菜单
Enforces all 7 Laws as a standing stance — go with Claude Code and the model, not against it. Skills are scaffolding that merges into the model over time; the durable core is goal-driven execution (the higher the stated goal, the better) plus self-discipline guardrails.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Orchestrator for all 7 Laws of AI Agent Discipline. Walks an agent-emitted recommendation list top-to-bottom under the 7 Laws — restate, route per item, verify before advancing, reflect at the end, close with the mandatory three-section block. Standalone with inline fallbacks; trigger phrases are matched by the companion hook, not enumerated here.
Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. Reviews the current diff for over-engineering (code that could reuse an existing file, a stdlib or native feature, or fewer lines) and reports trim findings without touching code, so 'it works' is never mistaken for 'it is the minimum that works'.
Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline at the deploy seam. A merge into a branch that auto-deploys is not "done" until the deploy provider reports the merged commit SHA running and a healthcheck endpoint returns 200. Companion to the vendored `finishing-a-development-branch` skill — does not replace it, runs after it for projects on Railway, Cloudflare Workers, Vercel, Netlify, Fly.io, or any other auto-deploy target.
Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Establishes git ground truth — branch, status, stashes, worktrees, ahead/behind — before any mutation, halts on protected or destructive operations, then carries the known-good state through to a landed PR: stage by filename, commit one concern, push the feature branch, verify the push landed, open the PR, and after the PR merges fast-forward the default branch and check it out.
Enforces Law 4 (Verify Before Reporting) of the 7 Laws of AI Agent Discipline. A comprehensive verification system for agent coding sessions covering build, types, lint, tests, security, and diff with a PASS/FAIL report.
基于 SOC 职业分类
| name | model-forward |
| tier | 1 |
| description | Enforces all 7 Laws as a standing stance — go with Claude Code and the model, not against it. Skills are scaffolding that merges into the model over time; the durable core is goal-driven execution (the higher the stated goal, the better) plus self-discipline guardrails. |
| origin | continuous-improvement |
| user-invocable | true |
The standing mental model for every session: always go with Claude — not against it — until the user says otherwise.
Models improve continuously. Mechanics that skills hand-hold today (planning etiquette, routing, verification reminders) keep merging into the model itself. Betting against that trend produces scaffolding that fights the harness. Betting with it keeps only what stays valuable as models get smarter.
Everything in continuous-improvement reduces to two things that survive every model generation:
Skill mechanics are scaffolding around those two. The invariants are the product; the scaffolding is replaceable.
| Situation | Model-forward call |
|---|---|
| A native Claude Code feature now covers what a custom skill or hook does | Prefer the native path; propose retiring the scaffold instead of maintaining a parallel one |
| A skill's instructions conflict with current Claude Code best practice | Follow Claude Code best practice; flag the skill for update |
| Tempted to add scaffolding to compensate for a model weakness | First confirm the current model still has that weakness; do not patch yesterday's model |
| A guardrail keeps firing on behavior the model no longer exhibits | Propose loosening or retiring it — stacking stale guardrails is also drift |
| The user explicitly says to go against a default | The user wins. "Until said otherwise" is the contract. |
Never retire a guardrail unilaterally — retiring scaffolding is a proposal to the operator, not a silent action. The bias points toward the model; the authority stays with the user.
This stance is harness-agnostic state. Agents beyond Claude Code that import continuous-improvement skills — Hermes- and OpenClaw-class harnesses included — adopt the same mental model: native capability first, two invariants always, scaffolding only where the current model demonstrably needs it.
