CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

new-feature

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

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is a well-sequenced, highly actionable orientation workflow with concrete commands, exact templates, and thoughtful edge-case handling (eval mode, missing mark_chapter, wrong branch). Its main weaknesses are minor: an unspecified Hindsight invocation, a verbose downstream-pipeline paragraph, and a few missing checkpoints. It is a solid, near-exemplary procedural skill body.

DimensionReasoningScore

Conciseness

The body is efficient, procedural, and assumes competence, but contains minor over-explanation that could be trimmed: the dense downstream-pipeline paragraph in step 6 and the repeated 'don't guess from the branch name' caveat (step 4 and the Important section). Not 5 because those tokens don't all earn their place; not 3 because the padding is minor rather than 'some unnecessary explanation' throughout.

4 / 5

Actionability

Provides mostly executable guidance: copy-paste-ready git commands, the terminal-title printf command, the exact mark_chapter payload, exact memory-query strings, a concrete output template, and verbatim user-facing questions. Not 5 because the Hindsight recall never names the actual tool or command to invoke, leaving a minor gap.

4 / 5

Workflow Clarity

Clear Preamble → Steps 1-6 sequence with most checkpoints present: redirect if on main/master, confirm understanding before proceeding, fallback if mark_chapter is unavailable, and the eval-mode stop condition. Not 5 because a few checkpoints are missing (e.g. no verification that the optional walkthrough completed before transitioning); no destructive or batch operations, so the cap-at-3 rule does not apply.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized into Preamble/Steps/Important sections with one-level-deep references to other skills (devflow:brainstorming, codebase-walkthrough). Not 5 because at ~85 lines the inlined downstream-pipeline detail in step 6 is a minor organization gap that could live elsewhere; not 3 because structure is good and nothing is buried or nested.

4 / 5

Total

16

/

20

Passed

Description

58%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 communicates a clear, reasonably specific purpose with three named actions, but it lacks any explicit 'when to use this' trigger guidance and leans on devflow-specific jargon rather than natural user phrases. This caps completeness and trigger-term quality at the midpoint. Adding an explicit trigger clause with natural synonyms would lift the description substantially.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when launched inside a feature worktree after `devflow worktree` has created it, to orient and kick off a new feature.'

Include natural user-facing trigger terms and synonyms (e.g. 'new feature', 'feature branch', 'start a feature', 'brainstorm') alongside the framework jargon like 'worktree' and 'Hindsight'.

Round out capability coverage by mentioning the optional codebase walkthrough and context presentation so the 'what' is comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions ('detect context, recall memories, and transition to brainstorming') within a clearly named domain (post-launch setup for a feature worktree). Not 5 because coverage is incomplete — presenting workspace context and the optional walkthrough are unmentioned; not 3 because more than 1-2 concrete actions are named.

4 / 5

Completeness

The 'what' is clear (post-launch setup: detect context, recall memories, transition to brainstorming) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3. The 'when' is only weakly implied by 'Post-launch' and 'for a new feature worktree'.

3 / 5

Trigger Term Quality

Contains relevant keywords ('feature worktree', 'recall memories', 'brainstorming') but they are framework-jargon-heavy and miss natural user phrasings and synonyms like 'start a new feature' or 'feature branch'. Fits the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor above.

3 / 5

Distinctiveness Conflict Risk

'Post-launch setup for a new feature worktree' carves a mostly distinct niche with minor overlap risk against closely related orientation or brainstorming skills. Not 5 because the absence of explicit triggers makes unintended triggering somewhat more plausible; not 3 because the domain is quite specific.

4 / 5

Total

14

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

AndreJorgeLopes/devflow

Path

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

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.