tidb-issue-metadata-guard
Use when creating or editing TiDB GitHub issues so issue templates, labels, issue titles, and issue descriptions stay consistent with repository workflow. Trigger on tasks involving issue creation, bug reports, enhancement tracking issues, label selection, or searching for existing issues and PRs before filing a new one.
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/tidb-issue-metadata-guard/SKILL.mdQuality
Discovery
89%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 well-structured skill description with explicit 'Use when' and 'Trigger on' clauses that clearly define when the skill should be activated. The trigger term coverage is excellent, spanning multiple natural user phrases. The main weakness is that the specific capabilities could be more concrete—listing exact actions/outputs rather than general procedural areas.
Suggestions
Add more concrete action verbs describing specific outputs, e.g., 'Generates properly formatted issue descriptions from bug details, selects appropriate labels from the TiDB label taxonomy, and searches for duplicate issues before filing.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (TiDB GitHub issues) and mentions several actions like creating/editing issues, using templates, selecting labels, and searching for existing issues. However, the actions are more procedural guidance than concrete capabilities—it doesn't specify what concrete transformations or outputs it produces (e.g., 'generates issue descriptions from bug details', 'applies correct labels based on component'). | 2 / 3 |
Completeness | The description explicitly answers both 'what' (creating/editing TiDB GitHub issues with consistent templates, labels, titles, descriptions) and 'when' (with an explicit 'Use when' clause and a 'Trigger on' clause listing specific scenarios like issue creation, bug reports, enhancement tracking, label selection, and searching for existing issues). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'GitHub issues', 'issue creation', 'bug reports', 'enhancement tracking', 'label selection', 'issue templates', 'issue titles', 'issue descriptions', 'existing issues and PRs', and 'TiDB'. These cover a wide range of terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to TiDB repository GitHub issues with particular workflow conventions. The combination of 'TiDB', 'GitHub issues', 'issue templates', and 'label selection' creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 procedural skill with clear workflow sequencing, good validation checkpoints, and useful fallback strategies for label permissions. Its main weaknesses are the lack of concrete executable command examples (e.g., full `gh issue create` invocations) and some verbosity in the sub-bullet guidance that could be tightened. The content would also benefit from example input/output showing a properly formatted issue body.
Suggestions
Add at least one complete executable example showing a `gh issue create` or `gh issue edit` command with all relevant flags, including the file-based body approach mentioned in step 6.
Include a concrete before/after example of a well-formatted issue body (e.g., a bug report) to make the template-filling and `<details>` folding guidance immediately actionable.
Tighten the sub-bullets under step 3 and step 5 by merging related points—for example, combine the severity labeling rules into a compact table rather than separate bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining concepts Claude already knows (like what GitHub issues are), but some points are somewhat verbose and could be tightened. For example, the detailed severity labeling rules and the multiple sub-bullets under template filling could be more concise while retaining clarity. | 2 / 3 |
Actionability | The skill provides concrete guidance with specific rules (e.g., severity labeling, label fallback strategies, `<details>` usage), but lacks executable code/command examples. For instance, it mentions `gh issue create` and `gh issue edit` but never shows a complete command with flags. The file-based workflow in step 6 mentions materializing a file and diffing but doesn't show how. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered steps covering creation, editing, and labeling. It includes validation checkpoints (step 6: review against template, diff patched body before calling gh) and fallback/error recovery paths (label permission fallback chain: direct labels → /label comment → Suggested labels comment). The Quick Checks section serves as a final validation checklist. | 3 / 3 |
Progressive Disclosure | The content is reasonably well-organized with clear sections (Overview, Workflow, Quick Checks), but everything is inline in a single file with no references to supporting documents. The detailed severity rules, template-filling guidelines, and `<details>` usage patterns could be split into referenced files. However, given no bundle files exist, the inline approach is somewhat justified, though the content is getting long enough to benefit from separation. | 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.
- Repository
- pingcap/tidb
- Commit
e70762e
- 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.