Name: new-feature
Rating: 53.6 (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

59%

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

67%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.

The body is a well-sequenced, highly actionable orientation guide with concrete commands and explicit checkpoints, slightly held back by verbosity in the downstream-pipeline and eval-mode explanations.

Suggestions

Trim the phase-handoff/spawn paragraph in step 6 to the essentials (the pipeline order and the handoff boundary) — the full spawned-session/recovery mechanism is more detail than this orientation skill needs.

Condense the eval-mode block into a single concise guard rule ('If $DEVFLOW_EVAL is set: print orientation only, perform no state writes or handoffs, then stop') to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the dense phase-handoff/spawn paragraph in step 6 and the lengthy eval-mode block over-explain downstream mechanics Claude does not need to act on here, matching 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides executable bash commands (git branch/log, terminal-title printf), an exact mark_chapter payload, concrete Hindsight query strings, a fixed output template, and named skill invocations; it is not 5 because several steps rely on conditional phrasing and placeholders ('If descriptive enough...').	4 / 5
Workflow Clarity	A clear Preamble plus numbered Steps 1–6 with explicit checkpoints (eval-mode gate, the main/master guard, the 'Don't guess' confirmation prompt, optional walkthrough) match 'clear sequence with most checkpoints present'; not 5 because some checkpoints are conditional rather than formal validation steps.	4 / 5
Progressive Disclosure	Content is well-organized into Preamble/Steps/Important with clearly signaled one-level references to sibling skills (codebase-walkthrough, /devflow:brainstorming, /devflow:render-diagram) and no nested bundle files; not 5 because the body exceeds ~50 lines and the long step-6 paragraph could be split out.	4 / 5
	Total	15 / 20 Passed

Description

51%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.

The description is concise and names concrete actions in a distinct niche, but it omits any explicit 'Use when' trigger and relies on technical jargon over natural user phrasing, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when launched inside a feature worktree after `devflow worktree` to orient context and begin a new feature.'

Add natural trigger terms users would actually say ('starting a new feature', 'begin feature work', 'new feature worktree') alongside the technical jargon.

Dimension	Reasoning	Score
Specificity	The description names the domain ('new feature worktree') and lists several concrete actions — 'detect context, recall memories, and transition to brainstorming' — matching the 'lists several specific actions; minor gaps' anchor; it is not a 5 because the actions remain high-level rather than fully comprehensive.	4 / 5
Completeness	A clear 'what' is present (post-launch setup with three named actions) but there is no 'Use when...' or equivalent explicit 'when' guidance, so per the rubric completeness is capped at 3 with 'when' only weakly implied by 'Post-launch setup for a new feature worktree'.	3 / 5
Trigger Term Quality	Terms lean technical ('post-launch setup', 'worktree', 'recall memories') with no explicit trigger clause, and the natural phrases a user would say ('starting a new feature', 'begin feature work') are largely missing; this sits below the midpoint rather than at 3, which requires more relevant natural keywords.	2 / 5
Distinctiveness Conflict Risk	The phrase carves a clear niche ('post-launch setup for a new feature worktree ... transition to brainstorming') that is mostly distinct from sibling skills, with only minor overlap risk against the brainstorming/devflow setup skills, matching the 'mostly distinct; minor overlap' anchor.	4 / 5
	Total	13 / 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: AndreJorgeLopes/devflow
Path: devflow-plugin/skills/new-feature/SKILL.md
Commit: bd4b70c

Reviewed: 17 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.