finish-feature

Finish a feature — run verification, create PR, retain learnings, and hand off cleanup to the terminal.

Quality

55%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/finish-feature/SKILL.md

Quality

Content

77%

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

This is a strong, well-structured workflow skill with excellent actionability and clear validation checkpoints throughout. The multi-step process is well-sequenced with explicit gates (check failures halt progress, user approval before commits, diff self-test before shipping). Minor weaknesses include some redundancy between inline constraints and the 'Important' section, and slightly verbose explanations of terminal behavior differences.

Suggestions

Remove the repeated constraints in the 'Important' section that are already stated inline (e.g., 'If checks fail, stop' is already in step 2), or consolidate them into one location only.

Trim the preamble's terminal title explanation — Claude doesn't need the rationale about Claude Desktop vs CLI differences; a single conditional command suffices.

Dimension	Reasoning	Score
Conciseness	Generally efficient but has some unnecessary verbosity — the preamble section explaining Claude Desktop vs CLI terminal behavior is somewhat over-explained, and some bash commands include comments that Claude would understand without. The 'Important' section at the end partially repeats constraints already stated inline.	2 / 3
Actionability	Highly actionable with specific, executable bash commands at every step, concrete git/gh CLI invocations, clear commit message format guidance, and a specific PR body template. The fallback commands when devflow is unavailable are a nice touch.	3 / 3
Workflow Clarity	Excellent multi-step workflow with clear sequencing, explicit validation checkpoints (step 2 with hard stop on failure), a self-test/review gate (step 3), user approval before committing (step 4), and a structured summary template at the end. The feedback loop for failing checks is explicit: stop and help fix.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and numbered steps, but it's a moderately long monolithic file with no references to supporting documents. The summary template and some of the detailed bash snippets could potentially be split out, though for a single skill file without bundle this is acceptable.	2 / 3
	Total	10 / 12 Passed

Description

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description provides a rough workflow outline but lacks specificity in its actions and omits explicit trigger guidance for when Claude should select this skill. The terms used are moderately relevant but miss common user phrasings, and several actions ('retain learnings', 'hand off cleanup to the terminal') are ambiguous.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'finish feature', 'done coding', 'ready to submit PR', 'wrap up work', 'create pull request'.

Clarify vague actions: specify what 'verification' means (e.g., run tests, linting), what 'retain learnings' entails (e.g., update documentation, save notes), and what 'hand off cleanup to the terminal' means.

Include natural keyword variations users might say, such as 'pull request', 'submit changes', 'ship feature', 'merge branch'.

Dimension	Reasoning	Score
Specificity	Names several actions (run verification, create PR, retain learnings, hand off cleanup) but they remain somewhat vague — e.g., what kind of verification? What learnings? 'Hand off cleanup to the terminal' is unclear.	2 / 3
Completeness	Describes what the skill does at a high level but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' itself is vague enough to push this to a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'PR', 'feature', and 'verification', but misses common natural phrases users might say such as 'pull request', 'submit code', 'finish work', 'merge', 'code review', or 'done with feature'.	2 / 3
Distinctiveness Conflict Risk	The combination of finishing a feature, creating a PR, and retaining learnings is somewhat distinctive, but terms like 'run verification' and 'create PR' could overlap with CI/CD skills, PR creation skills, or testing skills.	2 / 3
	Total	7 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: AndreJorgeLopes/devflow
Commit: 8d872bf

Reviewed: 1 day 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.