BC github-flow
GitHub issue/PR workflow automation. Topics — auth-scope (gh CLI priority + account mapping + batch scope refresh + 404 checklist), commit-message-discipline (commit message authoring + amend refresh + PUBLIC English enforcement), dependencies (blocked-by/sub-issues via GraphQL), epic-bundle (deferred findings → Epic + sub-issues), expand (expand-vs-split mid-work), identity-auth (gh account map + scope refresh + GH_TOKEN fallback), merge (CI/review gates + no autonomous push), plan-to-issue (MD → issue body), pr (PR with test plan), publish (branch + draft PR + CI watch + ready + merge, one topic), push-guards (branch/push-reject/force-push/main-push), register (dup check + strategy), review (structured comments), review-apply (deferred feedback apply), sanitize (PUBLIC repo personal data scan), upstream-issue (external OSS feature/bug). Use when: "plan to issue", "issue register", "create PR", "PR body", "code review", "merge PR", "PR squash", "sanitize", "PII", "expand PR", "blocked by", "epic bundle", "upstream issue", "review apply", "sub-issue", "gh auth", "force push", "push reject", "branch change forbid", "auth scope", "account mapping", "scope refresh", "commit message", "PUBLIC repo English".
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1223 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 75Steps. 3 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1791 tokens
- 100Running it twice. Mutating operations check current state
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1222: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -33 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 23 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.