Menu
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
A presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then runs a capped 3-round presentation checkup (演讲体检) on the rendered deck. It never renders slides itself. Use before generating PPT/HTML slides from raw material, and after rendering when the user says things like "给这份 deck 做演讲体检" or "PPT 渲染质检". If all you want is one beautiful template page with no outline and no checkup, a rendering skill alone is enough.
A first-30-days onboarding module for new hospitality hires — the behaviors, the practice, the checks, and the manager follow-up. Built as a decision-grade professional training deck for new hires, managers.
Open Design's feature business case for the plugin marketplace: the user pain, options, tradeoffs, and the measure of success. Built as a decision-grade product management deck for PM, eng, design, leadership.
Open Design + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
Open Design's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.
Open Design's enterprise AI-adoption brief: local-first agents at work, the risk controls, the ROI, and the rollout plan. Built as a decision-grade AI literacy deck for leadership, IT, security.
| name | patch-edit |
| description | Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices. |
| od | {"scenario":"code-migration","mode":"edit"} |
Spec §20.3 / §21.3.2: code-migration / tune-collab cannot ship a trustworthy diff when the agent rewrites whole files in one pass — the reviewer can't audit the change. This atom enforces "one step per turn, smallest possible localised edit".
plan/steps.json from rewrite-plan.iterations (the daemon's per-stage counter).code/index.json for the file's known imports + neighbours.The atom mutates files inside the project cwd via the file-edit tool.
After every iteration, it writes a per-step receipt:
project-cwd/
└── plan/
├── steps.json (status updated: 'pending' → 'completed' | 'skipped')
└── receipts/
└── step-<id>.json # { files: ['...'], diffSummary, rationale, completedAt }
The atom completes when every step in plan/steps.json is in a
terminal state (completed / skipped) OR iterations >= OD_MAX_DEVLOOP_ITERATIONS. Use:
{
"id": "patch-edit-loop",
"atoms": ["patch-edit"],
"repeat": true,
"until": "plan.steps.terminal === plan.steps.total || iterations >= 8"
}
files[].shell-tier file when the step's risk is not
'high' or the user hasn't confirmed.Implemented by the daemon runner in
apps/daemon/src/plugins/atoms/patch-edit.ts. It validates step ownership and
risk, applies unified diffs with atomic writes, and records receipts and
progress.