CtrlK
BlogDocsLog inGet started
Tessl Logo

he-spec

Write Harness Engineering specs before planning. Use when a feature, QA report, Linear issue, or UI source needs a clear WHAT contract.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is well-structured, concise, and actionable with a concrete validation gate and clear routing rules, suiting an instruction-only skill. Progressive disclosure is good with a clear reference index, though several referenced files are not present in the local bundle to verify.

Suggestions

Consolidate the duplicated 'do not plan or implement code' guidance from Constraints and Gotchas into a single statement to tighten token use.

Expand the Procedure steps with concrete, executable actions (e.g., how to define acceptance IDs or what frontmatter keys are required) rather than staying at the high level.

Add a brief error-recovery note in Validation describing what to do when a gate fails beyond 'stop at the first failed gate'.

DimensionReasoningScore

Conciseness

The body is sectioned and largely avoids explaining concepts Claude already knows, but it repeats the 'do not plan sequencing or implement code' constraint in both Constraints and Gotchas and reuses several abstract phrases ('spec-mode decision', 'implementation-grade behavior contract') that add modest padding.

4 / 5

Actionability

It gives mostly concrete guidance including a copy-paste validation command ('python3 Infrastructure/scripts/validation-and-linting/he_linear_traceability_lint.py <spec-path>'), but the core spec-writing steps remain high-level rather than executable instructions.

4 / 5

Workflow Clarity

The Procedure lists a clear three-step sequence and the Validation section provides an explicit required gate with 'Stop at the first failed gate' as a checkpoint, satisfying the destructive/batch feedback-loop requirement, though error-recovery detail is thin.

4 / 5

Progressive Disclosure

The SKILL.md is a well-organized overview that points to several one-level-deep reference paths (SKILL.full.md, spec-artifacts.md, spec-modes.md, subagent-routing.md) with a clear References section; the in-repo references/ directory holds only context-preservation.md, so most cited paths live outside this bundle, slightly limiting navigability.

4 / 5

Total

16

/

20

Passed

Description

85%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 is clear, complete, and distinctive, explicitly answering both what it does and when to use it with concrete triggers. It could list a broader set of concrete actions to reach full specificity, but it avoids vague fluff and over-claims.

DimensionReasoningScore

Specificity

Names a specific domain (Harness Engineering specs) and concrete actions ('Write Harness Engineering specs before planning'), but the action set is narrow (one verb) rather than multiple distinct concrete operations.

4 / 5

Completeness

It explicitly states what the skill does ('Write Harness Engineering specs before planning') and when to use it ('Use when a feature, QA report, Linear issue, or UI source needs a clear WHAT contract'), satisfying both what and when with a concrete trigger clause.

5 / 5

Trigger Term Quality

Covers several natural trigger nouns ('feature, QA report, Linear issue, or UI source') that a user would plausibly mention, though it relies on product-specific jargon (Linear, Harness Engineering) rather than broad synonyms.

4 / 5

Distinctiveness Conflict Risk

The WHAT-before-HOW contract framing and Linear/spec-specific triggers carve a clear niche distinct from planning or implementation skills, minimizing conflict risk.

5 / 5

Total

18

/

20

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

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.