Plan the change as OpenSpec artifacts: proposal, delta specs, design, tasks
Scanned 8/31/2026
Install to Claude Code
npx -y skills add clomia/claude-automata --skill plan --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Plan?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/clomia-plan)More formats (shields.io, HTML) on the badges page.
---
name: plan
description: "Plan the change as OpenSpec artifacts: proposal, delta specs, design, tasks"
argument-hint: "[change intent]"
effort: max
---
squash merge erases branch history. Only the archive of these artifacts preserves the
change's intent and design.
# 절차
1. Pick a change-id. Usually the tx branch's slug:
```bash
"${CLAUDE_PLUGIN_ROOT}/bin/tx-hook" openspec new change <change-id>
```
2. Write the artifacts in dependency order. Each artifact's instructions come from the
engine; the engine owns the format:
```bash
"${CLAUDE_PLUGIN_ROOT}/bin/tx-hook" openspec instructions <artifact> --change <change-id> --json
```
Tasks hold only work that is done before close. Post-merge actions are follow-up
changes, not tasks.
3. Validate:
```bash
"${CLAUDE_PLUGIN_ROOT}/bin/tx-hook" openspec validate <change-id> --strict --no-interactive --json
```
A delta-less change declares `skip_specs: true` in its `.openspec.yaml`; validate
then accepts zero deltas. Fix everything until green.
4. Continue straight into `tx:apply`. plan is not a stopping point.
# Unknown 처리
Every unknown met while planning resolves one of three ways:
- **measurable**: measure it and record the result.
- **reversible**: adopt an assumption and state it in design.
- **neither**: halt the change and record why in the proposal.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.