BC git-repo
Git repository and SourceGit integration. Topics — clone (ghq), conflict-dry-run (isolated merge test), credential-helper (multi-account HTTPS token), doctor (hook health & compliance audit — Tier 1 Base + Tier 2 Conditional taxonomy), fix-worktree (bare repo recovery), githooks (hook silently never runs — hooksPath precedence, passthrough chain, install trade-off), isolate-hunk (stage own edit amid unrelated content), merge-duplicate, rebase-audit (accidental-revert detection during an active rebase), to-ghq (formerly migrate), to-bare, worktree-register (metadata register/relink), patrol (batch inspect), move-worktree (register/reclaim merged PR), rename-worktree, sourcegit, ssh-key (multi-account SSH map), worktree (inventory + reuse + create), worktree-drift-sync (mirror fix across worktrees safely). Use when: "reuse worktree", "multi-account clone", "Repository not found", "wrong account", "concurrent uncommitted edit", "accidental revert", "githooks ignored", "hook not running", "core.hooksPath", "hook not firing", "repo doctor", "hook health", "diagnose hooks", "check hooks" triggers.
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 34. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1109 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 70Failures and branches. 4 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 42 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3735 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (6 tags): a typed call is more reliable
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 1108: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -34 of 8 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.