CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

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
SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

The content is well-structured with a clear, validated routing workflow and mostly concise, actionable guidance. Its main weakness is progressive disclosure: many referenced files are empty stubs or missing on disk, and one reference entry is malformed, undermining navigation reliability.

Suggestions

Restore the bundle files so references/contract.yaml, evals.yaml, and task-profile.json contain real content rather than path stubs, or remove the broken links from the References section.

Verify the ../../references/*.md paths (routing-map.json, deterministic-stage-routing.md, session-evidence-contract.md, etc.) resolve to existing files; the routing-map.json and deterministic-stage-routing.md targets are MISSING and are load-bearing for the Procedure.

Fix the malformed References entry where the 'Read when: routing could plausibly match...' line is stranded outside the deterministic-stage-routing.md list item, folding it into the list as the other entries are.

DimensionReasoningScore

Conciseness

The body is mostly lean with terse sections (When To Use, Inputs, Outputs, Procedure, Constraints) and assumes Claude's competence without over-explaining concepts, though the Procedure and Constraints sections repeat rule material also found in referenced files, leaving minor trim potential that keeps it at 4 rather than 5.

4 / 5

Actionability

It gives concrete, executable guidance: a deterministic decision order, explicit stage routing rules, named output fields (selected_stage, matched_rule, confidence), and a blocked-with-missing-input fallback, but the routing rules are instructions rather than copy-paste artifacts and the actual routing map lives in an external file, leaving minor gaps at 4 rather than 5.

4 / 5

Workflow Clarity

The Procedure is a clearly ordered 10-step sequence with an explicit validation/feedback gate: 'If still ambiguous after applying the table, return blocked with exactly one missing input' and a Validation section that fails fast at the first failed gate, matching the anchor 5 example of clear sequence with explicit checkpoints and a recovery loop.

5 / 5

Progressive Disclosure

The body references several one-level-deep files and signals some with 'Read when:' conditions, but the local references/ bundle files (contract.yaml, evals.yaml, task-profile.json) are empty path stubs rather than real content, the external ../../references/*.md targets do not exist, and one reference line is malformed (an inline 'Read when:' clause stranded outside a list item), so structure is present but reliability and organization are compromised at 3.

3 / 5

Total

16

/

20

Passed

Description

77%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.

The description is strong: it clearly states both the capability and explicit when-to-use trigger conditions with natural phrasing. It loses points on specificity (one routing action rather than several distinct operations) and minor trigger-term synonym coverage.

DimensionReasoningScore

Specificity

The description names the domain (route ambiguous HE requests to one lifecycle stage) and one concrete action (route), plus lists several concrete lifecycle verbs (start, resume, plan, implement, review, debug, schedule a heartbeat, resolve domain terminology), but routing is a single action category rather than multiple distinct concrete operations, so it sits at anchor 3 rather than 4.

3 / 5

Completeness

It explicitly 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') with concrete trigger phrases, matching the anchor 5 example.

5 / 5

Trigger Term Quality

It surfaces natural user phrases like 'where to start', 'resume', 'plan', 'review', 'debug', and 'schedule a heartbeat', which users would genuinely say, but it misses some synonyms and file/extension-style trigger tokens, placing it just above the midpoint at 4.

4 / 5

Distinctiveness Conflict Risk

The 'Harness Engineering' niche and the specific lifecycle-stage trigger list make it largely distinct and unlikely to fire for unrelated skills, but it could still overlap with adjacent HE lifecycle skills, so it is mostly distinct rather than a fully isolated niche (4 not 5).

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 9 suspicious

Warning

Total

14

/

16

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.