CtrlK
BlogDocsLog inGet started
Tessl Logo

add-voice-transcription

Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 a well-sequenced, fully executable workflow with strong validation gates and troubleshooting feedback loops, and it is appropriately structured as a single self-contained file. Its only weakness is minor conciseness redundancy in the API-key handling and one generic merge-conflict instruction.

DimensionReasoningScore

Conciseness

The body is lean and command-driven with almost no padding; project-specific facts ("The container reads environment from data/env/env, not .env directly", cost figures) earn their tokens. Minor trimmable redundancy remains: the OpenAI API key flow is handled in both Phase 1 and Phase 3, and "resolve them by reading the conflicted files and understanding the intent of both sides" tells Claude something it already knows, keeping it just below the fully lean anchor.

4 / 5

Actionability

Every phase uses copy-paste-ready commands: exact git remote/fetch/merge commands with a package-lock.json conflict fallback, npm build and vitest validation, a curl key-verification command, and a log-grep with named log signatures. The troubleshooting section covers the three most common failure modes with concrete causes and fixes.

5 / 5

Workflow Clarity

The four-phase sequence has explicit validation checkpoints: an idempotency check (skip to Phase 3 if src/transcription.ts exists), a prerequisite gate (WhatsApp merged first), a hard validation gate ("All tests must pass and build must be clean before proceeding"), a user-facing verification step, and symptom-to-cause troubleshooting feedback loops for error recovery.

5 / 5

Progressive Disclosure

There are no bundle files, and none are needed: the ~150-line body is a single cohesive workflow with well-organized, clearly headed sections rather than reference material that belongs in separate files. Navigation is easy and content is appropriately placed in the single SKILL.md.

5 / 5

Total

19

/

20

Passed

Description

70%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 specific, concrete, and clearly distinguishable, with good natural trigger terms. Its main weakness is the missing 'Use when...' clause, which leaves the triggering context implicit and caps completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when adding voice message support to a NanoClaw WhatsApp channel, or when voice notes arrive that the agent cannot read."

Broaden trigger coverage with synonyms such as "audio messages" and "speech-to-text" alongside "voice notes" and "transcription".

Mention the setup the skill performs (merging the skill branch and configuring an OpenAI API key) so the 'what' covers the full scope of the skill.

DimensionReasoningScore

Specificity

Names concrete actions ("Add voice message transcription", "Automatically transcribes WhatsApp voice notes") with specific tools (OpenAI's Whisper API, NanoClaw, WhatsApp). It lists several specific actions but omits aspects the skill covers such as API key configuration, fitting the 'minor gaps in coverage' anchor rather than the comprehensive anchor.

4 / 5

Completeness

The 'what' is clear and concrete (transcribes WhatsApp voice notes so the agent can read and respond), but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric guideline, a missing 'when' caps completeness at 3. It is not a 2 because the 'what' is fully explicit, and not a 4 because 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Includes natural phrases users would say: "voice message", "voice notes", "transcription", "WhatsApp". A few common variations are missing (e.g., "audio messages", "speech-to-text"), placing it just below the comprehensive synonym coverage anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Whisper-based WhatsApp voice transcription within NanoClaw) with distinct trigger terms, making it unlikely to fire for unrelated skills. It is specific to one platform, one channel, and one API, so overlap risk is minimal.

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.

Validation — 16 / 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.