CtrlK
BlogDocsLog inGet started
Tessl Logo

audio-cog

OpenSquilla-compatible audio generation adapter for webpage audio requests. Prefer OpenRouter config/API key in OpenSquilla; preserve the upstream CellCog workflow only as optional ClawHub provenance.

60

Quality

71%

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 ./src/opensquilla/skills/bundled/audio-cog/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 tight, highly actionable contract with exact request shapes, exit codes, and explicit failure-label validation checkpoints. It is well-structured and concisely written, with only minor room to externalize the detailed API contract into a reference file.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — exact request shape, required headers, and exit codes are stated without explaining what an SSE stream or base64 is. A few sentences are long but every token earns its place; minor trimming possible. Not a 5 because a few explanatory sentences (e.g. the rationale paragraphs) could be slightly tighter; not a 3 because there is no padded explanation of concepts Claude already knows.

4 / 5

Actionability

Fully executable guidance: the exact JSON request body, required `stream: true` and `audio.format: pcm16` fields, the SSE decode-concatenate-WAV procedure, manifest line format, and exit codes (78, 0) are copy-paste ready and cover the common case. Not a 4 because there are no meaningful gaps — the contract is complete and specific.

5 / 5

Workflow Clarity

Clear sequence with explicit validation checkpoints and feedback: pre-submit lease check emitting `AUDIO_CONFIG_NEEDED` and exit 78, model-capability check emitting `AUDIO_MODEL_UNSUPPORTED`, and post-submission degradation paths with structured replacement slots. The failure labels act as error-recovery feedback loops. Not a 4 because checkpoints are explicit and recovery guidance is present, not merely implied.

5 / 5

Progressive Disclosure

Well-organized into clear sections (Meta-Skill Entrypoint, OpenSquilla Compatibility Contract, OpenRouter Audio API Contract) with a single real bundle file (`scripts/openrouter_audio.py`, referenced via the entrypoint) and no nested references; lean overview. Not a 5 because the fairly detailed OpenRouter API contract block could arguably live in a separate reference file for a cleaner overview; not a 3 because structure and signaling are already good.

4 / 5

Total

18

/

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 clearly states the skill's role as an OpenSquilla-compatible OpenRouter audio adapter and names its domain, but it omits an explicit 'Use when...' trigger clause and lacks common synonyms users would say. It is distinct but could be more specific and trigger-friendly.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a webpage or meta-skill needs AI-generated narration, voiceover, or sound audio via OpenRouter.'

Include common synonyms and file extensions users say (voiceover, narration, TTS, .wav) to improve trigger term coverage.

List 1-2 more concrete actions (e.g. 'generates spoken narration WAV files, resolves OpenRouter audio config') to lift specificity from 3 to 4.

DimensionReasoningScore

Specificity

Quotes "audio generation adapter for webpage audio requests" and "preserve the upstream CellCog workflow only as optional ClawHub provenance" — names the domain with 1-2 concrete actions, but the verb set stays generic ("adapter", "preserve") without enumerating multiple specific actions. Not a 2 because it does name a concrete capability domain and role; not a 4 because no list of several specific actions.

3 / 5

Completeness

Clear "what" (audio generation adapter for webpage audio requests) but no "Use when..." / when-to-invoke trigger clause; the guideline caps completeness at 3 for a missing explicit trigger. Not a 2 because the what is clear and specific rather than vague; not a 4 because no when-guidance exists.

3 / 5

Trigger Term Quality

Natural terms present ("audio generation", "webpage audio requests", "OpenRouter", "API key") but common user synonyms and extensions are missing (voiceover, narration, TTS, .wav, sound effects). Not a 4 because keyword coverage lacks those common variations; not a 2 because the included terms are relevant rather than purely generic.

3 / 5

Distinctiveness Conflict Risk

Niche scope (OpenSquilla-compatible OpenRouter audio adapter for webpages) with distinct triggers and low overlap with other skills; mostly distinct with minor overlap risk against a generic audio skill. Not a 3 because it is more specific than "works with document files"-level overlap; not a 5 because the trigger phrasing could be sharper to fully minimize conflict.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
TokenRhythm/opensquilla
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.