AC git-workflow
Use this skill for any git commit, pull request, or release task. Invoke immediately when the user wants to: stage and commit changes, write a commit message, push code, create a PR or MR, tag a release, or update CHANGELOG. Triggers on: 「帮我提交」「commit」「提交代码」「创建 PR」「发布版本」「打 tag」 「推代码」, or English equivalents like "commit my changes", "create a pull request", "release v", "write a commit message", "push this branch". Do NOT trigger for: bulk repo syncing (use code-sync), general git questions without commit/PR intent, or Yunxiao MR creation (use yunxiao skill).
As a process C 56/100 · Has gaps — weak spots: result and completion, consistency, running it twice
How to improve
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 33 mutating operations with no state check
- 40Consistency. Frontmatter name (git-workflow) differs from the folder (nini-git-workflow)
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 25 steps, 1 vague phrases
- 100Execution cost. Instruction body is 1136 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 565: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.