AC Git Branch Janitor
Git branch cleanup assistant. Audits all local and remote branches, categorizes them as safe-to-delete (merged), stale-unmerged (old + no open PR), or active. Detects branches that exist locally but not on remote (orphaned), finds branches with no commits ahead of main, and optionally cross-references GitHub/GitLab PRs to confirm merge status. Outputs a prioritized delete plan with one copy-paste cleanup command. Zero external API required for local audit; optional GitHub CLI for PR status. Triggers on "clean up branches", "stale branches", "branch cleanup", "delete old branches", "git branch audit", "/git-branch-janitor".
As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 23 mutating operations with no state check
- 40Consistency. Frontmatter name (Git Branch Janitor) differs from the folder (phy-git-branch-janitor)
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 17 steps
- 100Execution cost. Instruction body is 2371 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 630: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (16 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.