CtrlK
BlogDocsLog inGet started
Tessl Logo

voice-note-ingest

Ingest a voice note with exact-phrasing preservation (never paraphrased). Routes content to originals/, concepts/, people/, companies/, ideas/, personal/, or voice-notes/ based on a decision tree. The user's exact words are the signal.

57

Quality

66%

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 ./skills/voice-note-ingest/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-organized and actionable, with a clear pipeline, a concrete decision tree, and a copy-paste brain-page template, but it lacks explicit validation checkpoints in its workflow and carries some test-scaffold boilerplate that adds tokens without aiding execution.

DimensionReasoningScore

Conciseness

The body is largely lean — pipeline, decision tree, page skeleton, and anti-patterns are all actionable content with no explaining of concepts Claude already knows — but the 'Contract' and 'Output Format' sections explicitly exist 'for the conformance test', adding non-instructional tokens that could be trimmed.

4 / 5

Actionability

Concrete, copy-paste-ready guidance is present throughout — the full brain-page markdown skeleton, a first-match-wins decision tree with exact destination slugs, citation format, and a naming example — with only minor gaps such as the hand-wavy STORE step ('pluggable per src/core/storage.ts') and the absence of a concrete transcription command.

4 / 5

Workflow Clarity

The five-step pipeline (STORE → TRANSCRIBE → ROUTE → WRITE → CROSS-LINK) is clearly sequenced and the skill is single-note/non-batch so the destructive-batch cap does not apply, but there are no explicit validate-then-fix checkpoints; the Anti-Patterns list acts only as an implicit checklist, matching the 'clear sequence with minor validation gaps' anchor.

4 / 5

Progressive Disclosure

Structure is good with clear section headers and well-signaled one-level-deep references (the top blockquote conventions for quality.md and _brain-filing-rules.md, plus a Related skills section), but no bundle files are provided and the doc is a single monolithic file with a long inline page skeleton that could be split out, keeping it at the 'good structure, minor gaps' anchor rather than 5.

4 / 5

Total

16

/

20

Passed

Description

58%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 and names a clear niche with enumerated routing destinations, but it lacks an explicit 'Use when...' trigger clause and only carries one natural keyword ('voice note'), capping completeness and trigger-term quality at 3.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g., 'Use when the user sends an audio or voice message via Telegram, voice memo upload, or audio attachment').

Broaden trigger-term coverage in the description to include synonyms users actually say: 'voice memo', 'audio message', and 'transcribe and file'.

Disambiguate from sibling exact-phrasing skills by noting voice-only scope (e.g., 'for audio/voice input; use idea-ingest for typed text').

DimensionReasoningScore

Specificity

The description names concrete actions — 'Ingest a voice note with exact-phrasing preservation (never paraphrased)' and 'Routes content to originals/, concepts/, people/, companies/, ideas/, personal/, or voice-notes/ based on a decision tree' — with all seven routing destinations enumerated; it falls short of a 5 because there are really only two distinct actions (ingest/preserve and route) rather than a comprehensive list of several.

4 / 5

Completeness

It gives a clear 'what' (ingest voice notes, preserve exact phrasing, route via decision tree) but contains no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3.

3 / 5

Trigger Term Quality

The description includes the natural phrase 'voice note' but omits common synonyms a user would actually say ('voice memo', 'audio message', 'transcribe'), matching the anchor that has some relevant keywords but misses common variations.

3 / 5

Distinctiveness Conflict Risk

The voice-note niche is distinct and audio-specific with minimal conflict risk, but it sits adjacent to related exact-phrasing capture skills (idea-ingest, signal-detector) creating minor overlap risk, matching the 'mostly distinct' anchor rather than the fully unambiguous 5.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing, 2 suspicious

Warning

Total

14

/

16

Passed

Repository
garrytan/gbrain
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.