CtrlK
BlogDocsLog inGet started
Tessl Logo

tidb-issue-metadata-guard

Create or edit TiDB issues, choose labels, or check for duplicates before filing.

65

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-structured instruction-only skill: a clearly sequenced workflow with real validation checkpoints, an escalation feedback loop for label permissions, and a final checklist. The only minor gaps are a few unexpanded gh command invocations and light redundancy between the new-issue and edit-issue content rules.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of padding — it never explains what GitHub or issues are, and every bullet states a skill-specific rule Claude could not infer. It sits at anchor 4 rather than 5 only because of minor repetition (the visible-summary/`<details>` rules are restated across the new-issue, edit-issue, and Quick Checks sections) and a few wordy phrasings that could be tightened.

4 / 5

Actionability

Concrete guidance throughout: exact paths (`.github/ISSUE_TEMPLATE/`), commands (`gh issue create`, `gh issue edit`, `/label <label name>`, `Suggested labels: ...`), concrete label names (`severity/major`, `severity/moderate`, `component/*`), and a concrete mechanism (`<details>` blocks). Anchor 5 is missed by minor gaps — no complete example invocations with flags (e.g. `gh issue edit --title ... --body-file ...`) and the duplicate-search step names no search command.

4 / 5

Workflow Clarity

The workflow has a clear numbered sequence (write → search → template → patch → label → file-based edits) with explicit validation checkpoints ("diff the patched body against the current issue body before calling gh", review against the template before calling gh), a genuine feedback loop for error recovery (label permissions missing → `/label` comment → `Suggested labels: ...` fallback), and a closing Quick Checks checklist — matching anchor 5's sequence + validation + feedback loop + checklist pattern.

5 / 5

Progressive Disclosure

There are no bundle files (references/, scripts/, assets/ are absent), and the ~50-line body needs none: it is cleanly organized into Overview, Workflow, and Quick Checks sections with no content that belongs in a separate file. Per the rubric's scoring note for short, single-purpose skills with no external references, this warrants a 5.

5 / 5

Total

18

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with concrete actions and good natural trigger terms for the TiDB issue-filing niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. "Use when creating, editing, or labeling TiDB GitHub issues, filing bug reports, or checking for duplicate issues before filing."

Mention one or two more natural trigger variations users would say, such as "bug report" or "GitHub issue", to broaden keyword coverage.

Optionally surface the template-application and label-severity aspects of the skill in the description to close the small coverage gap against what the skill actually does.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Create or edit TiDB issues, choose labels, or check for duplicates before filing" — in a named domain (TiDB issue tracking). It stops short of anchor 5 because coverage has minor gaps: it never mentions applying issue templates or patching existing issue bodies, both of which are core parts of the skill's workflow.

4 / 5

Completeness

The "what" is clear (create/edit issues, choose labels, check duplicates), but there is no "Use when..." clause or equivalent explicit trigger guidance; "before filing" only weakly implies when to use the skill. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3 — it is above anchor 2 because the "what" is concrete, but below anchor 4 which requires an explicit 'when'.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "TiDB", "issues", "labels", "duplicates", "filing". It misses a few common variations such as "bug report", "GitHub issue", or "severity", so it fits anchor 4 (good coverage, a few natural terms missing) rather than the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"TiDB issues" carves out a clear niche with distinct triggers (TiDB, labels, duplicates), matching anchor 5's minimal conflict risk. It does not sit at anchor 4, since even a generic GitHub-issue skill would be distinguished by the TiDB qualifier and the metadata/label focus.

5 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pingcap/tidb
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.