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.

75

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured routing skill: actionable handoff schema and validation commands, a clear sequenced workflow with a stop-at-gate checkpoint, and clean one-level reference navigation. Its only weakness is redundancy — the read-only execution boundary is repeated across four sections.

Suggestions

Collapse the repeated execution-boundary statement into a single canonical "Execution Boundaries" section and have Outputs, Gotchas, and Validation reference it instead of restating it.

Trim domain jargon stacks (e.g. "plugin-cache visibility, command-surface rows, flat skill symlinks, runtime picker visibility") where a shorter phrasing carries the same routing signal.

Consider moving the two validation commands into a short "Verification" subsection so they read as a runnable checklist rather than prose at the end of Validation.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes domain competence, but the execution-boundary statement ("Downstream lanes own source edits, runtime sync, external review, Tessl evals, packaging, publishing...") is restated nearly verbatim across Outputs, Gotchas, Execution Boundaries, and Validation, which is redundant padding rather than a score-3 lean overview.

2 / 3

Actionability

Provides a literal YAML handoff schema with enumerated lane names and mode values, a concrete request→lane routing table, and copy-paste-ready validation commands (validate_skill_authoring_family.sh and ./bin/ask skills external-review).

3 / 3

Workflow Clarity

A numbered 9-step routing sequence is given, with an explicit validation checkpoint ("Stop at the first failed required gate, classify it, and do not sync, commit, publish, or install until it is fixed or explicitly blocked") and a dedicated Failure Mode section for error handling.

3 / 3

Progressive Disclosure

The body is an overview that defers detail to five one-level-deep references, each prefaced by a "Read when..." trigger, and all five referenced files (contract.yaml, evals.yaml, task-profile.json, discovery-interview.md, routing-policy.md) are present in ./references/.

3 / 3

Total

11

/

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.

A strong description: concrete actions, natural trigger terms, an explicit Use-when clause, and a distinctive niche, all in third-person voice. It cleanly satisfies the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Analyzes Codex skill-management requests, selects the workflow lane, and returns selected_lane, mode, next_step, and blockers" — naming specific output fields rather than vague capability language.

3 / 3

Completeness

Explicitly answers both what (analyzes/selects/returns) and when via an explicit "Use when the user says..." trigger clause, satisfying the highest completeness anchor.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would actually say — "create a skill", "add/update/fix/review a skill", "install/sync/list skills", "choose a workflow", "merge/retire a skill" — across the full skill lifecycle.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche (Codex skill-management routing) with distinct lifecycle triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.