spec-feature

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with a clear, gated multi-step workflow and concrete commands throughout. Its main weaknesses are modest verbosity in the preamble and handoff prose, and the absence of any external reference structure to offload the large inline spec template.

Suggestions

Trim the diagram-complexity preamble and the internal description of what the phase-handoff skill does, since that detail lives in the handoff skill itself.

Consider extracting the spec document template into a references/ file referenced one level deep, keeping only the section skeleton inline.

No validation/verification step is required for this non-destructive planning skill, so the workflow_clarity cap does not apply; the current gates are already strong.

Dimension	Reasoning	Score
Conciseness	The workflow is largely lean and assumes Claude's competence, but the diagram-complexity preamble and the step-8 handoff prose describing what another skill does internally add some unnecessary tokens that could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: the regex '[A-Z]+-[0-9]+', the exact mark_chapter payload, a bash one-liner, the precise spec file path and template, and exact slash-command invocations with arguments.	3 / 3
Workflow Clarity	An explicit 8-step ordered sequence with checkpoints: clarifying questions in step 1, an explicit user-review gate in step 6, and a gated handoff in step 8, giving clear feedback loops and sequence.	3 / 3
Progressive Disclosure	Sections are clearly organized but there are no bundle/reference files, so the large inline spec template stays in the main file rather than being split into one-level-deep references.	2 / 3
	Total	10 / 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 explicit 'when to use' trigger guidance, which limits both completeness and trigger-term coverage. Adding a 'Use when...' clause with natural trigger phrases would raise the weaker dimensions.

Suggestions

Add a 'Use when ...' clause naming natural triggers like 'Use when designing or planning a new feature, writing a feature spec, or breaking a feature into implementation tasks.'

Broaden trigger terms to common variations a user would say (e.g. 'feature spec', 'design a feature', 'requirements', 'implementation plan').

Keep the concrete action list but front-load the trigger context so the 'when' is as explicit as the 'what'.

Dimension	Reasoning	Score
Specificity	Enumerates four distinct concrete actions ('recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks'), matching the level-3 anchor for listing multiple specific actions rather than just naming a domain.	3 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains the natural phrase 'spec a new feature' but lacks common variations such as 'design a feature', 'feature spec', or 'requirements', so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	'Spec a new feature' identifies a recognizable niche but without explicit trigger phrases it could still overlap with general planning or architecture skills.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: AndreJorgeLopes/devflow
Commit: 9556c94

Reviewed: 2 days 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.