cerebro-creation

Implement focused Cerebro issues or PR follow-ups from Droid Create workflows.

0.97x

Quality

47%

Does it follow best practices?

Impact

96%

0.97x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.factory/skills/cerebro-creation/SKILL.md

Quality

Discovery

22%

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 too vague and relies heavily on proprietary terminology without explaining what concrete actions the skill performs. It lacks an explicit 'Use when...' clause and does not provide enough detail for Claude to reliably select this skill from a large pool. The proprietary terms offer some distinctiveness but don't compensate for the lack of specificity and completeness.

Suggestions

Add a 'Use when...' clause specifying explicit triggers, e.g., 'Use when the user references a Cerebro issue number, asks to implement a Droid Create follow-up, or mentions PR feedback from Cerebro.'

List concrete actions the skill performs, such as 'reads Cerebro issue details, generates implementation code, creates branches, and submits pull requests for review.'

Clarify what 'Cerebro' and 'Droid Create workflows' are in brief context so Claude can distinguish this skill from generic issue-tracking or PR management skills.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'implement focused issues' and 'PR follow-ups' without specifying concrete actions. It references proprietary terms ('Cerebro', 'Droid Create') without explaining what actions are actually performed.	1 / 3
Completeness	The description weakly addresses 'what' (implement issues/PR follow-ups) but provides no explicit 'when' clause or trigger guidance. There is no 'Use when...' statement, which per the rubric should cap completeness at 2, and the 'what' is also too vague to score higher than 1.	1 / 3
Trigger Term Quality	It includes some potentially useful trigger terms like 'Cerebro issues', 'PR follow-ups', and 'Droid Create workflows', but these are highly specific internal/proprietary terms. A user familiar with the system might use 'Cerebro' or 'Droid Create', but common variations and natural language triggers are missing.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Cerebro' and 'Droid Create' provides some distinctiveness through proprietary naming, but 'implement issues' and 'PR follow-ups' are generic enough to overlap with other development or issue-tracking skills.	2 / 3
	Total	6 / 12 Passed

Implementation

72%

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

This is a concise, well-structured skill that efficiently communicates a workflow for implementing Cerebro issues. Its main weakness is a lack of concrete, executable guidance—no specific commands, example file paths, or code snippets that would make the instructions fully actionable. The workflow would also benefit from explicit validation/error-recovery steps when tests or verification fail.

Suggestions

Add concrete command examples for key steps (e.g., specific `go test ./pkg/...` invocations, `make verify` expected output patterns, or example file paths in the Cerebro repo).

Include a feedback loop for test/verify failures: what to check, how to interpret errors, and when to retry vs. stop.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. Every line conveys actionable information without explaining concepts Claude already knows (Go, Makefiles, CI pipelines). No padding or unnecessary context.	3 / 3
Actionability	The guidance is specific in intent (e.g., 'run targeted tests first, then make verify') but lacks concrete executable examples—no specific commands, code snippets, or file paths. Phrases like 'match existing Go package boundaries' and 'source connector patterns' are directional but not copy-paste actionable.	2 / 3
Workflow Clarity	Steps are sequenced logically (read → identify → match → test → verify → leave changes), but there are no explicit validation checkpoints or feedback loops. For a workflow involving code changes and test runs, there's no guidance on what to do if tests fail or if 'make verify' surfaces issues.	2 / 3
Progressive Disclosure	For a simple, short skill under 50 lines with no need for external references, the content is well-organized into clear sections (Instructions, Stop Conditions). No monolithic walls of text or unnecessary nesting.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: writer/cerebro
Commit: 3aeaf20

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.