he-spec

Create bounded, evidence-backed Harness Engineering specs from approved intent. Use when a selected issue, milestone, reframe phase, or execution slice needs acceptance criteria, traceability, risk gates, and validation boundaries before planning or implementation.

Quality

78%

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/skills/he-spec/SKILL.md

Quality

Content

81%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-structured, action-oriented spec-generation skill with strong workflow sequencing and validation feedback loops. The main gap is progressive disclosure: several references point outside the bundle and the locally bundled reference files are not connected to the body.

Suggestions

Wire the bundled references/ files (contract.yaml, evals.yaml, task-profile.json) into the body or relocate the externally-pointed ../../references and Plugins/... paths so the skill is self-contained and navigable.

Consolidate the long field-name enumerations in Outputs and Validation into a concise table or a single referenced contract to reduce token weight while preserving actionability.

Dimension	Reasoning	Score
Conciseness	The body is dense and instruction-only, assuming Claude's competence with no padding about known concepts, though the field-name lists and gate enumerations add some bulk that could be trimmed.	4 / 5
Actionability	It gives concrete executable commands (check_bluf_structure.py, check_generated_artifact_shape.py with flags), explicit field lists, and clear block conditions, with only minor gaps around per-mode invocation detail.	4 / 5
Workflow Clarity	The 9-step procedure is explicitly sequenced with fail-fast validation, pass/fail/blocked gate recording, block conditions, and one-recovery-step feedback loops for destructive or batch operations.	5 / 5
Progressive Disclosure	The condition-signaled "Read when X -> path" References block is well-organized one-level navigation, but several cited paths point outside the skill bundle and the bundled references/ files (contract.yaml, evals.yaml) are not wired into the body.	4 / 5
	Total	17 / 20 Passed

Description

76%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 answers both what and when with concrete trigger phrases and a distinct niche. Trigger-term quality is the weakest area because the phrasing is jargon-heavy rather than user-natural.

Suggestions

Add more user-natural trigger synonyms alongside the HE jargon (e.g., "write a spec", "define acceptance criteria", "spec out a feature") so users phrase requests in plain language.

Soften specialized terms like "reframe phase" and "execution slice" with a brief plain-language gloss so the trigger is recognizable beyond the HE workflow.

Dimension	Reasoning	Score
Specificity	"Create bounded, evidence-backed Harness Engineering specs" names the domain and lists several concrete deliverables (acceptance criteria, traceability, risk gates, validation boundaries), with only minor jargon-dense gaps in coverage.	4 / 5
Completeness	It explicitly states what the skill does (create bounded specs from approved intent) and gives a concrete "Use when..." clause with multiple trigger conditions.	5 / 5
Trigger Term Quality	"selected issue, milestone, reframe phase, or execution slice" are domain-relevant triggers, but they lean on specialized HE jargon and miss the more natural synonyms a user would commonly say.	3 / 5
Distinctiveness Conflict Risk	The Harness Engineering spec niche with its specific triggers is mostly distinct from sibling skills, with only minor overlap risk against other he-* planning skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/skills/he-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.