tidb-bazel-prepare-gate

Use when deciding whether make bazel_prepare is required before build or test commands based on local file changes in TiDB.

Quality

70%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tidb-bazel-prepare-gate/SKILL.md

Quality

Content

64%

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

This is a focused, well-scoped skill that efficiently addresses a specific build-system decision point. Its main weakness is that the core decision logic is delegated to AGENTS.md rather than being fully enumerated, which reduces actionability—Claude must cross-reference another file to make the complete determination. The git inspection commands are concrete and useful, but the skill would benefit from either inlining all trigger conditions or providing a complete summary.

Suggestions

Inline the complete list of trigger conditions from AGENTS.md so Claude can make the decision without cross-referencing another file, or at minimum provide a complete summary checklist.

Add a validation step after running `make bazel_prepare` (e.g., check exit code, verify expected output) to confirm the prepare step succeeded before proceeding to build/test.

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient. It assumes Claude knows what Bazel is, what `make` targets do, and how git works. Every section serves a clear purpose with no unnecessary explanation. The opening note to skip this skill in normal coding loops is a valuable token-saving directive.	3 / 3
Actionability	The git commands are concrete and copy-paste ready, and the diff pattern examples are helpful. However, the core decision rules are delegated to `AGENTS.md` rather than being enumerated here, meaning Claude must look elsewhere to actually make the decision. The skill provides inspection steps but incomplete decision logic.	2 / 3
Workflow Clarity	The workflow has a clear sequence (inspect → decide → act), and the final step provides a binary outcome (run make bazel_prepare or continue). However, there's no validation checkpoint after running `make bazel_prepare` (e.g., checking exit code, verifying generated files), and the decision rules are partially specified here but fully delegated to AGENTS.md, creating ambiguity.	2 / 3
Progressive Disclosure	The skill references `AGENTS.md` for the authoritative decision rules, which is a reasonable one-level-deep reference. However, since no bundle files are provided and the referenced content isn't summarized inline, the reader must navigate away to understand the complete trigger conditions. The two inline examples (test function and import changes) partially mitigate this but don't cover all conditions.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 is well-targeted and clearly scoped to a specific TiDB build workflow task. It effectively communicates both what the skill does and when to use it. However, it could benefit from listing more concrete actions (e.g., checking which files changed, determining affected build targets) and including more natural trigger term variations.

Suggestions

Add more concrete actions beyond 'deciding whether' — e.g., 'Checks local file changes against Bazel build graph dependencies, determines if make bazel_prepare must be run before build or test commands.'

Include additional trigger term variations users might naturally say, such as 'bazel build failing', 'need to regenerate build files', 'BUILD.bazel out of date', or 'make prepare'.

Dimension	Reasoning	Score
Specificity	The description names a specific domain action ('deciding whether make bazel_prepare is required') and context ('before build or test commands based on local file changes in TiDB'), but it only describes one action rather than listing multiple concrete capabilities.	2 / 3
Completeness	The description explicitly answers both 'what' (deciding whether make bazel_prepare is required before build or test commands based on local file changes) and 'when' (starts with 'Use when'), providing a clear trigger condition.	3 / 3
Trigger Term Quality	Includes relevant keywords like 'bazel_prepare', 'build', 'test commands', 'TiDB', and 'local file changes', but these are fairly technical terms. It misses common variations a user might say such as 'bazel build', 'make test', 'prepare build', or 'regenerate build files'.	2 / 3
Distinctiveness Conflict Risk	Highly specific to TiDB's bazel_prepare workflow, making it very unlikely to conflict with other skills. The combination of 'bazel_prepare', 'TiDB', and 'local file changes' creates a clear, narrow niche.	3 / 3
	Total	10 / 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: 28 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.