skill-finish-branch

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

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/skill-finish-branch/SKILL.md

Quality

Content

63%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 well-structured, largely executable workflow with strong validation checkpoints for risky operations. Its main weaknesses are redundancy across the summary tables and broken step numbering, plus a monolithic single-file structure with no progressive disclosure.

Suggestions

Fix the duplicated step numbers: there are two 'Step 4' and two 'Step 5' headers, and 'Execute Choice' is labeled Step 4 despite following 'Step 5: Present Options' — renumber sequentially.

Remove or collapse the 'Red Flags' and 'Common Mistakes' tables where they merely restate the inline step guidance, to reduce token cost.

Move the per-option detailed scripts (and the Octopus integration examples) into reference files linked one level deep from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but repeats inline guidance in the 'Red Flags' and 'Common Mistakes' tables (e.g. merge-without-testing, proceed-when-tests-fail already stated in Step 1), which is padding that could be trimmed.	3 / 5
Actionability	Concrete, executable bash is provided throughout (test detection, diff review, merge, PR creation with validated env vars and a real script, discard); minor gaps like the changelog prepend lacking an actual command keep it below 5.	4 / 5
Workflow Clarity	The sequence is clear with strong validation checkpoints (stop on test failure, review-clean check, typed 'discard' confirmation for the destructive op); the broken step numbering (two Step 4 and two Step 5 headers, execute-choice after present-options) is a fixable structural gap rather than a validation gap.	4 / 5
Progressive Disclosure	Internal sectioning is good, but ~355 lines are inlined in one file with no one-level-deep reference docs for deeper detail (per-option scripts, integration examples); the under-50-line simple-skill exception does not apply.	3 / 5
	Total	14 / 20 Passed

Description

67%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 solid, third-person description that states both what the skill does and when to use it, with several concrete actions. The main weakness is the narrow explicit trigger clause, which limits trigger-term quality and completeness.

Suggestions

Broaden the 'use when' clause to include natural variations, e.g. 'use when implementation is done, you're ready to ship, or the user asks to finish/merge/PR a branch'.

Add a couple of common user phrasings as triggers (e.g. 'create a PR', 'merge this branch', 'I'm done') to improve trigger-term coverage.

Consider naming the review/validation step in the description so the capabilities read as more comprehensive.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ('run tests, create PR, merge or discard') covering the branch-finishing flow; falls short of 5 because the actions are relatively high-level rather than comprehensively specific.	4 / 5
Completeness	Both 'what' (wrap up a branch via the four actions) and 'when' ('use when implementation is done') are explicitly present; the 'when' is concrete but could cover more triggering scenarios to reach 5.	4 / 5
Trigger Term Quality	Relevant keywords appear (branch, tests, PR, merge, discard) but the single explicit trigger 'use when implementation is done' is narrow, omitting common variations like 'ship this', 'I'm done', or 'finish this branch'.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (branch-finishing pipeline) with distinct triggers; only minor overlap risk with generic 'create PR' or 'merge' git skills keeps it below 5.	4 / 5
	Total	15 / 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: nyldn/claude-octopus
Path: skills/skill-finish-branch/SKILL.md
Commit: 242e51d

Reviewed: 3 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.