Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

adg-risk-classifier

Étoiles4

Forks0

Mis à jour10 juin 2026 à 06:08

Use before implementation or review work to choose the cheapest safe Proofline lane and avoid unnecessary governance gates.

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

zreed3

zreed3/agentic-development-platform

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	adg-risk-classifier
description	Use before implementation or review work to choose the cheapest safe Proofline lane and avoid unnecessary governance gates.

ADG Risk Classifier

Use this before material work when the lane is not obvious.

Workflow

Run:

npm run work:classify -- --intent "<task summary>" --file <path>

Use the returned lane:
- L0 spike: read-only exploration only.
- L1 quick-fix: small UI, docs, copy, or low-risk bug fix.
- L2 bounded slice: normal implementation.
- L3 sensitive: auth, RBAC, data scope, schema, policy, audit, or production risk.
- L4 release signoff: verified, release-ready, RC, GA, or signoff claim.
Upgrade immediately if sensitive scope appears.

Output

Keep caveman output short:

lane L1 quick-fix
files <paths>
checks <targeted checks>
full gate no

Never downgrade sensitive or signoff work without a recorded decision.

Plus depuis ce dépôt

même dépôt

adg-backlog-decompose

zreed3/agentic-development-platform

Decompose a feature or intent into small, context-bound backlog items in the SQL backlog, for a planning model (Opus or Sonnet). Use before a swarm of workers: turn one feature into tightly scoped, logged items, each with a write scope and a context profile, so cheaper sub-agents can each work one item in isolation and total token use drops.

2026-06-154

adg-backlog-swarm

zreed3/agentic-development-platform

Orchestrate a context-bound, backlog-logged multi-agent swarm to cut token use. Use to run a feature as a planner (Opus or Sonnet) that logs small backlog items, then cheaper workers (Sonnet or Haiku) that each implement one item under its bounded context packet, while the parent keeps integration, the SQL backlog, the audit log, and verification.

2026-06-154

adg-evidence-curator

zreed3/agentic-development-platform

Select, record, and validate ADG evidence. Use when choosing targeted checks, recording failed commands, linking tests to requirements, writing audit events, registering advisory gaps, or preparing feature/release evidence.

2026-06-154

adg-feature-elicitation

zreed3/agentic-development-platform

Elicit generic ADG feature intent into a normalized requirements graph. Use when naming a feature, defining how it fits the platform, deriving RBAC-aligned stories and use cases, or creating success, anti-success, scenario, and gap evidence in config/agentic/elicitation.json.

2026-06-154

adg-item-worker

zreed3/agentic-development-platform

Work a single backlog item under a bounded context packet, for a context-cheap sub-agent (Sonnet or Haiku). Use when an orchestrator hands you one item id to implement in isolation: claim it, load only its context:item packet, edit only its write scope, record evidence, and complete it. Keeps token use low and work traceable.

2026-06-154

adg-quick-ui-fix

zreed3/agentic-development-platform

Use for small UI, copy, docs, styling, or visual polish fixes that should avoid full governance unless risk increases.

2026-06-154

Exécutez n'importe quel Skill en un clic