new-feature
Post-launch setup for a new feature worktree — detect context, recall memories, and transition to brainstorming.
52
56%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/new-feature/SKILL.mdQuality
Discovery
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 targets a narrow workflow (post-launch feature worktree setup) but uses abstract, jargon-heavy language that would be difficult for Claude to match against natural user requests. It lacks an explicit 'Use when...' clause and the actions described are vague rather than concrete, making it hard to distinguish from other context-gathering or planning skills.
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 actions like 'detect context' and 'recall memories' with concrete specifics, e.g., 'Reads recent git history, loads relevant project memories, and generates a brainstorming plan for next steps.'
Include natural keywords a user might say, such as 'new branch', 'feature setup', 'getting started on a feature', or 'initialize workspace'.
| 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' (detect context, recall memories, transition to brainstorming for a new feature worktree) but lacks an explicit 'Use when...' clause or equivalent trigger guidance, capping this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | The terms used ('worktree', 'post-launch setup', 'recall memories', 'brainstorming') are internal/technical jargon unlikely to match natural user language. A user would not typically say 'post-launch setup for a new feature worktree' when requesting help. | 1 / 3 |
Distinctiveness Conflict Risk | The description is somewhat specific to a post-launch worktree workflow, which narrows the niche, but terms like 'brainstorming' and 'detect context' are generic enough to potentially overlap with other planning or context-gathering skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
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 orchestration skill with clear, actionable steps and good workflow sequencing. Its main strengths are concrete commands, explicit conditional logic, and a clear pipeline overview. Weaknesses include some redundancy between the steps and the 'Important' section, and the lack of linked references to the skills and tools it depends on.
Suggestions
Remove or consolidate the 'Important' section — most points are already covered in the steps (e.g., 'always recall from Hindsight' duplicates step 2, 'never skip brainstorming' duplicates step 6).
Add file links or references to the dependent skills (codebase-walkthrough, brainstorming) and tools (Hindsight) so Claude can navigate to them if needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary verbosity — the 'Important' section repeats points already made in the steps (e.g., 'always recall from Hindsight' is already step 2), and some instructions like 'Don't guess from the branch name' are elaborated more than needed. The pipeline overview at the end is useful context but borderline. | 2 / 3 |
Actionability | Provides concrete, executable bash commands for workspace detection, specific regex patterns for ticket extraction, exact Hindsight query formats, a clear output template, and explicit tool invocations (mark_chapter, codebase-walkthrough, brainstorming). Each step tells Claude exactly what to do. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with numbered steps, explicit branching logic (e.g., if on main/master, stop and tell user), conditional steps (walkthrough is optional), and a clear pipeline overview showing what comes after. The guard against being on main/master and the 'ask before guessing' checkpoints serve as validation steps. | 3 / 3 |
Progressive Disclosure | References to other skills (codebase-walkthrough, brainstorming) and tools (Hindsight, mark_chapter, devflow:phase-handoff) are mentioned but not linked to files. The pipeline overview is inline rather than referenced. No bundle files are provided, so there's no supporting structure, but the skill does appropriately delegate to other skills rather than inlining everything. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%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
b0b1bb6
- Reviewed
Table of Contents
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.