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.
82
73%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/branch-wrapup/SKILL.mdQuality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly communicates both the purpose and trigger conditions for the skill. It lists specific concrete actions and defines clear usage scenarios. The main weakness is that trigger term coverage could be broader, particularly including the unabbreviated 'pull request' and other natural phrases users might use.
Suggestions
Expand trigger terms to include common variations like 'pull request', 'ready to merge', 'pre-merge checks', or 'code review prep' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'runs build, type-check, lint, test, security scans, and finishes with a conventional commit.' These are all distinct, well-defined development actions. | 3 / 3 |
Completeness | Clearly answers both what ('runs build, type-check, lint, test, security scans, and finishes with a conventional commit') and when ('Use before creating a PR, after completing features, or when wrapping up a branch') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'PR', 'build', 'lint', 'test', 'commit', 'branch', and 'features', but misses common variations users might say such as 'pull request', 'code review prep', 'pre-merge checks', 'CI checks', or 'ready to merge'. | 2 / 3 |
Distinctiveness Conflict Risk | The concept of a 'pre-PR quality gate' combining multiple checks into a single workflow is a clear niche. The combination of build + type-check + lint + test + security + commit is distinctive and unlikely to conflict with individual linting or testing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability and workflow clarity with concrete commands, clear phase sequencing, and explicit gate rules. However, it is significantly over-verbose—explaining what each phase catches, including integration tables, continuous mode guidance, and troubleshooting that inflate the token cost without proportional value. The content would benefit from aggressive trimming and splitting secondary content into reference files.
Suggestions
Remove all 'What it catches' bullet lists under each phase—Claude already knows what a build check or type check catches.
Move Troubleshooting, Continuous Mode, and Integration with Other Skills sections to a separate REFERENCE.md file, keeping only a one-line link in the main skill.
Consolidate the output format template—the ASCII box art report is nice but takes many tokens; consider a compact version or move to a reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It over-explains what each phase 'catches' (Claude knows what a build check catches), includes unnecessary sections like 'When to Use' bullet lists, 'Continuous Mode' suggestions, 'Integration with Other Skills' tables, and 'Troubleshooting' that bloat the context window significantly. Much of this could be cut or moved to a reference file. | 1 / 3 |
Actionability | Every phase includes concrete, executable PowerShell commands that are copy-paste ready. The commit message format, security scan patterns, and hygiene checks are all specific and actionable with real command-line examples. | 3 / 3 |
Workflow Clarity | The 9-phase workflow is clearly sequenced with explicit gate rules (blocking vs soft vs info) summarized in a table. Validation checkpoints are explicit—build failure stops immediately, P0 smells block, and the commit phase only runs if blockers pass. The Phase Gate Rules table is an excellent feedback loop summary. | 3 / 3 |
Progressive Disclosure | The skill references external files like `verify.ps1`, `copilot-instructions.md`, and `code-smells.md`, which is good. However, the main file is monolithic with extensive inline content (troubleshooting, continuous mode, integration tables, full output format template) that could be split into separate reference files. The content that should be separate is inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- 0xrabbidfly/eric-cartman
- Commit
1e34e1c
- 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.