AC code-workflow
4-stage code-change workflow: research → plan → user review → implement (TDD). Topics — steps (Step 0-3: resume + research + plan + review + branch), implement (Step 4: TDD + build + commit), pr (capture + PR with image/GIF/video). For issue implementation, tracked tasks, new features. TDD default (opt out --no-tdd). github-flow auto-companion on GitHub repos. Use when: "coding workflow", "research plan implement", "write plan", "plan md", "user review", "code plan", "code changes", "PR with screenshots", "pull request", "capture and PR".
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "depends-on" - note
frontmatter-keyunknown frontmatter key "triggers"
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
- 30Running it twice. 12 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1937 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 544: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.