AC Git
Commits, branches, merges, and rebases Git repositories, resolves conflicts, and recovers lost history. Use when the work touches a repo, commit, branch, merge, rebase, stash, tag, or submodule; when Git refuses a command — index.lock exists, push rejected as non-fast-forward, detached HEAD, dubious ownership, unrelated histories, conflict markers left behind; when something looks lost after a hard reset, a bad rebase, a deleted branch, or a dropped stash; when splitting a mixed change, wording commit messages, cleaning history before review, or force-pushing without wrecking a teammate's work; when a credential or a huge file got committed; when setting up worktrees, hooks, LFS, sparse checkout, signing, or separate work and personal identities. Not for CI pipeline YAML (github-actions, gitlab) or for composing the pull request description itself (pull-request).
Commits, branches, merges, and rebases Git repositories, resolves conflicts, and recovers lost history.
As a process C 61/100 · Has gaps — weak spots: 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-aws-keysecrets.md:31AWS access key ID (placeholder value)`expressions.txt` holds one rule per line: `lite…PLE==>REDACTED` or `regex:ghp_[A-Za-z0-9]{36}==>REDACTED`.placeholder
Files scanned: 23. 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) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 94 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4209 tokens
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 875: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.