it is not a 2 because the 'what' is explicit and concrete.	3 / 5
Trigger Term Quality	"speech-to-text" and "Whisper" are natural terms a user might say, but common synonyms and extensions users actually utter ("transcribe", "audio", "subtitles", ".mp3", "SRT") are absent, so it sits at 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The "local" + "Whisper CLI" + "no API key" framing carves a clear niche distinct from API-based STT skills with only minor overlap risk against other transcription tools; not a 5 because no explicit trigger phrases are provided to fully minimize conflict.	4 / 5
	Total	13 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/openai-whisper/SKILL.md
Commit: 017761f

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.