AB commit-tidy
Analyze staged/committed changes and recommend split, squash, or commit-message strategy. Topics — conflict-commit-review (per-chunk review gate for conflict-residue commit messages), hunk-split (single-hunk staging via git apply --cached), interactive-amend (worktree-based amend+rebase loop), soft-reset-amend (soft-reset top N + selective re-commit), staging-discipline (staged-set audit + sensitive-dir gate), security-scan (PUBLIC repo secret pattern check), message-discipline (Conventional Commit tags, PUBLIC English, --amend refresh). Use when: "commit split", "squash commits", "tidy commits", "amend earlier", "interactive amend", "soft reset", "rewrite commits", "PUBLIC repo commit", "secret in commit", "commit message", "commit author identity", "commit message English", "staging discipline", "hunk split", "stage one hunk", "git apply --cached", "non-interactive git add -p", "conflict commit", "Conflicts message", "review conflict resolution", "bad merge resolution".
As a process B 65/100 · Nearly there — weak spots: when it triggers, inputs and preconditions
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4053 tokens
- 100Steps. 55 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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 986: 120–800 characters recommended
- +2Single-language instructions
- +5Description quotes 21 example trigger phrases
- +4Structure: 27 headings
- +3Step-by-step instructions: 55 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.