tidb-verify-profile

Use when choosing local validation scope in TiDB work, especially to separate fast coding-loop checks from completion checks and avoid unnecessary slow commands.

2.20x

Quality

74%

Does it follow best practices?

Impact

97%

2.20x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tidb-verify-profile/SKILL.md

Quality

Content

86%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.

The body is a tight, well-structured execution guide with concrete commands and a clear Ready-gate sequence, appropriately deferring policy to AGENTS.md. Main gap is that validation feedback loops and the validation matrix are externalized rather than summarized inline.

Dimension	Reasoning	Score
Conciseness	Lean ~30-line body with no padding and no over-explanation of concepts Claude already knows; every line carries actionable signal and assumes competence.	5 / 5
Actionability	Provides concrete executable commands (go test -run ... -tags=intest,deadlock, make lint, realtikvtest) with clear decision guidance, but some specifics (the validation matrix) are externalized to AGENTS.md rather than self-contained.	4 / 5
Workflow Clarity	The Ready profile gives a clear numbered sequence (map paths -> targeted tests -> make lint -> output contract) with most checkpoints present, though explicit validate->fix->retry feedback loops live in AGENTS.md rather than inline.	4 / 5
Progressive Disclosure	Well-organized overview + three profile subsections, under 50 lines, one-level reference to AGENTS.md, no nested or buried references; easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

62%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.

The description clearly scopes the skill to TiDB local validation and provides an explicit 'Use when' trigger with concrete intent. It is solid on both what and when, though the trigger phrasing could enumerate more concrete user-mentionable terms.

Suggestions

Add concrete user-mentionable trigger phrases (e.g., 'Use when the user mentions TiDB testing, lint, realtikvtest, or asks what to validate before a PR').

List a few more specific concrete actions (e.g., 'run targeted go tests, gate with make lint') to lift specificity.

Include natural synonyms/file tags users say (e.g., 'unit tests', 'go test', 'lint', 'PR readiness') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the TiDB validation domain and 1-2 concrete actions ('separate fast coding-loop checks from completion checks', 'avoid unnecessary slow commands') but is not comprehensive in listing specific actions.	3 / 5
Completeness	Both 'what' (choosing/separating validation scope) and 'when' ('Use when choosing local validation scope in TiDB work') are explicit, but the trigger phrasing is somewhat abstract rather than enumerating concrete user-mentionable triggers.	4 / 5
Trigger Term Quality	Good natural-keyword coverage ('TiDB work', 'validation', 'coding-loop', 'completion checks', 'slow commands') with a genuine 'Use when' trigger, though a few common synonyms a user might say are missing.	4 / 5
Distinctiveness Conflict Risk	The TiDB-localized validation niche is mostly distinct with minimal conflict risk, with only minor overlap against generic testing skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: .agents/skills/tidb-verify-profile/SKILL.md
Commit: d8d57d7

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.