skill-finish-branch

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

Quality

75%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable skill with concrete commands and good validation checkpoints, undermined by structural sloppiness — duplicate step numbers and mismatched option ordering — plus redundancy across multiple caution sections and a monolithic layout with no progressive disclosure.

Suggestions

Fix the duplicate step numbering and align option order so "Present Options" (1=Create PR, 2=Merge locally) matches the "Execute Choice" sub-headings (currently reversed).

Collapse the redundant caution material — merge "Red Flags - Never Do", "Common Mistakes", and "The Bottom Line" into a single concise checklist to reduce token overhead.

Consider splitting the per-option execution scripts into a referenced file (e.g. scripts/finish-branch.sh) so SKILL.md stays a lean overview with one-level-deep references.

Dimension	Reasoning	Score
Conciseness	Mostly action-oriented, but redundancy across the "Execution Contract", "Red Flags - Never Do", "Common Mistakes", and "The Bottom Line" sections restates the same cautions, and the Codex host preamble adds non-essential context.	2 / 3
Actionability	Provides concrete, executable bash (git/gh/npm), a real orchestrate.sh invocation, and a copy-paste AskUserQuestion block with specific options; placeholders like "feat: [description]" are reasonable templates.	3 / 3
Workflow Clarity	The process is sequenced with validation checkpoints (tests fail → STOP, discard requires typed "discard"), but duplicate step numbering (two "Step 4" and two "Step 5") and inconsistent option ordering between "Present Options" (1=Create PR) and "Execute Choice" (Option 1=Merge Locally) create a real clarity gap.	2 / 3
Progressive Disclosure	No bundle files exist and the body is a single ~350-line monolithic file; sections are well-organized but content that could be split (option execution details, red flags) is inline, and the only references (codex-host-adapter.md, orchestrate.sh) point to external plugin paths rather than a bundled structure.	2 / 3
	Total	9 / 12 Passed

Description

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.

A strong, concise description that names concrete actions and includes an explicit use-when trigger. Its main weakness is a slightly narrow trigger clause that omits common phrasings users would naturally say.

Suggestions

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

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "run tests, create PR, merge or discard" — rather than vague language, matching the anchor that enumerates specific tasks.	3 / 3
Completeness	Clearly states what it does (run tests, create PR, merge or discard) and when to use it via the explicit "use when implementation is done" clause, answering both what and when.	3 / 3
Trigger Term Quality	Has some natural terms ("wrap up a branch", "create PR", "merge") but the explicit trigger "use when implementation is done" is narrow and misses common variations like "ship", "finish the branch", or "ready to merge".	2 / 3
Distinctiveness Conflict Risk	"Wrap up a branch" carves a clear niche (finishing a development branch) with triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: .claude/skills/skill-finish-branch/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.