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.

57

Quality

66%

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/deferred-store/skills/team_automation/he-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 is a well-structured organizational skill that effectively serves as an overview with good progressive disclosure to detailed references. Its main weaknesses are the abstract procedure (no concrete examples of spec output format, frontmatter structure, or acceptance ID patterns) and some redundancy across sections. Adding a concrete example of a minimal spec artifact and consolidating duplicated guidance would significantly improve it.

Suggestions

Add a concrete example showing what a minimal spec artifact looks like — including sample Linear frontmatter, an SA/VAC acceptance ID, and the traceability table format — so Claude knows exactly what to produce.

Consolidate duplicated guidance: 'Do not plan sequencing or implement code' appears in Core Contract, Constraints, and Gotchas. State it once in Constraints.

Expand the 3-step Procedure with sub-steps or at least link to a reference that details each step, since the current level of abstraction leaves too much ambiguity about what 'define expected behavior' concretely means in output terms.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but has some redundancy — 'Do not plan sequencing or implement code from this skill' appears in both Constraints and Gotchas, and several sections (Philosophy, When to use, Examples) add minimal value beyond what the opening line already conveys. Some sections like 'Failure mode' and 'Anti-patterns' could be consolidated.

2 / 3

Actionability

The skill provides a concrete validation command (`python3 Infrastructure/scripts/validation-and-linting/he_linear_traceability_lint.py <spec-path>`) and names specific deliverables (SA/VAC IDs, Linear frontmatter), but the procedure is abstract (3 high-level steps with no concrete examples of what a spec looks like, what frontmatter format to use, or what acceptance IDs look like). The examples section gives only trigger phrases, not input/output examples.

2 / 3

Workflow Clarity

The procedure lists 3 steps and the validation section provides a gate-based approach with 'stop at first failed gate,' which is good. However, the procedure steps are too high-level to be truly actionable, and the validation gates don't form a clear feedback loop (e.g., what to do when the lint script fails beyond 'stop'). The routing to he-deepen-spec for gaps is a useful checkpoint but is mentioned in multiple places without a unified flow.

2 / 3

Progressive Disclosure

The References section provides clear, one-level-deep pointers to the full guide, spec artifact contract, spec mode rules, and routing references. The SKILL.md serves as a concise overview with well-signaled paths to detailed materials. The structure is well-organized with distinct sections for different concerns.

3 / 3

Total

9

/

12

Passed

Description

75%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 an explicit 'Use when' clause and clear niche positioning, which are its main strengths. However, it lacks specificity about what concrete actions the skill performs beyond 'write' and relies on some domain-specific jargon ('WHAT contract') that may not match natural user language. Adding more concrete actions and common trigger term variations would improve it.

Suggestions

List specific concrete actions the skill performs, e.g., 'Defines acceptance criteria, outlines scope boundaries, structures requirements sections' to improve specificity.

Add more natural trigger term variations users might say, such as 'requirements doc', 'technical spec', 'specification', 'PRD', or 'define requirements'.

DimensionReasoningScore

Specificity

It names a specific artifact ('Harness Engineering specs') and mentions the purpose ('clear WHAT contract'), but doesn't list concrete actions beyond 'write'. It lacks detail on what writing a spec entails (e.g., defining acceptance criteria, outlining requirements, structuring sections).

2 / 3

Completeness

It explicitly answers both 'what' (write Harness Engineering specs before planning) and 'when' (when a feature, QA report, Linear issue, or UI source needs a clear WHAT contract), with a clear 'Use when' clause listing specific trigger scenarios.

3 / 3

Trigger Term Quality

Includes some relevant trigger terms like 'feature', 'QA report', 'Linear issue', 'UI source', and 'spec'. However, it misses common variations users might say such as 'requirements', 'specification', 'engineering document', 'PRD', or 'technical spec'. 'WHAT contract' is domain-specific jargon that users may not naturally use.

2 / 3

Distinctiveness Conflict Risk

The description is quite specific to 'Harness Engineering specs' and the 'WHAT contract' concept, making it a clear niche that is unlikely to conflict with general documentation, planning, or coding skills.

3 / 3

Total

10

/

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.