he-router

Route ambiguous Harness Engineering requests to one lifecycle stage when users ask where to start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain terminology.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

55%

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, instruction-only routing procedure with clear sequencing and validation, but it leans on external reference files that are missing from the bundle, which undermines both actionability and progressive disclosure.

Suggestions

Create or relocate the missing ../../references/* files (routing-map.json, deterministic-stage-routing.md, session-evidence-contract.md, subagent-routing.md, deferred-context-index.md, domain-model-routing.md, qa-intake-routing.md) so the cited routing tables and contracts actually exist, or rewrite the Procedure to be self-contained.

Tighten Procedure steps by dropping the trailing 'because ...' justifications; the deterministic order and Constraints already convey the rationale.

Inline the essential routing precedence (or a compact version of routing-map.json) so the core action does not depend on an absent file, then point to the deeper references for edge cases.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and skimmable with no concept over-explanation, but several Procedure steps carry justifying clauses ('because direct invocations and lifecycle state should beat broad keyword matches') that pad tokens without adding routing instruction, so it is not fully lean.	2 / 3
Actionability	Routing rules give concrete stage targets and a deterministic decision order, but the actionable core is prose procedure heavily dependent on external files (routing-map.json, deterministic-stage-routing.md) that are not present in the bundle, leaving guidance incomplete without them.	2 / 3
Workflow Clarity	A clear 10-step sequence is paired with a Validation section and 'Fail fast at first failed gate', providing explicit checkpoints and an error-recovery feedback loop as the top anchor requires.	3 / 3
Progressive Disclosure	Although sections and a References list are well organized, seven of the cited ../../references/* files (routing-map.json, deterministic-stage-routing.md, session-evidence-contract.md, subagent-routing.md, deferred-context-index.md, domain-model-routing.md, qa-intake-routing.md) do not exist in the bundle, leaving dangling navigation that breaks discovery.	1 / 3
	Total	8 / 12 Passed

Description

100%

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 concise, third-person, and answers both what the skill does and when to use it with a strong set of natural trigger terms. It carves out a distinct niche and avoids fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Route ... to one lifecycle stage' with 'start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain terminology'), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Route ambiguous Harness Engineering requests to one lifecycle stage') and when ('when users ask where to start...'), matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Covers natural terms users would say ('where to start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain terminology'), aligning with the 'good coverage of natural terms' anchor rather than the 'some relevant keywords' level below.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche ('Harness Engineering' lifecycle routing) with distinct triggers, unlikely to conflict with unrelated skills; not the 'somewhat specific but could overlap' level below.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 9 suspicious	Warning

	Total	14 / 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.