he-refine

Refine Harness Engineering artifacts, plans, specs, or work into clearer action plans. Use when users ask for tightening, simplification, or lifecycle repair.

Quality

67%

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/skills/team_automation/he-refine/SKILL.md

Quality

Content

63%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.

The skill body is well-structured and concise with a clear sequenced procedure and validation gates, but its guidance is instruction-level without executable specifics and its progressive disclosure claim is undermined by reference files that are never linked and asset links that point to missing files.

Suggestions

Add concrete, executable commands for the dev-server steps (e.g., the actual probe/health-check command and port-detection approach) so the procedure is copy-pasteable.

Link the real ./references/ files (contract.yaml, evals.yaml, task-profile.json) from the body, or remove the 'archived references' claim if they are not meant to be navigated.

Fix or remove the ./assets/ icon links in 'Full Context' since those asset files do not exist in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is compact, sectioned into short bullets, and largely avoids explaining concepts Claude already knows; minor padded phrasing like 'Keep polish work measurable and bounded to user-visible outcomes' keeps it at 4 rather than a fully lean 5.	4 / 5
Actionability	Steps such as 'Resolve dev-server startup from launch config first, then fall back to project-type and port detection' are concrete in intent but give no executable commands or specifics on how to detect ports/probe readiness; this is actionable guidance with missing key details (3), not mostly-executable (4).	3 / 5
Workflow Clarity	A clear numbered Procedure (1–5) pairs with an explicit Validation section and a 'Fail fast: stop at first failed gate' checkpoint, giving most checkpoints; it lacks an explicit fix→retry feedback loop for server-startup failure, so it is 4 rather than 5.	4 / 5
Progressive Disclosure	The body claims 'keeps full operational context in archived references' but never links the actual ./references/ files (contract.yaml, evals.yaml, task-profile.json), and the only 'Full Context' links point to ./assets/ icons that are not present; references exist in the bundle but are not signaled or navigable, matching anchor 3.	3 / 5
	Total	14 / 20 Passed

Description

71%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.

The description cleanly answers both what and when with concrete triggers, giving it strong completeness and reasonable distinctiveness within the Harness Engineering niche. It is slightly weaker on specificity and trigger-term coverage, naming one umbrella action and a few synonyms but missing common variations.

Suggestions

Enumerate the concrete refinement actions explicitly (e.g., 'tightens acceptance criteria, simplifies scope, repairs stalled or broken lifecycle stages') to lift specificity.

Add natural user-facing synonyms such as 'clean up', 'clarify', or 'polish' alongside 'tightening/simplification' to broaden trigger coverage.

Keep the 'Use when...' clause but make the trigger verbs match phrases users actually say verbatim.

Dimension	Reasoning	Score
Specificity	Quotes 'Refine Harness Engineering artifacts, plans, specs, or work into clearer action plans' — it names the domain and one core action (refine into action plans) but does not enumerate multiple distinct concrete actions; not below 2 (it is not merely generic) nor at 4 (it does not list several specific actions).	3 / 5
Completeness	It explicitly states both what ('Refine Harness Engineering artifacts, plans, specs, or work into clearer action plans') and when ('Use when users ask for tightening, simplification, or lifecycle repair') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Triggers 'tightening, simplification, or lifecycle repair' are relevant and somewhat natural, but it misses common synonyms a user would say ('clean up', 'clarify', 'polish', 'tighten this plan'); sits at anchor 3 rather than 4 due to missing variations.	3 / 5
Distinctiveness Conflict Risk	'Harness Engineering artifacts' and 'lifecycle repair' carve a fairly distinct niche with low overlap risk, but 'tightening/simplification' could overlap with general plan-polishing skills, so it is mostly distinct (4) rather than a clear niche (5).	4 / 5
	Total	15 / 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: 2 missing	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/skills/team_automation/he-refine/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.