CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

validating-a-change

comprehensive validation of a change to ensure it is correct and ready for a pull request

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/validating-a-change/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 orchestration playbook: every step has concrete commands, verbatim subagent prompts, explicit validation checkpoints, and clear completion/failure criteria. Its only weaknesses are mild redundancy in restating the resolve-before-proceeding rule and slightly under-specified build-configuration commands.

DimensionReasoningScore

Conciseness

The body is directive and operational throughout, explaining nothing Claude already knows, but the 'fully resolve issues within a step before proceeding' principle is stated three times (Overview, Validation Steps intro, ALWAYS section) and the ordering rationale is duplicated between the Overview list and the steps. Fits 'Efficient; minor instances of over-explanation that could be trimmed' rather than level 5.

4 / 5

Actionability

Concrete, executable guidance dominates: exact git commands ('git diff', 'git diff --cached', 'git diff master...HEAD'), verbatim subagent launch prompts with explicit substitution variables, and exact commands like 'make format'. Minor gaps keep it below level 5: the exact build command for the '--disable-tests' check is not given, and Step 5 defers configuration details to another skill.

4 / 5

Workflow Clarity

Six explicitly ordered steps with a stated ordering rationale, per-step validation checkpoints ('If any tests fail, run a subagent to fix the issues before proceeding'), a completion checklist, and an error-recovery loop for stuck validation ('Which step keeps failing... whether the fundamental approach may need reconsideration'). This matches the top anchor: clear sequence, explicit validation steps, and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-sectioned with nothing inlined that belongs in a separate file — the content legitimately lives in SKILL.md. Minor gaps: sibling-skill references are bare backtick names with no paths or signals, and the ~160-line body repeats the ordering rationale, fitting 'Good structure; most content is appropriately placed; minor organization gaps' rather than the fully clean level-5 anchor.

4 / 5

Total

17

/

20

Passed

Description

45%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 communicates a clear purpose (pre-pull-request validation of a change) but is generic: no concrete capabilities, no trigger guidance, and few natural keywords. It would likely fail to trigger reliably and could be confused with individual review or testing skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to validate or check a change before opening a pull request, or when verifying changes are ready to merge.'

List the concrete actions the skill performs, e.g. 'Runs high- and low-level code reviews, adds missing test coverage, runs tests and sanitizer/fuzz configurations, and formats code.'

Include natural trigger phrases and synonyms users would actually say ('validate my change', 'is this ready for a PR', 'check before merging') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('validation of a change', 'ready for a pull request') but lists no concrete actions — none of the actual capabilities (code review, adding tests, running tests across configurations, formatting) appear, and 'comprehensive' is filler. This matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete named actions.

2 / 5

Completeness

The 'what' is clear (validate that a change is correct and ready for a pull request), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not level 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

It contains some relevant keywords ('validation', 'change', 'correct', 'pull request') but misses the natural phrases and variations users would say, such as 'check my changes', 'ready to merge', 'run tests', or 'review before PR'. Fits 'Some relevant keywords but missing common variations or synonyms'; not level 2 because the terms present are domain-relevant rather than fully generic.

3 / 5

Distinctiveness Conflict Risk

The pre-PR validation niche is somewhat specific, but because the description omits the distinguishing steps (code review, test coverage, multi-configuration builds, formatting), it could still overlap with plain code-review or testing skills. Fits 'Somewhat specific but could still overlap with similar skills'; not level 4 since the differentiating actions are never articulated.

3 / 5

Total

11

/

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

stellar/stellar-core

Path

.claude/skills/validating-a-change/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.