he-deepen-spec

Deepen an existing system or UI spec so boundaries, lifecycle rules, failure handling, and validation are strong enough for planning. Use when the user wants Harness Engineering spec hardening or a requirements review pass before planning.

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.

Well-structured, concise, and clearly sequenced with explicit validation gates. It loses points on actionability (some abstract guidance) and progressive disclosure (several referenced bundle paths are missing/broken).

Suggestions

Make remaining abstract steps actionable: define what "deepen lifecycle behavior" or "compare in prose" must produce (e.g., a required output template or checklist of lifecycle/failure cases).

Fix or remove broken reference paths — create the cited Infrastructure/references/contract.yaml, evals.yaml, task-profile.json and assets/ files, or repoint links to the references that actually exist.

Consolidate the overlapping routing/link sections (Full Context, Subagent Routing) to reduce navigation clutter and keep references clearly one level deep.

Dimension	Reasoning	Score
Conciseness	Lean imperative bullets with no padding and no explanation of concepts Claude already knows; every section (Philosophy, Procedure, Validation, Constraints, Anti-patterns) earns its tokens.	3 / 3
Actionability	Concrete deliverables and named artifacts ("Generate at least two meaningfully different interface shapes, each with signature/call shape, caller usage example", "Resolve available roles from ~/.codex/agents/manifest.json") mix with abstract directions ("compare in prose", "deepen lifecycle behavior"), landing at mostly actionable with some gaps.	2 / 3
Workflow Clarity	A numbered 7-step Procedure plus a Validation section with explicit gates and "Fail fast: stop at first failed gate and do not proceed" provides a clear sequence with an explicit checkpoint and halt/feedback loop.	3 / 3
Progressive Disclosure	The body signals an archived full guide and lists references under Full Context, but the canonical referenced paths (Infrastructure/references/contract.yaml, evals.yaml, task-profile.json, assets/) do not exist in the bundle and navigation is cluttered with multiple overlapping relative links.	2 / 3
	Total	10 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete actions, explicit "Use when" trigger, and a distinct niche. It is capped on trigger-term quality because the language is somewhat domain-internal rather than natural user phrasing.

Suggestions

Add more natural user-side trigger phrasing (e.g., "Use when a spec feels vague, contracts are unclear, or before turning a spec into a plan") alongside the Harness Engineering terminology.

Consider adding common term variants such as "requirements", "spec review", "contract definition" to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Deepen an existing system or UI spec" targeting "boundaries, lifecycle rules, failure handling, and validation" — which matches the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly states what it does (deepen spec for boundaries/lifecycle/failure/validation) and when via an explicit "Use when the user wants..." clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Relevant terms like "spec hardening" and "requirements review pass before planning" appear, but phrasing leans on domain jargon ("Harness Engineering spec hardening") and misses common user variations, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche trigger ("Harness Engineering spec hardening or a requirements review pass before planning") is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 4 missing, 3 deeper-than-1-level, 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Commit: 5a6027f

Reviewed: 5 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.