branch-wrapup

Pre-PR quality gate that runs build, type-check, lint, test, security scans, and finishes with a conventional commit. Use before creating a PR, after completing features, or when wrapping up a branch.

Quality

79%

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 ./.github/skills/branch-wrapup/SKILL.md

Quality

Content

70%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.

A strong operational core: the 10-phase pipeline is unambiguous, gate-driven, and backed by concrete PowerShell commands with genuine validation checkpoints. Weaknesses are structural and editorial — heavy inline monolith with an unbacked script reference, plus decorative sections (ASCII report template, integration table, creative-ideas instruction) that dilute token efficiency.

Suggestions

Actually bundle verify.ps1 in scripts/ (or drop the 'PowerShell Script' section) — the skill claims a bundled script that does not exist in the bundle, which is a broken reference for progressive disclosure.

Move the full Select-String scan pattern catalogs (Phases 5, 7, 9) into a references/ file, keeping SKILL.md as the phase/gate overview, to reduce the ~380-line monolith.

Cut the ASCII verification-report template, the 'Integration with Other Skills' table, and the '1–2 implementable app ideas' instruction — none of them change what Claude does during a wrapup and they cost significant tokens.

Dimension	Reasoning	Score
Conciseness	The ten phases are command-dense and efficient, but the decorative ASCII verification-report template, the 'Integration with Other Skills' table, and instructions to append '1–2 implementable app ideas' to code-smells.md pad a verification gate with material that earns no tokens. It sits above anchor 2 (most sections carry real commands) but below anchor 4 due to this volume of non-essential material.	3 / 5
Actionability	Nearly every phase supplies copy-paste PowerShell (npm scripts, Select-String patterns, madge, git commands), so it is mostly executable. Minor gaps keep it below anchor 5: Phase 10's commit block is a template rather than runnable code, Phase 9's tracker is a comment, and the referenced verify.ps1 is not actually bundled.	4 / 5
Workflow Clarity	Ten explicitly sequenced phases with per-phase blocking rules ('Must pass to continue', 'stop the pipeline immediately'), a Phase Gate Rules table, and a Troubleshooting section with fix-and-retry recovery loops. This matches the anchor for clear sequence with explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	Sections are well-organized and navigable, but the skill is monolithic at ~380 lines with all detail inlined, and its one claimed bundle script ('See: verify.ps1') does not exist in the bundle, nor do the referenced .github skill files. This fits anchor 3 (structure present, but content that should be separate is inline and references are not backed by real files); it is above anchor 2 because navigation is genuinely clear.	3 / 5
	Total	15 / 20 Passed

Description

88%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.

An exemplary description: concrete action list plus an explicit three-trigger 'Use when' clause in third person, with no fluff. The only shortfall is mild — a few natural synonyms for the trigger terms and slight overlap risk with adjacent commit/review skills.

Dimension	Reasoning	Score
Specificity	'runs build, type-check, lint, test, security scans, and finishes with a conventional commit' lists five-plus specific concrete actions with comprehensive coverage of the skill's scope. This matches anchor 5; anchor 4 would require minor coverage gaps, and there are none of substance.	5 / 5
Completeness	It explicitly answers 'what' (the named gates plus the conventional commit) and 'when' ('Use before creating a PR, after completing features, or when wrapping up a branch') with concrete trigger phrases, matching anchor 5. Not anchor 4, since the 'when' clause is already explicit and specific.	5 / 5
Trigger Term Quality	'before creating a PR', 'after completing features', 'wrapping up a branch' are natural user phrases, complemented by tool terms (type-check, lint, conventional commit). A few natural synonyms are missing ('pull request' spelled out, 'pre-push', 'before opening a PR'), which places it at anchor 4 rather than the full-synonym coverage of anchor 5, and clearly above anchor 3.	4 / 5
Distinctiveness Conflict Risk	'Pre-PR quality gate' carves a clear niche, but generic gate terms overlap with closely related skills the ecosystem already has (git-commit, code-review, CI), fitting anchor 4 ('mostly distinct; minor overlap risk'). Not anchor 5, since lint/test/commit vocabulary could collide with those adjacent skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: 0xRabbidfly/Eric-Cartman
Path: .github/skills/branch-wrapup/SKILL.md
Commit: aa16c9e

Reviewed: 6 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.