AC commit-message-writer
Generate conventional, descriptive commit messages from git diffs. Analyzes staged changes or branch diffs and produces well-formatted commit messages following the Conventional Commits specification (feat, fix, chore, docs, refactor, test, etc.). Use when the user wants to: (1) Generate a commit message from 'git diff --staged', (2) Write a message for unpushed commits, (3) Rewrite a vague commit message, (4) Generate changelog entries from a range of commits, (5) Ensure team consistency with Conventional Commits. Best for developers, teams using standardized commit conventions, open-source maintainers, and anyone tired of 'fixed stuff' commit messages.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 40Consistency. Frontmatter name (commit-message-writer) differs from the folder (git-commit-gen)
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 100Steps. 17 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 904 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 662: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.