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.

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-voice-transcription/SKILL.md
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 body is a strong, executable runbook with clear sequencing, validation checkpoints, and concrete troubleshooting, meriting top scores on actionability and workflow clarity; only minor conciseness trims and a possible split of troubleshooting into a referenced file keep progressive disclosure and conciseness just below 5.

DimensionReasoningScore

Conciseness

The body is efficient and free of padded conceptual explanations, with most sentences earning their place; a few explanatory lines (e.g. the container-env note and cost aside) could be trimmed, keeping it just below the leanest anchor.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands throughout (git fetch/merge, npm install/build, vitest run, curl key check, log tailing) covering the common install/verify/troubleshoot cases.

5 / 5

Workflow Clarity

A clear four-phase sequence with an explicit validation checkpoint ("All tests must pass and build must be clean before proceeding") and feedback loops in the troubleshooting section for error recovery.

5 / 5

Progressive Disclosure

Well organized into clearly labeled phases and sections with no nested references, but at ~140 lines with troubleshooting inlined rather than split out, it is slightly short of the cleanest one-level-deep reference structure.

4 / 5

Total

18

/

20

Passed

Description

61%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 states what the skill does and is specific to a recognizable niche, but it omits an explicit "Use when..." trigger clause, which caps completeness and distinctiveness below their top anchors.

Suggestions

Add an explicit trigger clause, e.g. "Use when adding voice message transcription to a NanoClaw WhatsApp channel, or when the user wants to transcribe WhatsApp voice notes."

Include common synonyms/extensions to broaden trigger coverage, such as "audio messages" and "transcribe audio".

Name a couple more concrete actions (e.g. download and deliver the transcript to the agent) to lift specificity toward 5.

DimensionReasoningScore

Specificity

Names the domain (voice transcription via Whisper for WhatsApp/NanoClaw) and two concrete actions ("Automatically transcribes" voice notes so the agent can "read and respond to them"), but coverage is narrow rather than comprehensive.

3 / 5

Completeness

Has a clear "what" (transcribe WhatsApp voice notes using Whisper) but no explicit "Use when..." trigger clause, so "when" is only weakly implied; per the rubric a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("voice message", "voice notes", "transcription", "WhatsApp") with good coverage; a few common synonyms (e.g. "audio messages", "transcribe audio") are missing, keeping it just below 5.

4 / 5

Distinctiveness Conflict Risk

Targets a specific niche (WhatsApp voice transcription for NanoClaw via Whisper) with distinct triggers and minimal overlap risk; slightly short of 5 only because it lacks explicit trigger phrasing that would fully disambiguate it.

4 / 5

Total

14

/

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.