CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-feature

Spec a new feature — recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks.

55

Quality

62%

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/spec-feature/SKILL.md

The canonical home for this skill is spec-feature in AndreJorgeLopes/devflow

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete tool calls, paths, and a complete spec template, but it is weighed down by verbose asides and a monolithic structure with no progressive disclosure of the template or background into separate files.

Suggestions

Trim the step-8 handoff paragraph to the essential invocation and arguments; move spawn_task/worktree internals into a reference file or drop them since the handoff skill owns that behavior.

Extract the full spec-document template into a bundled template file (e.g. references/spec-template.md) and reference it one level deep, reducing the inline body.

Add an explicit validation checkpoint for the spec (e.g. 'Confirm every Acceptance Criterion is observable and every task maps to an AC before handoff') to lift workflow clarity toward 3.

DimensionReasoningScore

Conciseness

The body is mostly efficient and instructional, but verbose asides — the diagram-complexity block, the long step-8 explanation of spawn_task internals and worktree forking, and the ELI5 rendering detail — pad beyond what Claude needs; not score 3 because some tokens do not earn their place.

2 / 3

Actionability

Provides concrete file paths (docs/specs/<feature-name>.md), named tool calls (mark_chapter, recall, retain, phase-handoff), an exact bash window-title snippet, a full spec template, and image-embed snippets — fully executable and copy-paste ready.

3 / 3

Workflow Clarity

The 8-step sequence is clearly ordered with some checkpoints (clarifying questions before proceeding, present spec for review, explicit handoff boundary), but there is no validate→fix→retry feedback loop for the spec artifact itself, so it falls short of the explicit-validation anchor at score 3.

2 / 3

Progressive Disclosure

No bundle files exist and the body is a 130-line monolith with the full spec template and long prose inline; content that could be split into a reference file is kept inline, so it is structured but not optimally disclosed.

2 / 3

Total

9

/

12

Passed

Description

60%

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 specific and action-oriented but omits any 'Use when' trigger guidance, so it fails to tell Claude when to invoke it and caps completeness and trigger-term quality at 2.

Suggestions

Add a 'Use when ...' clause naming natural triggers, e.g. 'Use when the user wants to spec a new feature, plan a feature before coding, or turn a feature request into a spec and task list.'

Include common user phrasings like 'spec a feature', 'feature request', 'implementation plan', or 'break work into tasks' as trigger terms.

Tighten distinctiveness by contrasting with the downstream planning skill so it is clear this is the spec/plan phase, not the implementation phase.

DimensionReasoningScore

Specificity

Quotes 'recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks' — lists multiple specific concrete actions, matching the score-3 anchor; not score 2 because it goes beyond naming a domain plus a couple actions.

3 / 3

Completeness

Clearly states what the skill does, but the 'when to use it' half is entirely missing — per the judging guidelines a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

No 'Use when...' clause or natural trigger terms a user would say ('spec a feature', 'feature request'); only the action verbs are present, so coverage of natural keywords is partial and missing common variations.

2 / 3

Distinctiveness Conflict Risk

'Spec a new feature' carves out a niche but without explicit triggers it could still overlap with general planning/writing-plans skills, matching the 'somewhat specific but could overlap' anchor.

2 / 3

Total

9

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

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.