CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-factory-router

Analyzes Codex skill-management requests, selects the workflow lane, and returns selected_lane, mode, next_step, and blockers. Use when the user says create a skill, add/update/fix/review a skill, install/sync/list skills, choose a workflow, or merge/retire a skill.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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-structured, actionable routing skill with clear sequencing, explicit validation/failure handling, and excellent progressive disclosure. Its main weakness is repetition of the read-only boundary discipline across several sections, which inflates token cost without adding information.

Suggestions

Consolidate the repeated read-only boundary guidance (When To Use, Execution Boundaries, Gotchas, Anti-Patterns, Validation) into a single authoritative section to remove ~4-5 restatements of 'downstream lanes own edits/evals/install/publish'.

Fill or constrain the placeholder output fields (rationale, next_step) with a short example handoff so the YAML template is copy-paste ready.

Tighten step 8's abstract 'decide whether the durable answer is a skill, docs, script, hook, validator, rule, or direct answer' into a concrete decision rule or pointer to the first-principles gate reference.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the read-only boundary guidance ('downstream lanes own edits/evals/install/publish'; 'do not fork system lanes'; 'do not collapse evidence surfaces') is restated across When To Use, Execution Boundaries, Gotchas, Anti-Patterns, and Validation sections, so it could be meaningfully tightened.

3 / 5

Actionability

Provides a concrete routing table mapping request types to named lanes and modes, an enumerated YAML output schema, and specific validation commands, but placeholder fields (rationale, next_step) and the abstract step 8 ('decide whether the durable answer is a skill, docs, script...') leave minor gaps.

4 / 5

Workflow Clarity

Steps 1-9 are clearly sequenced with explicit stop conditions ('Return the handoff and stop'), a dedicated Failure Mode section, and validation gates ('Stop at the first failed required gate'); the destructive/batch cap does not apply since the router is explicitly read-only.

5 / 5

Progressive Disclosure

The body is an overview pointing to five well-signaled, one-level-deep references, each prefaced with a 'Read when...' condition; all referenced files exist in ./references/ and content is appropriately split for easy navigation.

5 / 5

Total

17

/

20

Passed

Description

100%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, third-person description that concretely states both capabilities and a comprehensive set of natural trigger phrases. It clearly answers what the skill does and when to invoke it with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Analyzes... requests, selects the workflow lane, and returns selected_lane, mode, next_step, and blockers') with named output fields, giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (analyzes requests, selects lane, returns named fields) and 'when' (a concrete 'Use when...' clause with specific trigger phrases).

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say: 'create a skill, add/update/fix/review a skill, install/sync/list skills, choose a workflow, or merge/retire a skill', covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche — Codex skill-management routing and workflow-lane selection — with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.