Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

code-check

Étoiles1

Forks2

Mis à jour3 juillet 2026 à 13:49

Code Check skill owned by Bea (Ai Engineer). Runs on: on file change/create. Scaffold generated from the Mindshare skills registry; install into ~/.claude/skills/code-check/ to use.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

AesopScott

AesopScott/central

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en assurance qualité des logiciels et testeursProfessions informatiques et mathématiques·SOC 15-1253

SKILL.md

readonly

Plus depuis ce dépôt

même dépôt

role

AesopScott/central

Build role agents for a root organization or multi-agent corporation. Use when the user wants to create an organizational role such as CEO, CFO, advisor, operator, manager, support lead, data steward, research lead, or functional department voice, and needs to decide role mode, engagement type, authority, implementation form, learning behavior, and whether the role should be advisory, workflow-owned, skill-backed, loop-backed, autonomous, human-in-the-loop, or only a lightweight prompt/persona.

2026-07-121

token-harness

AesopScott/central

Observe CLI model calls, prompt/input payloads, stdout/stderr, provider-reported usage metadata, and local token estimates across Codex, Claude, DeepSeek, OpenAI, Anthropic, or other AI CLIs. Use when a user needs truthful token visibility, prompt-origin accounting, usage audits, or a harness around model CLI input/output; labels exact provider usage separately from local estimates and blocks claims that cannot be proven.

Create an agent brief for the MAPS Define phase from an existing role. Use when turning an approved role artifact into an agent brief with goals, users, authorization, scope, non-goals, success criteria, failure criteria, escalation points, risks, and assumptions.

2026-07-031

accounting

AesopScott/central

Accounting skill owned by Finn (Finance Director). Runs on: scheduled + emails link. Scaffold generated from the Mindshare skills registry; install into ~/.claude/skills/accounting/ to use.

2026-07-031

adrian-legal-gate

AesopScott/central

Adrian Legal Gate skill owned by Adrian (Legal Director). Runs on: external commitment / contract. Scaffold generated from the Mindshare skills registry; install into ~/.claude/skills/adrian-legal-gate/ to use.

2026-07-031

name	code-check
description	Code Check skill owned by Bea (Ai Engineer). Runs on: on file change/create. Scaffold generated from the Mindshare skills registry; install into ~/.claude/skills/code-check/ to use.

Code Check

Owned by Bea (Ai Engineer). Generated scaffold from the Mindshare skills registry (roles/skills-registry.json). This file is a real, installable Claude skill: drop the code-check/ folder into ~/.claude/skills/ and invoke it with /code-check. The structure below is honest scaffold depth — the owning role deepens the body with its real procedure.

Purpose

Provide the code check capability for Bea (Ai Engineer). Use this skill when the owning role needs a repeatable, registered procedure rather than an ad-hoc prompt.

When To Use

Trigger: on file change/create
Invoke with /code-check or when the user describes the task this skill names.

Inputs & Outputs

Reads/writes: not yet declared in the registry. Treat as read-only until the owner specifies inputs and outputs.

Authority & Gates

Registry status: owner-gated
Secrets gate — depends on credentials in .env.local; Scott (final authority) must provision and approve.

Tool ability is not authority. This scaffold defaults to report-only. Any step that commits, sends, spends, or changes control-plane state stays blocked until the gate owner approves.

Procedure

Confirm the trigger condition and that the owning role authorizes this run.
Read the declared inputs above. Do not reach outside them without owner approval.
Perform the code check work the owning role defines here.
Produce a clear, reviewable report. Lead with the finding, then evidence, then recommended next action.
Stop at every registered gate. Hand the gated step to its owner with the cleanest safe path forward.

Output

A reviewable report or artifact for Bea (Ai Engineer). No silent state changes. Every gated action is surfaced for approval, not auto-applied.

Boundary

This file grants no authority by itself. Activation, autonomy, git/release, secrets, external comms, and spending all remain gated to their registered owners until explicitly approved.

Registry Notes

Uses deepseek API — needs key. Results to code-review drawer.