CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

api-contract-review

Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable review workflow with a real one-level-deep reference, but a verbatim-duplicated 'Internal parameters' section wastes tokens and hurts organization. Fixing the duplication would raise both conciseness and structure scores.

Suggestions

Delete the second verbatim copy of the 'Internal parameters' section (lines 75-87) — it is an exact repeat and pure token waste.

Move the internal-parameter registry (e.g. the EnvTypes/DescribeEnvs entry) and the evaluation prompts into references/review-checklist.md or a dedicated reference file, keeping SKILL.md as an overview.

Add an explicit feedback loop in Phase 4: after preparing the fix, re-verify against the documented contract and confirm the new tests fail on the old payload before opening the PR.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the entire 'Internal parameters' section (including the EnvTypes/DescribeEnvs example) is duplicated verbatim twice (lines 61-73 and 75-87), which is pure padding. This fits 'mostly efficient but includes some unnecessary ... could be tightened'; it does not reach 2 because the rest of the body is lean.

3 / 5

Actionability

Concrete, executable guidance throughout: specific doc URLs, exact paths like 'mcp/src/tools/*', named mismatch labels, and explicit escalation rules. As an instruction-only skill the absence of code is acceptable, but commands for locating/running the referenced tests are left implicit, leaving minor gaps.

4 / 5

Workflow Clarity

Four clearly sequenced phases with validation gates ('If the docs do not clearly support the action ... stop short of guessing') and a closing self-check checklist. Not a 5 because the duplicated Internal parameters section muddies phase structure and there is no explicit feedback loop for re-verifying after a fix.

4 / 5

Progressive Disclosure

The body points early and clearly to the real one-level-deep 'references/review-checklist.md' (verified to exist) plus a routing table. Not a 5 because detail like the internal-parameter registry and evaluation prompts is inlined in SKILL.md rather than split into references.

4 / 5

Total

15

/

20

Passed

Description

92%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 strong description: it states concrete capabilities and explicit trigger conditions in third person, and carves out a distinct niche. Its only weakness is slightly limited synonym coverage for trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests' — covering the domain comprehensively with no vague filler.

5 / 5

Completeness

It explicitly answers both what ('auditing ... for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests') and when ('Use when auditing ... especially during periodic quality review or before preparing corrective PRs') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural terms like 'auditing', 'MCP tools', 'API', 'contract tests', 'quality review', and 'corrective PRs' give good keyword coverage, but a few natural synonyms users might say (e.g. 'verify', 'drift', 'stale') are only partially covered. This sits between the 'good coverage with a few missing' (4) and 'comprehensive with synonyms' (5) anchors, closer to 4.

4 / 5

Distinctiveness Conflict Risk

The CloudBase cloud API contract-correctness niche is highly specific with distinct triggers (MCP tools, generated action metadata, contract tests), so overlap with other skills is minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

TencentCloudBase/CloudBase-AI-Toolkit

Path

skills/api-contract-review/SKILL.md

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.