stage
Stage files, run pre-commit, fix failures, loop until clean
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/stage/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is a terse action sequence that conveys the basic workflow but lacks a 'Use when...' clause, detailed capability descriptions, and sufficient trigger terms. It reads more like a pipeline step list than a skill description that would help Claude reliably select it from a large skill set.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to commit code and needs pre-commit hooks to pass, or mentions pre-commit, linting, or formatting checks.'
Expand trigger terms to include natural user language like 'linting', 'git hooks', 'pre-commit hooks', 'code formatting', 'commit preparation', and 'fix lint errors'.
Add more specificity about what kinds of failures are fixed (e.g., 'auto-fix linting, formatting, and type-check errors raised by pre-commit hooks').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names several concrete actions (stage files, run pre-commit, fix failures, loop until clean) but they are terse and lack detail about what kinds of failures are fixed or how files are staged. | 2 / 3 |
Completeness | Describes what the skill does (stage, run pre-commit, fix, loop) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also quite thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'pre-commit', 'stage files', and 'fix failures' that users might mention, but misses common variations like 'linting', 'git hooks', 'code formatting', 'commit checks', or 'pre-commit hooks'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'pre-commit' provides some distinctiveness, but 'stage files' and 'fix failures' are generic enough to potentially overlap with general git workflow or code fixing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise workflow skill that clearly defines a feedback loop with explicit iteration limits and failure handling. Its main weakness is that commands are referenced inline rather than in code blocks, and the file exclusion guidance could be more concrete. Overall it's a strong, lean skill that respects Claude's intelligence.
Suggestions
Wrap commands like `git add`, `pre-commit run --all-files`, and `git diff --cached --name-only` in proper code blocks for better readability and copy-paste readiness.
Add a concrete example of how to exclude sensitive files during staging (e.g., using pathspec negation or listing specific patterns to avoid).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what git or pre-commit are. The skill assumes Claude knows these tools and focuses purely on the workflow steps. | 3 / 3 |
Actionability | Provides specific commands (git status, git add, pre-commit run --all-files, git diff --cached --name-only) but they're inline rather than in executable code blocks. The exclusion criteria (Step 1.2) are clear but lack concrete examples of how to exclude files (e.g., specific glob patterns or git add commands with exclusions). | 2 / 3 |
Workflow Clarity | Excellent multi-step workflow with a clear feedback loop (pre-commit run → fix → re-stage → retry) capped at 5 iterations, explicit failure handling (report and stop), and a validation checkpoint before proceeding. The sequence is unambiguous with clear exit conditions. | 3 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized into logical numbered steps with clear section headers. No bundle files are needed for this scope. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- PaloAltoNetworks/shifter
- Commit
a7c1694
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.