CtrlK
BlogDocsLog inGet started
Tessl Logo

use-local-whisper

Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is highly actionable and exceptionally well-sequenced with validation and feedback loops, keeping token use mostly efficient. Its only weakness is that all material lives in a single inlined file with no progressive split.

Suggestions

Consider extracting the Configuration and Troubleshooting sections into a reference file to improve progressive disclosure for the longer-than-50-line body.

Trim minor editorial padding such as 'good balance of speed and accuracy' to further tighten conciseness.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence, with only minor over-explanation (e.g., 'good balance of speed and accuracy' and the troubleshooting section re-pointing to Phase 3) that could be trimmed.

4 / 5

Actionability

It provides fully executable, copy-paste-ready commands throughout — grep checks, brew install, curl model download, git fetch/merge, npm run build, launchctl, and a manual ffmpeg/whisper-cli test — covering the common cases.

5 / 5

Workflow Clarity

Three phases (Pre-flight, Apply, Verify) are clearly sequenced with explicit validation checkpoints (already-applied skip, dependency OK/MISSING probes, build, test, log-pattern checks) and feedback loops via the Troubleshooting section and the merge error-recovery block.

5 / 5

Progressive Disclosure

The ~150-line single file is well-organized into phases and sections, but everything is inlined with no bundle files or one-level-deep references, leaving minor organization gaps relative to the well-split ideal.

4 / 5

Total

18

/

20

Passed

Description

73%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 clearly answers both what it does and when to use it within a distinct, low-conflict niche. It is strong on trigger phrasing and distinctiveness but only lists a single concrete action, limiting specificity.

Suggestions

Add one or two more concrete capabilities (e.g., 'transcribes audio with no API key or network') to lift specificity beyond a single action.

Broaden the 'when' clause with additional natural trigger phrases such as 'offline transcription' or 'on-device voice notes'.

DimensionReasoningScore

Specificity

Names the domain (voice transcription) and one concrete action — "Switches to whisper.cpp running on Apple Silicon" — but offers no broader list of capabilities, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

Both the 'what' (switch to local whisper.cpp) and 'when' ("Use when the user wants local voice transcription instead of OpenAI Whisper API") are present, but the trigger is a single narrow condition rather than multiple concrete trigger phrases.

4 / 5

Trigger Term Quality

"local voice transcription" and "instead of OpenAI Whisper API" are natural phrases a user would say, giving good keyword coverage, though synonyms like "on-device" or "offline transcription" are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — local whisper.cpp on Apple Silicon, WhatsApp only, requires voice-transcription skill applied first — with distinct triggers and minimal overlap with other skills.

5 / 5

Total

16

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jbaruch/nanoclaw-telegram
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.