CtrlK
BlogDocsLog inGet started
Tessl Logo

he-refine

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

50

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

42%Scale 1-3

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

This skill provides a reasonable high-level framework for iterative refinement workflows with good structural organization and sensible constraints. However, it lacks concrete, executable guidance—no specific commands, tool names, or code examples—making it more of a process description than an actionable skill. The progressive disclosure claim is undermined by the absence of any referenced detail files or supporting documentation.

Suggestions

Add concrete commands or tool invocations to the Procedure steps (e.g., specific dev-server startup commands, browser probe methods, validation scripts).

Provide at least one complete input→output example showing the structured output format with schema_version, result, validation, blockers, and next action fields.

Create and link actual reference files for the detailed operational context mentioned in the opening line, or remove the progressive disclosure claim.

Make the iteration feedback loop in steps 3-5 explicit with a numbered sub-workflow showing the validate→fix→re-check cycle and concrete exit criteria.

DimensionReasoningScore

Conciseness

The content is mostly efficient but includes some unnecessary philosophical framing and redundant phrasing. Lines like 'This entrypoint stays concise and keeps full operational context in archived references' are meta-commentary that doesn't add actionable value. The anti-patterns section, while useful, partially restates constraints already covered.

2 / 3

Actionability

The procedure provides a clear sequence of steps but remains at a high abstraction level—no concrete commands, code snippets, or specific tool invocations are given. Steps like 'Resolve dev-server startup from launch config first' lack specifics on how to do this. The examples section shows user prompts but not expected outputs or concrete execution patterns.

2 / 3

Workflow Clarity

The procedure has a clear sequence and the validation section includes gate-based checks ('fail fast: stop at first failed gate'). However, the feedback loop between steps 3-4 is implicit rather than explicit, and there are no concrete validation commands or checkpoints—just declarative statements about what should be verified. For a workflow involving live server manipulation and iterative edits, the lack of explicit validation mechanics caps this at 2.

2 / 3

Progressive Disclosure

The skill references 'archived references' and a 'context-disposition policy' but provides no actual links to supporting documents. The 'Full Context' section only links to icon assets, not operational references. The claim of progressive disclosure architecture is unsupported by the actual bundle structure (no bundle files provided, no referenced detail files).

1 / 3

Total

7

/

12

Passed

Description

67%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 has a solid structure with both 'what' and 'when' clauses, which is good. However, the specific actions are somewhat vague and jargon-heavy ('lifecycle repair', 'tightening'), and the domain 'Harness Engineering' is not well-explained, making it hard for Claude to confidently select this skill. The trigger terms could better match natural user language.

Suggestions

Replace jargon like 'lifecycle repair' and 'tightening' with more concrete, user-facing actions (e.g., 'restructure project plans', 'remove redundant steps', 'fix broken workflows').

Add more natural trigger terms users would actually say, such as 'clean up plan', 'simplify spec', 'make actionable', 'streamline', or 'clarify requirements'.

DimensionReasoningScore

Specificity

Names some actions ('tightening, simplification, lifecycle repair') and a domain ('Harness Engineering artifacts, plans, specs'), but the actions are somewhat abstract and not concretely defined—what does 'lifecycle repair' or 'tightening' specifically entail?

2 / 3

Completeness

Explicitly answers both 'what' (refine Harness Engineering artifacts into clearer action plans) and 'when' ('Use when users ask for tightening, simplification, or lifecycle repair'), satisfying the completeness requirement with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Includes some relevant terms like 'tightening', 'simplification', 'action plans', 'specs', and 'lifecycle repair', but these are somewhat niche/jargon-heavy. Users might more naturally say 'clean up', 'simplify', 'refine plan', or 'improve spec' rather than 'lifecycle repair'.

2 / 3

Distinctiveness Conflict Risk

The 'Harness Engineering' qualifier provides some distinctiveness, but terms like 'refine', 'plans', 'specs', and 'simplification' are broad enough to overlap with general editing, planning, or documentation skills. 'Lifecycle repair' is distinctive but unclear.

2 / 3

Total

9

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
jscraik/Agent-Skills
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.