Name: new-feature
Rating: 60 (1 reviews)
Author: AndreJorgeLopes

Blog Docs Log in Get started

new-feature

Post-launch setup for a new feature worktree — detect context, recall memories, and transition to brainstorming.

Quality

68%

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/new-feature/SKILL.md

The canonical home for this skill is new-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 concrete commands and a clear sequenced workflow, but it is held back by a verbose inline mechanics paragraph and mild repetition that hurt conciseness and progressive disclosure.

Suggestions

Move the detailed spec→plan→lock-tests→impl phase-handoff mechanics (the long paragraph in Step 6) into a separate reference file and link to it, keeping Step 6 focused on invoking brainstorming.

De-duplicate Step 4's guidance and trim the 'Important' section so it does not restate steps already covered, recovering token budget.

If the phase-handoff details must stay inline, split them into a clearly labeled 'Downstream pipeline (reference)' subsection so the orientation flow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the dense inline pipeline/phase-handoff mechanics paragraph and some restated guidance (Step 4 re-explains itself; the 'Important' section reiterates earlier steps) could be tightened. Not a 1 because it does not explain concepts Claude already knows; not a 3 because of the padded mechanics and repetition.	2 / 3
Actionability	It gives concrete, executable guidance throughout — real git commands, a window-title printf, specific Hindsight query strings, and a copy-paste output template — matching the fully executable/copy-paste-ready anchor.	3 / 3
Workflow Clarity	The process is clearly sequenced (Preamble → Steps 1–6 → transition) with explicit guard conditions such as the branch-is-main check, the eval-mode guard, and the 'ask before guessing' checkpoint. This is an orientation skill with no destructive/batch operation, so the missing-feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	The file is sectioned and has no nested references, but at ~90 lines it exceeds the under-50-lines simple-skill allowance and carries a dense inline paragraph on downstream phase-handoff mechanics that arguably belongs in a separate reference. Not a 1 because organization is reasonable; not a 3 because content that could be split is inline and no bundle files exist to offset it.	2 / 3
	Total	10 / 12 Passed

Description

60%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 specific and action-oriented with concrete named steps, but it lacks explicit "when to use" trigger guidance and leans on internal terminology, leaving its triggering and distinctiveness weaker.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when launching inside a new feature worktree to orient before brainstorming,' to answer the 'when' half of completeness.

Include natural trigger terms a user would actually say (e.g. 'new feature', 'start a feature', 'feature worktree') alongside the existing technical phrasing to lift trigger-term quality.

Tighten distinctiveness by naming the devflow surface and the specific launch moment so it cannot be confused with sibling devflow skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "detect context, recall memories, and transition to brainstorming" — matching the anchor for several specific concrete actions rather than a single vague domain mention.	3 / 3
Completeness	It clearly states what the skill does (post-launch setup with three named actions) but only implies when to use it; there is no explicit "Use when..." trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It contains domain-relevant terms ("new feature worktree", "brainstorming") but these read as internal/technical phrasing rather than natural user triggers, and common variations are missing. Not a 1 because the terms are on-topic; not a 3 because no natural keyword coverage is present.	2 / 3
Distinctiveness Conflict Risk	The "new feature worktree" niche is somewhat specific, but as one skill in a devflow suite with no explicit triggers it could still overlap with sibling skills, matching the "somewhat specific but could overlap" anchor.	2 / 3
	Total	9 / 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/new-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.