cerebro-source-integration

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

1.21x

Quality

63%

Does it follow best practices?

Impact

95%

1.21x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.factory/skills/cerebro-source-integration/SKILL.md

Quality

Content

72%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 exceptionally lean and well-structured for a simple scaffolding skill, but its guidance is high-level: it lacks executable examples, concrete file/template paths, and an explicit validate-fix-retry loop. Adding a concrete reference template path and a feedback-loop step would raise actionability and workflow clarity.

Suggestions

Name a concrete template to copy from (e.g. "Copy sources/<closest>/ as a starting point") and reference the config/preview/runtime files to edit, to improve actionability.

Add a validate-fix-retry loop after step 6, e.g. "If tests or `make verify` fail, fix and re-run until green" rather than hedging with "when feasible".

Optionally include a short config-validation code snippet or pointer to the validation helper used by existing integrations to make guidance executable.

Dimension	Reasoning	Score
Conciseness	The body is ~20 lines with no padding and no explanation of concepts Claude already knows; every line is actionable instruction, matching the "lean and efficient; every token earns its place" anchor.	5 / 5
Actionability	It names concrete concerns (loopback, unsafe schemes, malformed URLs, unbounded responses, pagination loops) and points to "the closest existing integration under sources/" plus `make verify`, but provides no executable code, templates, or specific commands beyond `make verify`, so guidance is directional rather than copy-paste ready.	3 / 5
Workflow Clarity	Six numbered steps give a clear sequence and step 6 includes verification (run tests, `make verify`), but validation is a single hedged terminal step ("when feasible") with no intermediate checkpoints and no validate-fix-retry feedback loop, fitting the "sequence present but checkpoints missing or implicit" anchor.	3 / 5
Progressive Disclosure	Under 50 lines with no external bundle files and no need for references, it is cleanly organized into ## Instructions and ## Boundaries sections, qualifying for the simple-skill exception that well-organized sections earn a 5.	5 / 5
	Total	16 / 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 is specific and distinct but stops short of explicit activation guidance, capping its strongest-weighted dimension. Adding a "Use when..." trigger clause with natural synonyms would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when adding or modifying a Cerebro source integration under sources/."

Add natural synonyms users might say (e.g. "connector", "ingest source", "data source") to broaden trigger-term coverage.

List one or two more concrete actions (e.g. "validate config", "wire preview and sync handlers") to push specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	"Scaffold Cerebro source integrations" names the domain and a primary action, and "following existing source, preview, runtime, and test patterns" references four pattern areas, but it does not enumerate multiple distinct concrete actions, so it sits at the domain-plus-1-2-actions anchor rather than the several-specific-actions anchor.	3 / 5
Completeness	The "what" is clear (scaffold integrations following named patterns), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3 with the "when" only weakly implied.	3 / 5
Trigger Term Quality	It surfaces relevant terms ("Cerebro source integrations", "source", "preview", "runtime", "test patterns") a user in this codebase might say, but offers no synonyms, natural paraphrases, or file extensions, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	"Cerebro source integrations" carves a specific niche tied to a named product, with only minor overlap risk against related Cerebro skills (e.g. destination or preview-only integrations), fitting the "mostly distinct; minor overlap risk" anchor.	4 / 5
	Total	13 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: writer/cerebro
Path: .factory/skills/cerebro-source-integration/SKILL.md
Commit: b8ea1b3

Reviewed: about 4 hours 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.