pre-push-check

Run the full pre-push review pipeline — code review checks, self-review against CLAUDE.md, and a final report.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/pre-push-check/SKILL.md

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-sequenced, actionable pre-push pipeline with concrete commands and a clear report template; it is concise and well-organized into a single self-contained file. The main gap is the absence of an explicit fix-and-re-run validation feedback loop on the review-tool output.

Suggestions

Add an explicit feedback loop: after 'devflow check' fails, instruct to fix the reported issues and re-run 'devflow check' until it passes before moving to the report.

Make the report template copy-paste-ready by showing a small worked example verdict rather than only [PASS/FAIL] placeholders.

Tighten the CLAUDE.md review bullets into a concise checklist to reduce token weight while preserving coverage.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — concrete commands ('git diff --stat', 'devflow check') and tight bullet checklists without explaining concepts Claude already knows; only minor padding (the parenthetical fallback list and enumerated CLAUDE.md bullets) keeps it just below a 5.	4 / 5
Actionability	It gives concrete, executable commands ('devflow check', 'git log --oneline origin/HEAD..HEAD', 'yarn lint') and a fill-in report template, but the report block uses placeholders rather than copy-paste-ready output and some checks ('hardcoded secrets') are descriptive rather than scripted, so it stops at 'mostly executable, minor gaps'.	4 / 5
Workflow Clarity	Six numbered steps are clearly sequenced with a verification step ('If issues are found… ask the user') and a binary verdict output, but it lacks an explicit validate-then-fix feedback loop on the devflow/lint output itself (e.g. re-run after fixing), so it is just shy of the score-5 anchor.	4 / 5
Progressive Disclosure	This is a single-file skill with no bundle files present and well-organized sections (Steps, checklists, report template) all at one level — per the scoring notes, skills under 50 lines with no need for external references can score 5 with just well-organized sections, which this is.	5 / 5
	Total	17 / 20 Passed

Description

50%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 states what the skill does (a three-part pre-push review pipeline) but omits any explicit 'Use when...' trigger guidance, which caps completeness at 3. Trigger-term and distinctiveness coverage is moderate, anchored on 'pre-push' alone.

Suggestions

Add an explicit trigger clause, e.g. 'Use when about to push code, before running git push, or when the user asks to verify changes are ready to push.'

Add natural synonyms and file/tool names (e.g. 'git push', 'before committing', 'pre-commit review') to broaden trigger-term coverage.

Sharpen distinctiveness by naming the unique combination (e.g. 'Runs devflow check plus a CLAUDE.md compliance review, then produces a pass/warn/fail report') to separate it from generic review skills.

Dimension	Reasoning	Score
Specificity	Names the domain (pre-push review) and lists three concrete actions — 'code review checks, self-review against CLAUDE.md, and a final report' — which fits the score-3 anchor of '1-2 concrete actions, but not comprehensive', as these are high-level phases rather than granular operations.	3 / 5
Completeness	The 'what' is clearly stated (run the review pipeline with three parts), but there is no 'Use when...' or explicit trigger clause stating when Claude should invoke this skill, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'pre-push' is the key natural keyword a user would say, and 'push'/'code review' are relevant, but common synonyms like 'before committing', 'git push', or 'commit review' are missing, matching the score-3 anchor of 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The 'pre-push review pipeline' framing is somewhat specific, but 'code review checks' and 'self-review' overlap broadly with general review skills, so it could still trigger for related skills, matching the score-3 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	12 / 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: AndreJorgeLopes/devflow
Path: skills/pre-push-check/SKILL.md
Commit: bd4b70c

Reviewed: 17 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.