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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Infrastructure/references/deferred-skill-context/harness-engineering-he-router/SKILL.md

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-organized routing skill with good progressive disclosure and clear references, but it suffers from missing concrete output examples (no sample structured response is shown) and some ambiguity in how the procedure steps interact with each other. The skill would benefit from a concrete input→output example and tighter integration of validation into the workflow steps.

Suggestions

Add at least one complete input→output example showing the expected structured response (selected_stage, matched_rule, confidence, rationale, next_invocation, subagent policy) so Claude knows the exact output format.

Clarify the relationship between step 2 (deterministic decision order) and steps 4-7 (specific routing rules)—are steps 4-7 the implementation of step 2, or do they run after it? Consider restructuring as sub-steps.

Integrate validation checkpoints inline within the procedure (e.g., after step 3: 'Verify selected stage exists in routing-map.json before continuing') rather than listing them in a separate section at the end.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some redundancy—several routing rules in the Procedure section overlap with Anti Patterns and Constraints, and the Examples section lists natural-language scenarios without showing expected outputs, adding bulk without proportional value. Some steps could be consolidated.	2 / 3
Actionability	The procedure provides a deterministic decision sequence and names specific stages, but the actual routing logic is deferred to external references (routing-map.json, deterministic-stage-routing.md) that are not provided. There are no concrete output examples showing the expected structured response format (e.g., a sample JSON with selected_stage, matched_rule, confidence, etc.), making it incomplete for copy-paste execution.	2 / 3
Workflow Clarity	The 10-step procedure is sequenced and includes a 'fail fast' validation section, but validation checkpoints are listed separately at the end rather than integrated inline. The feedback loop for ambiguity (step 10: return blocked) is present but there's no explicit retry/re-prompt mechanism. The interaction between steps 4-7 (which all route different request types) and step 2 (deterministic decision order) is unclear—it's not obvious whether steps 4-7 are sub-cases of step 2 or overrides.	2 / 3
Progressive Disclosure	The skill is well-structured as an overview with clear, one-level-deep references to external files. Each reference includes a 'Read when' annotation explaining when to consult it. The main body stays at routing-logic level while deferring detailed contracts, evals, and domain-specific routing to separate files.	3 / 3
	Total	9 / 12 Passed

Description

89%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.

This is a well-structured description that clearly defines its routing/disambiguation purpose within the Harness Engineering domain. It provides explicit trigger scenarios and a clear 'when' clause. The main weakness is that the core capability ('route to one lifecycle stage') is somewhat abstract—it could benefit from slightly more specificity about what the routing actually produces or does.

Dimension	Reasoning	Score
Specificity	The description names a domain ('Harness Engineering requests') and lists several actions (start, resume, plan, implement, review, debug, schedule a heartbeat, resolve domain terminology), but the core action is 'route to one lifecycle stage' which is somewhat abstract. The listed items are more like trigger scenarios than concrete capabilities.	2 / 3
Completeness	The description answers both 'what' (route ambiguous Harness Engineering requests to one lifecycle stage) and 'when' (when users ask where to start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain terminology). The 'when' clause is explicit with multiple trigger scenarios.	3 / 3
Trigger Term Quality	Good coverage of natural terms users would say: 'where to start', 'resume', 'plan', 'implement', 'review', 'debug', 'schedule a heartbeat', 'resolve domain terminology'. These are specific, varied trigger phrases that map well to user intent.	3 / 3
Distinctiveness Conflict Risk	The description is highly specific to 'Harness Engineering' and 'lifecycle stage' routing, with domain-specific terms like 'heartbeat' scheduling. This creates a clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: jscraik/Agent-Skills
Path: Infrastructure/references/deferred-skill-context/harness-engineering-he-router/SKILL.md
Commit: d933d80

Reviewed: 21 hours 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.