skill-finish-branch

Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done

Quality

72%

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 ./.claude/skills/skill-finish-branch/SKILL.md

Quality

Content

56%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.

Actionable and safety-conscious with strong validation checkpoints, but hurt by verbosity and structural issues: duplicate step numbering, redundant restating tables, and a complete absence of progressive disclosure for a skill this size.

Suggestions

Fix the duplicate step numbering (two 'Step 4' and two 'Step 5' sections) so the pipeline reads as a single coherent sequence.

Consolidate the Quick Reference, Red Flags, and Common Mistakes tables into one section to remove redundant restating of the same guidance.

Split the multi-provider review, octopus integration, and PR-creation details into one-level-deep reference files and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose across ~380 lines: duplicate step numbering (two 'Step 4' and two 'Step 5' sections), three tables (Quick Reference, Red Flags, Common Mistakes) that restate the same guidance, and branded filler like the mandated 'CLAUDE OCTOPUS ACTIVATED' line.	2 / 5
Actionability	Mostly executable bash throughout (test detection, git diff, orchestrate.sh, gh pr create, merge sequences), with minor gaps: placeholder variables like ${PR_TITLE:?...} require completion and the merge option hardcodes 'npm test' despite the earlier generic detection.	4 / 5
Workflow Clarity	Clear sequenced pipeline with strong validation checkpoints ('If tests fail: STOP', typed 'discard' confirmation, review-then-fix loop), but the broken duplicate step numbering muddies the sequence and the merge-branch test verification is hardcoded.	4 / 5
Progressive Disclosure	Has clear section headers but no bundle files and no external references — multi-provider review, octopus integration, and safe-gh-comment details are all inlined in a single monolithic file rather than split into one-level-deep references.	3 / 5
	Total	13 / 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.

A strong, specific description that clearly states what the skill does and when to use it, with natural trigger phrases. Minor gaps in synonym coverage and slight overlap risk keep it just below a perfect score.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'run tests, create PR, merge or discard' — giving comprehensive coverage of branch-finishing operations.	5 / 5
Completeness	Explicitly answers both what ('run tests, create PR, merge or discard') and when ('use when implementation is done') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('wrap up a branch', 'create PR', 'merge', 'discard', 'implementation is done'), but the description proper omits common synonyms like 'push' and 'commit and push' that live only in the separate trigger field.	4 / 5
Distinctiveness Conflict Risk	Clear git branch-finishing niche with distinct triggers, but minor overlap risk with generic test-running and built-in git commit tooling.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-finish-branch/SKILL.md
Commit: f9b8c92

Reviewed: 5 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.