new-feature

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

Quality

56%

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/new-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 well-structured post-launch setup skill with strong actionability and clear workflow sequencing. Its main weakness is moderate verbosity — the pipeline overview and phase-handoff details in step 6 could be extracted to a reference file, and some points in the 'Important' section repeat earlier instructions. Overall it provides clear, executable guidance for the specific task.

Suggestions

Move the pipeline overview and phase-handoff mechanics (frozen-state files, mcp__ccd_session__spawn_task details) from step 6 into a separate PIPELINE.md reference to reduce inline verbosity.

Deduplicate the 'Important' section — several points (always recall from Hindsight, don't guess from branch name) are already stated in the steps above.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary verbosity — e.g., the pipeline overview at the end with phase-handoff details and the explanation of how spawned sessions work is context that could be in a separate reference. The repeated emphasis on not guessing and the optional diagram offer add some bloat. However, most content is relevant to the task.	2 / 3
Actionability	The skill provides concrete, executable bash commands for detecting workspace context, specific regex patterns for ticket ID extraction, exact Hindsight query formats, and a clear output template. The steps are copy-paste ready and leave little ambiguity about what to do.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced with numbered steps, explicit conditional logic (e.g., if on main/master, stop; if mark_chapter unavailable, skip silently), and a clear pipeline progression. The preamble is separated from the main steps, and the transition to brainstorming is well-defined with the full downstream pipeline shown.	3 / 3
Progressive Disclosure	The skill references other skills (codebase-walkthrough, devflow:brainstorming, devflow:render-diagram, devflow:phase-handoff) appropriately, but the pipeline details and phase-handoff mechanics in step 6 are inlined when they could be in a separate reference. No bundle files are provided, so we can't verify referenced paths. The content is reasonably organized but the 'Important' section partially repeats earlier content.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 moderately specific to a niche workflow (post-launch feature worktree setup) but relies on internal jargon and abstract action terms that would not naturally match user queries. It lacks an explicit 'Use when...' clause, and the actions described (detect context, recall memories) are vague rather than concrete.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when a new feature branch or worktree has just been created and the user wants to set up their working context.'

Replace abstract terms like 'detect context' and 'recall memories' with concrete actions, e.g., 'reads project configuration files, retrieves relevant stored notes and past decisions, and generates brainstorming prompts for next steps.'

Include natural keywords a user might say, such as 'new branch setup', 'feature kickoff', 'project onboarding', or 'start working on a new feature'.

Dimension	Reasoning	Score
Specificity	Names a domain (post-launch feature worktree setup) and some actions (detect context, recall memories, transition to brainstorming), but these actions are somewhat abstract and not fully concrete — 'detect context' and 'recall memories' are vague about what is actually being done.	2 / 3
Completeness	It describes 'what' at a high level (detect context, recall memories, transition to brainstorming) but lacks an explicit 'Use when...' clause or clear trigger guidance for when Claude should select this skill.	2 / 3
Trigger Term Quality	The terms used ('worktree', 'post-launch setup', 'recall memories', 'brainstorming') are internal/technical jargon unlikely to match natural user queries. A user would not naturally say 'post-launch setup for a new feature worktree' when requesting help.	1 / 3
Distinctiveness Conflict Risk	The mention of 'worktree' and 'post-launch' gives it some specificity, but 'brainstorming' and 'detect context' are generic enough to potentially overlap with other planning or context-gathering 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.