Name: finish-feature
Rating: 62.4 (1 reviews)
Author: AndreJorgeLopes

finish-feature

Finish a feature — run verification, an adversarial review gate (re-grounded on the original design doc + ticket ACs, not the plan) and a deferral-closure gate, then create the PR, retain learnings, and hand off cleanup to the terminal.

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 ./devflow-plugin/skills/finish-feature/SKILL.md

The canonical home for this skill is finish-feature in AndreJorgeLopes/devflow

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable with a clear, validated multi-step workflow and concrete executable commands throughout. Its weaknesses are verbosity from repeated rationale and inline content that, in a longer file with no bundle references, leaves progressive disclosure at the mid-level.

Suggestions

Trim repeated rationale — state the 'plan is a lossy compression' point once in Step 4 and remove its re-statements in the Important section to tighten conciseness.

Consider extracting the Step 4 review-gate rationale/method into a reference file (e.g. REVIEW-GATE.md) and linking to it from a concise overview, improving progressive disclosure and reducing inline length.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence on basics, but it pads with repeated rationale (the "plan is a lossy compression" point restated multiple times), long "Why this step exists" prose, and an Important section that re-warns about already-stated rules — matching the score-2 anchor of mostly efficient but could be tightened rather than the lean score-3 anchor.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands (`devflow check`, `make flows-check`, `git push -u origin HEAD`, `gh pr create --title "<title>" --body "<body>"`), a pinned commit-subject regex, exact PR section headings, and deterministic predicates with exit codes, matching the score-3 anchor.	3 / 3
Workflow Clarity	The 9-step pipeline is clearly sequenced with explicit validation checkpoints and feedback loops ("If checks fail ... stop", "Do not continue past this step", the "Fail loud" empty-diff check, severity-gated review, stop-and-ask fallbacks), plus a guard against irreversible actions during eval mode, matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle files exist, so this is a single ~199-line file with well-organized internal sections but no one-level-deep external references; the long Step 4 rationale is inline content that could be split out, matching the score-2 anchor of some structure with content that could be better separated rather than the well-signaled reference structure of score 3.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is concrete and distinctive, naming specific pipeline actions and a niche unlikely to conflict. Its main weakness is the lack of an explicit "Use when..." trigger clause and limited spread of natural trigger keywords, which cap completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrasings, e.g. 'Use when finishing, wrapping up, or completing a feature before handing off for cleanup'.

Soften or augment the jargon (e.g. 'adversarial review gate', 'deferral-closure gate') with plain-language keyword variants a user would actually say to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — "run verification", "an adversarial review gate", "a deferral-closure gate", "create the PR", "retain learnings", and "hand off cleanup" — matching the score-3 anchor that lists several specific actions rather than vague language.	3 / 3
Completeness	It clearly answers what the skill does, but there is no explicit "Use when..." trigger clause; per the judging guidelines a missing explicit trigger guidance caps completeness at 2, and it is not the score-1 case because the what is stated concretely.	2 / 3
Trigger Term Quality	The lead phrase "Finish a feature" is a natural trigger a user would say, but the rest is jargon-heavy ("adversarial review gate", "deferral-closure gate", "re-grounded on the original design doc + ticket ACs") with no spread of common keyword variations, matching the score-2 anchor of some relevant keywords missing common variations rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	The highly specific niche — review gate re-grounded on design doc + ticket ACs, a deferral-closure gate, and terminal handoff of worktree cleanup — gives it a clear, distinct trigger set unlikely to collide with other skills, matching the score-3 anchor.	3 / 3
	Total	10 / 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: AndreJorgeLopes/devflow
Path: devflow-plugin/skills/finish-feature/SKILL.md
Commit: 526efe4

Reviewed: 21 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.