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

62%

Does it follow best practices?

Impact

97%

2.20x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/tidb-verify-profile/SKILL.md

Quality

Discovery

40%

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 fails to specify what concrete actions the skill performs, relying on abstract concepts like 'validation scope' and 'coding-loop checks' without naming specific commands, tools, or outputs. While it includes a 'Use when' clause and the TiDB domain keyword, the lack of concrete capabilities makes it difficult for Claude to confidently select this skill over alternatives.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Runs fast local checks such as `make check`, linting, and unit tests separately from full integration test suites'

Include natural trigger terms users would say, such as specific command names, tool names (e.g., 'golangci-lint', 'make build'), or phrases like 'run tests locally', 'quick validation', 'pre-commit checks'

Clarify the 'what' more explicitly—describe what 'fast coding-loop checks' and 'completion checks' actually are and what commands or workflows they correspond to

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'local validation scope', 'fast coding-loop checks', and 'completion checks' without listing any concrete actions. It doesn't specify what the skill actually does—no verbs like 'run', 'configure', 'execute', or specific tools/commands mentioned.	1 / 3
Completeness	It has a 'Use when' clause addressing the 'when' question (choosing local validation scope in TiDB work), but the 'what' is extremely weak—it doesn't explain what the skill actually does or what specific actions it performs. The 'when' is present but the 'what' is essentially missing.	2 / 3
Trigger Term Quality	It includes 'TiDB' and 'validation' as relevant keywords, and 'coding-loop checks' hints at a development workflow. However, it lacks natural terms a user would say such as 'lint', 'test', 'build', 'compile', or specific command names that would trigger this skill.	2 / 3
Distinctiveness Conflict Risk	The mention of 'TiDB' provides some niche specificity, but 'validation scope' and 'coding-loop checks' are generic enough to overlap with other CI/CD, testing, or linting skills. Without concrete commands or tools, it could conflict with other TiDB-related or validation-related 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-crafted decision-routing skill that efficiently defines three verification profiles with clear triggers and boundaries. Its main strength is conciseness and clear workflow structure. The primary weakness is that actionability depends heavily on AGENTS.md for the actual validation matrices and trigger phrases, making this skill somewhat incomplete in isolation.

Suggestions

Consider inlining the 'Quick Decision Matrix' trigger phrases or at least listing the key mandatory trigger phrases directly, so the skill is more self-contained for the Ready profile.

Add a brief example showing how to 'map changed paths to required test surfaces' so Claude has a concrete pattern to follow without needing to look up AGENTS.md every time.

Dimension	Reasoning	Score
Conciseness	Every line serves a purpose. No unnecessary explanations of what TiDB is, what linting does, or how Go testing works. The profile structure is lean and assumes Claude already understands the tooling.	3 / 3
Actionability	Provides concrete commands like `go test -run <TestName> -tags=intest,deadlock` and `make lint`, but heavily delegates specifics to AGENTS.md (e.g., 'Task -> Validation Matrix', 'Quick Decision Matrix'). The skill itself doesn't contain fully self-contained executable guidance—it's more of a decision framework that points elsewhere for the actual details.	2 / 3
Workflow Clarity	The three profiles create a clear decision framework with unambiguous triggers. The 'Ready' profile has an explicit ordered sequence (map paths → run tests → lint → report) and the 'Heavy' profile includes clear guardrails (never run bazel_lint_changed unless explicitly requested). For a decision-routing skill, this is well-sequenced.	3 / 3
Progressive Disclosure	The skill is appropriately scoped as an execution guide that references AGENTS.md for policy details, with clear one-level-deep pointers (e.g., 'AGENTS.md -> Quick Decision Matrix', 'AGENTS.md -> Task -> Validation Matrix'). No bundle files are needed for this concise routing skill.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: pingcap/tidb
Commit: e70762e

Reviewed: 4 days 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.