CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

routing-card-authoring

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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-organized, high-signal reference spec: exact per-field rules, honest gating guidance, and a runnable checklist with validation. Its main weaknesses are the absent worked-example card, missing fix-and-revalidate recovery steps, and dangling pointers to bundle files that are not shipped alongside it.

Suggestions

Ship or inline a minimal valid routing-card example: 'templates/routing-card.example.json' and 'schemas/routing-card.schema.json' are referenced as the complete passing card and validation target but are not in the bundle, so the checklist's final step cannot actually be run.

Add an error-recovery loop to the checklist after the validation step (e.g., 'if validation fails, fix the flagged fields and re-validate before publishing') to satisfy the feedback-loop expectation for batch/gated artifacts.

Trim repeated gate warnings (e.g., consolidate the 'never an identity/callability gate' phrasing used for both workforce.languages and workforce.modalities) to recover a few tokens without losing the rule.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — field tables carry the payload with no padding about JSON or schemas Claude already knows. A few warning phrasings repeat ('never an identity/callability gate', 'It is not an allowlist') and could be trimmed, placing it at the 4 anchor rather than the every-token-earns-its-place 5.

4 / 5

Actionability

Per-field guidance is precise and executable: 'Exactly "routing-card/2.0"', '4–8 ids in verb_object snake_case', '6+ real sentences... 3 Korean and 3 English', plus a builder-runnable checklist ending in schema validation. The gap keeping it below 5 is that the complete worked example it defers to ('templates/routing-card.example.json') is not present in the bundle.

4 / 5

Workflow Clarity

The 'Checklist a builder can run' gives a clear 8-step sequence with an explicit validation checkpoint ('Validate: the card parses against schemas/routing-card.schema.json'), matching the 4 anchor. It falls short of 5 because there is no error-recovery loop — no instruction for what to do when validation fails.

4 / 5

Progressive Disclosure

A single, well-sectioned file with references that are one level deep and clearly named inline (schema, contracts, ontology, example template). The minor gap is that none of the referenced paths exist in this bundle — no references/, scripts/, or assets/ — so a reader cannot actually navigate to them, which keeps it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

92%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: it explicitly states what the skill does and when to use it, names the concrete artifact and its consumers, and even advertises the key defect class (sentences leaking into id fields). Minor room remains in adding user-natural synonyms beyond the internal builder jargon.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions: 'emits or repairs .agentlas/routing-card.json', 'States what belongs in every field', identifies 'which fields the hub can actually match on' and 'which fields silently break matching when a sentence leaks into them'. Coverage is comprehensive for a field-spec skill, matching the 5 anchor rather than 4, where minor gaps would remain.

5 / 5

Completeness

Both halves are explicit: 'Use whenever a build emits or repairs .agentlas/routing-card.json' answers when, and 'States what belongs in every field...' answers what, with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Good natural keyword coverage including the exact artifact path '.agentlas/routing-card.json' plus verbs like 'emits', 'repairs', and 'hub' matching. A few natural phrasings users might say are missing and it leans on internal jargon ('single-agent builder, the team builder, and the packager'), so it fits the 4 anchor rather than comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a single specific artifact and contract ('.agentlas/routing-card.json', 'the shared card contract') with named consumers, giving it a clear niche with minimal risk of triggering for the wrong skill.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agentlas-ai/Agentlas-OS

Path

codex/plugins/agentlas-core-engine-meta-agent/skills/routing-card-authoring/SKILL.md

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.