CtrlK
BlogDocsLog inGet started
Tessl Logo

cerebro-source-integration

Scaffold Cerebro source integrations following existing source, preview, runtime, and test patterns.

84

1.21x
Quality

Does it follow best practices?

Impact

95%

1.21x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, actionable, and well-organized for a single-purpose instruction skill, with concrete named targets and a clear sequenced workflow. The only weakness is a soft, hedged verification checkpoint rather than an explicit validate-fix-retry loop.

Suggestions

Make the verification step a hard gate instead of "when feasible", e.g. "Run focused source package tests; if any fail, fix and re-run before proceeding to `make verify`" to add an explicit feedback loop.

Consider an explicit ordered checkpoint after config parsing/validation (e.g., 'confirm validation passes before adding preview/runtime behavior') to strengthen the workflow for this batch-oriented task.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — e.g. "Implement config parsing with safe defaults, strict validation, and clear error mapping" — with no concept explanation Claude already knows, matching the anchor where every token earns its place.

3 / 3

Actionability

Guidance names concrete targets (the `sources/` directory, `make verify`, and specific test categories: config validation, preview decoding, pagination, error handling); for an instruction-only skill this specific, actionable guidance is not penalized for lacking code.

3 / 3

Workflow Clarity

The six steps are clearly sequenced and include a verification step ("Run focused source package tests, then `make verify` when feasible"), but the "when feasible" hedge and absence of an explicit fix-and-retry feedback loop make the checkpoint implicit rather than a hard gate.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no external references needed, and content is organized into clean "Instructions" and "Boundaries" sections, which per the guideline lets progressive disclosure score 3 on well-organized sections alone.

3 / 3

Total

11

/

12

Passed

Description

67%

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 well-scoped to a distinct niche, but it omits any explicit 'Use when...' trigger guidance, which caps completeness and weakens trigger-term quality. Adding a natural usage trigger would lift the two lowest dimensions.

Suggestions

Append an explicit trigger clause such as 'Use when adding or modifying a Cerebro source integration under sources/' to answer when the skill applies.

Include natural phrasings a user would actually say (e.g., 'add a new source', 'wire up a source connector') alongside the technical terms to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete facets being scaffolded — "source, preview, runtime, and test patterns" — beyond a single verb, matching the anchor that lists several specific concrete actions rather than vague language.

3 / 3

Completeness

It states what the skill does ("Scaffold Cerebro source integrations following existing...patterns") but provides no explicit 'when to use it' guidance; per the guideline a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

"Cerebro source integrations" provides some relevant keywords a project user might say, but it lacks common natural variations and a 'Use when...' phrasing, fitting the anchor with some relevant keywords but missing common variations.

2 / 3

Distinctiveness Conflict Risk

"Cerebro source integrations" names a specific project plus a specific task, forming a clear niche unlikely to trigger the wrong skill, matching the anchor for a clear distinct niche.

3 / 3

Total

10

/

12

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
writer/cerebro
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.