Use when creating or editing TiDB pull requests so PR title scope, PR template fields, hidden HTML comments, and bot-parsed checklist sections stay intact. Trigger on tasks involving PR creation, PR body updates, issue linking from a PR, test checklist updates, or investigating labels like do-not-merge/needs-tests-checked.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that clearly defines its niche (TiDB PR formatting and template compliance), lists concrete actions, and provides explicit trigger guidance. The domain-specific terminology and label references make it highly distinguishable from generic PR or git skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: PR title scope formatting, PR template fields, hidden HTML comments, bot-parsed checklist sections, issue linking, test checklist updates, and label investigation. | 3 / 3 |
Completeness | Clearly answers both 'what' (maintaining PR title scope, template fields, HTML comments, bot-parsed sections) and 'when' with explicit triggers ('Use when creating or editing TiDB pull requests', 'Trigger on tasks involving PR creation, PR body updates, issue linking...'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'pull requests', 'PR title', 'PR body', 'PR creation', 'issue linking', 'test checklist', 'do-not-merge/needs-tests-checked', and 'TiDB'. Good coverage of domain-specific terms a user working on TiDB PRs would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to TiDB pull requests with unique triggers like 'bot-parsed checklist sections', 'hidden HTML comments', and the specific label 'do-not-merge/needs-tests-checked'. Unlikely to conflict with generic PR or git skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured skill that clearly defines the workflow for TiDB PR metadata management with good validation steps. Its main weaknesses are the lack of concrete examples (e.g., a sample PR body showing mutable vs. immutable sections) and the absence of supporting bundle files that would make the guidance more actionable and self-contained.
Suggestions
Add a concrete before/after example showing a PR body with mutable sections highlighted vs. immutable HTML comments and headings that must be preserved.
Include a sample PR title example inline, e.g., `planner, executor: add partition pruning for hash joins` to make the title format immediately clear.
Consider providing a trimmed version of the PR template inline or as a bundle file so Claude doesn't need to read it from the repo every time.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining basic concepts, but some points could be tightened. For example, step 6 ('Prefer file-based edits for GitHub metadata') adds moderate value but is somewhat verbose in its explanation. The Quick Checks section partially duplicates guidance already given in the workflow. | 2 / 3 |
Actionability | The skill provides specific guidance on what to preserve and what to edit, and includes one concrete command (`gh pr create -T .github/pull_request_template.md`). However, it lacks executable examples of actual PR body edits, before/after snippets showing the template structure, or concrete examples of the title format with real module names. The guidance is specific but not fully copy-paste ready. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with distinct steps for new vs. existing PRs. Step 7 provides an explicit validation checkpoint (re-read PR, check bot labels, diff against template if unexpected). The feedback loop of checking labels and diffing before making further changes is well-articulated for this type of metadata-sensitive operation. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (Overview, Workflow, Quick Checks), but everything is inline in a single file. It references `.github/pull_request_template.md` and `tidb-issue-metadata-guard` but provides no bundle files or linked documents. For a skill of this complexity, an example PR body or a reference to the actual template structure would improve navigation and understanding. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
e70762e
Table of Contents
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.