CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-code-feature-spec

This skill should be used when the user says "feature spec", "arness code feature spec", "arn-code-feature-spec", "spec this feature", "help me spec", "design this feature", "feature design", "write a spec", "create a specification", "I have an idea for a feature", "let's flesh out this feature", "decompose feature", "spec XL feature", "resume spec", "continue spec", "finish my spec", "break down feature", or wants to iteratively develop a feature idea into a well-formed specification through guided conversation with architectural analysis. For XL features with decomposition hints, creates multiple sub-feature specs with full traceability. Produces specification documents capturing WHAT to build and WHY, which then feed into plan creation.

74

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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, highly actionable workflow with strong sequencing, validation checkpoints, and clean progressive disclosure into real reference files. Its only weakness is conciseness: sketch-context and draft-lifecycle handling is duplicated across several steps and could be consolidated.

Suggestions

Consolidate the repeated sketch-context handling (Step 2 detection, Step 3c offer, Step 4 on-demand capture, Step 5 population) into one canonical block or a dedicated reference, since the manifest-field capture language recurs nearly verbatim across four steps.

Centralize the DRAFT lifecycle (Step 3d write, Step 4 update protocol, Error Handling, Step 5 finalization) into a single reference to remove duplicated draft-handling prose.

Trim meta-rationale sentences such as "This prevents scope creep by ensuring the agent knows what sibling features already handle..." since Claude can infer the purpose from the stated rule.

DimensionReasoningScore

Conciseness

It avoids explaining basics Claude already knows, but sketch-context handling (manifest field capture) and DRAFT-lifecycle prose are repeated nearly verbatim across Steps 2, 3c, 4, and 5, and several meta-rationale sentences could be trimmed — the score-2 anchor of mostly efficient but could be tightened.

2 / 3

Actionability

Highly actionable with concrete regex (`F-\d{3}`, `UC-\d{3}`), exact file paths, structured agent prompt blocks, AskUserQuestion option text, and executable `gh issue create` commands in the bundle — fully concrete, copy-ready guidance matching the score-3 anchor.

3 / 3

Workflow Clarity

Clearly sequenced Steps 0–5 with sub-steps, explicit checkpoints (draft detection in 2b, readiness check in Step 4, finalization checklist in Step 5), and error-recovery feedback loops (draft delete/recreate, sketch manifest validation, write-failure fallbacks) matching the score-3 anchor.

3 / 3

Progressive Disclosure

The body is an overview that delegates heavy procedures to real one-level-deep reference files (greenfield-loading.md, xl-decomposition.md, feature-spec-template.md, agent-invocation-guide.md, all present in ./references/), each clearly signaled with "Read ... for the full ..." — matching the score-3 well-signaled one-level-deep reference anchor.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong across all dimensions: it states concrete actions, provides a rich set of natural trigger phrases, explicitly covers both what the skill does and when to use it, and carves out a distinct spec-authoring niche in third-person voice. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: "iteratively develop a feature idea into a well-formed specification", "creates multiple sub-feature specs with full traceability", and "Produces specification documents capturing WHAT to build and WHY" — matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both halves: "This skill should be used when the user says..." (when) and the producing-specification/feeding-plan-creation statements (what), satisfying the score-3 anchor of clearly answering both with explicit triggers.

3 / 3

Trigger Term Quality

Extensive natural-language triggers a user would actually say ("feature spec", "spec this feature", "help me spec", "write a spec", "I have an idea for a feature", "resume spec", "break down feature"), giving comprehensive coverage well beyond the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

The specification-authoring niche is clearly distinct from downstream planning/coding, and the trigger cluster ("spec this feature", "decompose feature", "resume spec") is unlikely to fire for unrelated skills, matching the score-3 clear-niche anchor.

3 / 3

Total

12

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
AppsVortex/arness
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.