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

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-deepen-spec/SKILL.md

Quality

Content

71%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.

A well-organized, lean instruction-only skill with a clear sequenced procedure and explicit validation gates. Its main weakness is progressive disclosure: numerous referenced files are absent from the bundled references directory, so several navigation links are broken.

Suggestions

Resolve or remove broken bundle references: contract.yaml, evals.yaml, task-profile.json, subagent-routing.md, domain-model-routing.md, routing-map.json, and assets/ are cited but not present under ./references or ./assets.

Tighten redundancy between the Philosophy, When-to-use, and the frontmatter description to recover token budget.

Make the validation feedback loop explicit (validate -> fix -> re-validate -> only-then-proceed) in the Procedure rather than only in the separate Validation section.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, using terse bullets without explaining basic concepts, but the Philosophy and When-to-use sections slightly restate the description and could be trimmed, fitting anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Procedure steps give concrete, specific guidance (e.g., 'Generate at least two meaningfully different interface shapes, each with signature/call shape, caller usage example'), which is actionable for an instruction-only skill, with only minor gaps versus fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	A clear 7-step procedure is paired with a Validation section and 'Fail fast: stop at first failed gate and do not proceed', providing most checkpoints, but the fix-and-retry feedback loop is less explicit than the anchor-5 example, so anchor 4 is the best fit.	4 / 5
Progressive Disclosure	Structure and reference signaling are good (explicit 'Full Context' section, one-level-deep intent), but many referenced paths (contract.yaml, evals.yaml, task-profile.json, subagent-routing.md, assets/) do not exist in the local bundle where only references/context-preservation.md is present, leaving navigation partly broken.	3 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong description that clearly states both capability and trigger conditions in third person, with concrete actions and a well-scoped niche. It is held back only by slightly less-than-comprehensive keyword synonyms and minor overlap risk with adjacent spec skills.

Dimension	Reasoning	Score
Specificity	Names the spec-hardening domain and several concrete actions ('boundaries, lifecycle rules, failure handling, and validation'), with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Deepen an existing system or UI spec so boundaries, lifecycle rules, failure handling, and validation are strong enough for planning') and when ('Use when the user wants Harness Engineering spec hardening or a requirements review pass before planning') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('spec hardening', 'requirements review pass', 'before planning') giving good keyword coverage, though a few common synonyms are missing so it falls short of the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The 'Harness Engineering spec hardening' framing carves a clear niche with minimal conflict risk, but 'spec hardening'/'requirements review' are general enough to risk minor overlap with related spec skills, so anchor 4 fits better than 5.	4 / 5
	Total	17 / 20 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
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/team_automation/he-deepen-spec/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.