CtrlK
BlogDocsLog inGet started
Tessl Logo

new-feature

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

58

Quality

66%

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 ./skills/new-feature/SKILL.md
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 body is a well-structured, mostly executable orientation workflow with clear sequencing and guardrails, held back only by minor redundancy, a few templated rather than copy-paste snippets, and a dense inline pipeline paragraph.

Suggestions

De-duplicate the 'don't guess from the branch name / surface assumptions' guidance so it appears once, trimming conciseness redundancy.

Move the dense end-of-step-6 pipeline/phase-handoff mechanics into a short pointer or reference, keeping the step focused on the immediate transition action.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence (concrete bash/JSON snippets, no basic-concept padding), with only minor trimmable redundancy — e.g., the 'don't guess from the branch name' guidance restated across step 4 and the Important section — placing it above the 3-anchor but short of the fully lean 5-anchor.

4 / 5

Actionability

Guidance is largely executable — real commands (`git branch --show-current`, `printf <title-set sequence>`), a concrete `mark_chapter` payload, and explicit Hindsight query strings — with only minor gaps (the query strings are pattern templates rather than copy-paste calls), fitting the 'mostly executable' 4-anchor.

4 / 5

Workflow Clarity

A clear Preamble + Steps 1–6 sequence with checkpoints (branch-is-main guard, ask-before-guessing confirmation, eval-mode guardrail) is present; it lacks an explicit validate→fix→retry feedback loop, but the skill is non-destructive so the destructive-operation cap does not apply, keeping it at the 4-anchor rather than 5.

4 / 5

Progressive Disclosure

Content is a single self-contained file with well-organized sections (Preamble, Steps, Important) and no nested references — cross-links are to peer skills, not bundle files — which is good structure with only minor organization gaps (the dense inline phase-handoff paragraph), sitting at the 4-anchor.

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 states concrete actions and a distinct niche but omits any 'Use when' trigger guidance and relies on somewhat internal terminology, which caps completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit 'Use when ...' clause naming the natural trigger (e.g., 'Use when you are launched inside a new feature worktree and need to orient before brainstorming').

Broaden trigger terms with user-natural synonyms (e.g., 'starting a new feature', 'feature worktree setup') rather than only devflow-internal phrasing.

DimensionReasoningScore

Specificity

Names the domain (new feature worktree) and three concrete actions — 'detect context, recall memories, and transition to brainstorming' — leaving only minor coverage gaps, so it sits above the 3-anchor (1-2 actions) but below the comprehensive 5-anchor.

4 / 5

Completeness

It clearly states the 'what' (post-launch setup actions) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like 'new feature worktree' and 'brainstorming' are relevant but lean toward internal/devflow jargon rather than the natural phrases a user would say, and lack common synonyms — matching the 'some relevant keywords but missing variations' anchor rather than the 4-anchor's fuller coverage.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly specific — post-launch setup inside a feature worktree — giving it distinct triggers with only minor overlap risk against related devflow skills, fitting the 'mostly distinct' 4-anchor rather than the fully clear-niche 5-anchor.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.