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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is a well-structured, actionable overview with clear sequencing, validation feedback loops, and disciplined progressive disclosure. Its sole weakness is density: several prose blocks run long and could be split for readability without losing content.

Suggestions

Tighten the dense "When to Use" and "Procedure" prose into shorter declarative bullets so each operational instruction earns its tokens more visibly.

Consider moving the long GPT-5.5 role-stack trigger paragraph ("You are GPT-5.5 acting as a senior software engineering reviewer...") into a reference file, keeping only a one-line pointer in the body.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows and stays operational, but the dense, jargon-packed compound sentences (e.g., the long "Use when an approved milestone... inspect repo, tracker, artifact" paragraph) could be tightened for readability, fitting the "mostly efficient but could be tightened" anchor rather than the lean level.	2 / 3
Actionability	Provides concrete executable validation commands (e.g., `python3 Plugins/harness-engineering/scripts/check_bluf_structure.py <spec-path> --json`), explicit output field lists, mode names, and status value enumerations — copy-paste-ready guidance.	3 / 3
Workflow Clarity	A numbered nine-step Procedure with explicit sequence, a Fail-fast Validation section recording pass/fail/blocked, block-on-failure feedback loops, and a Failure Mode with one recovery step — clear checkpoints for the write/mutation operations involved.	3 / 3
Progressive Disclosure	The body is an overview with a well-signaled `## References` section using condition-gated "Read when..." pointers to one-level-deep files (e.g., `references/contract.yaml`, `../../references/spec-plan-runtime-boundary-contract.md`), and the bundle references are real files, matching the clear-overview-with-one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 precise, trigger-equipped description that clearly conveys both capability and invocation conditions. Its only weakness is specialized jargon in the trigger clause that may not match a user's natural phrasing.

Suggestions

Add a plainer-language trigger variation (e.g., "Use when the user asks for a spec, acceptance criteria, or testable contract for a selected issue or slice") alongside the domain terms to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete deliverables — "Create bounded, evidence-backed Harness Engineering specs" that include "acceptance criteria, traceability, risk gates, and validation boundaries" — matching the multi-action anchor.	3 / 3
Completeness	Explicitly states what ("Create bounded, evidence-backed ... specs from approved intent") and when ("Use when a selected issue, milestone, reframe phase, or execution slice needs ..."), satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Trigger phrases ("selected issue, milestone, reframe phase, or execution slice") are domain-relevant but jargon-heavy and lack the common natural variations a user would casually say, fitting the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	Tightly scoped to Harness Engineering specs with triggers tied to a selected slice/milestone, giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
Commit: 5a6027f

Reviewed: 5 days 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.