Conciseness

The body is ~20 lines of pure instruction with zero padding — every line directs an action ("Implement config parsing with safe defaults, strict validation, and clear error mapping", "Run focused source package tests, then `make verify`"). No concepts Claude already knows are explained, matching anchor 5 ("lean and efficient; assumes Claude's competence; every token earns its place").

Actionability

This is an instruction-only skill and the guidance is concrete: it names the template location (`sources/`), specific test categories ("config validation, preview decoding, pagination, and error handling"), specific threats ("loopback, unsafe schemes, malformed URLs, unbounded responses, and pagination loops"), and an executable command (`make verify`). It falls short of anchor 5 only because no example integration, file layout, or command for scaffolding is given, leaving minor gaps in executable detail.

Workflow Clarity

The six numbered steps give a coherent sequence (find template → implement config → add preview/runtime → harden network settings → write tests → run tests and `make verify`), with validation present in steps 5-6. It misses anchor 5 because there is no explicit feedback loop — nothing says "fix failures and re-run" after tests or verify fail — though the scaffolding context is not destructive/batch so the score-3 cap does not apply.

Progressive Disclosure

The skill is under 50 lines, needs no external references (none exist in the bundle), and is organized into two clearly labeled sections ("Instructions", "Boundaries"). Per the rubric's guideline for such skills, well-organized sections alone merit anchor 5.

Specificity

"Scaffold Cerebro source integrations" names the domain and one concrete action, and "source, preview, runtime, and test patterns" enumerates the pattern areas, but it stops short of listing multiple concrete actions like the anchor-5 examples ("extract text", "fill forms", "merge documents"). It sits above score 2 (which would be a generic action with no pattern detail) and below score 4 (which would list several distinct executable capabilities).

Completeness

The "what" is clear — scaffolding Cerebro source integrations — but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3. It is above score 2 because the "what" is concrete rather than vague, but below score 4 because "when" is entirely absent rather than merely implicit or incomplete.

Trigger Term Quality

Relevant keywords are present — "Cerebro", "source integrations", "scaffold" — but natural user phrasings such as "add a new data source", "connector", or "hook up a feed" are missing, and there are no synonyms or variations of the trigger terms. This matches anchor 3 ("some relevant keywords but missing common variations or synonyms"), not anchor 4 which would require broader natural-term coverage.

Distinctiveness Conflict Risk

"Cerebro source integrations" carves out a clear niche with distinct terms ("Cerebro", "source", "integration", "scaffold") that virtually no other skill would claim, giving minimal conflict risk. It clearly matches anchor 5 ("clear niche with distinct triggers; minimal conflict risk") rather than anchor 4, which presumes overlap risk with closely related skills.