Skill authoring and audit

Skill hoatv2211/GameStudio-CodexKIT/skills/skill-authoring-and-audit

Use when creating or revising a GameStudio-CodexKIT skill, resolving ambiguous skill triggers, auditing provenance or lifecycle maturity, or deriving reusable capabilities from session history.From its SKILL.md

Install

npx -y skills add hoatv2211/GameStudio-CodexKIT --skill skill-authoring-and-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.5 KB, as published. Nobody here has run it

Skill Authoring and Audit

Overview

One governance skill supports two modes: author creates or updates a needed workflow; audit detects gaps, collisions, stale maturity, and unsupported claims. Update-first is mandatory.

When to use

Use when a recurring workflow needs codification, a skill trigger is ambiguous, session history reveals repeated failures, or catalog lifecycle and provenance need review.

When NOT to use

Do not use this skill merely to execute or report an existing evaluation, and do not author a skill for a one-off task, duplicate an existing capability, copy noncommercial content, or promote maturity without eval and dogfood evidence.

Required inputs and context discovery

Collect requested mode, catalog and registries, existing descriptions, project-local skills and agent roles, routing cases, session or issue evidence, provenance source/license/SHA, owner, reviewer, risk, and target pack.

Safety and risk level

Writes are limited to owned skill, eval, registry, and documentation paths. Never mutate .research sources, external projects, generated adapters, or copied NC content.

Workflow

Scan the catalog for exact, neighboring, deprecated, or updateable capabilities. Completion criterion: the decision is update, new skill, backlog, or no action.
In author mode, create failing routing, behavior, or pressure cases from observed needs before editing the skill. Completion criterion: the gap is reproducible and not a hypothetical preference.
Write the smallest complete skill with closed schema, provenance, safety, evidence, workflow criteria, and concise triggers. Completion criterion: structural validation passes for the skill.
Run deterministic routing, behavior, pressure, originality, and safety checks. Completion criterion: failures are repaired without weakening cases.
In audit mode, scan catalog, project overlays, agent-role IDs, and session history for stale skills, repeated manual workflows, trigger or role collisions, missing owners, and observed-versus-target KPI gaps. Completion criterion: findings have evidence, owner, severity, and update-first recommendation.
Apply lifecycle promotion or demotion only when prerequisites are observed. Completion criterion: registry maturity matches evidence rather than aspiration.

Evidence and output contract

Produce skill-audit.json with mode, findings, overlap, routing/behavior/pressure results, provenance, lifecycle recommendation, observed metrics, target metrics, and changed paths.

Handoff contract

Record requested mode, preflight decision, skill/eval files, provenance source, commands, failures, lifecycle status, and next audit or dogfood action.

Pitfalls and anti-rationalization

“A new skill would be cleaner” does not beat updating an existing one.
High overlap with undeclared provenance is a Gate 10 failure.
Target metrics are never observed metrics.
Missing live dogfood is BLOCKED, not a maturity PASS.

Verification checklist

Update-first preflight was performed.
New behavior had a failing case first.
Provenance and license are complete.
Routing, behavior, pressure, and safety gates ran.
Lifecycle uses observed evidence.

References and scripts

When maintaining this kit from a full repository clone, use scripts/validate.py, scripts/route_eval.py, scripts/check_originality.py, scripts/catalog_audit.py, and the eval directories. Standalone skill installs do not include repository governance tooling.