doing-a-simple-two-sta…
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic…
Use when beginning implementation from a design plan - orchestrates branch creation, detailed planning, and hands off to execution with all necessary context
$ npx -y skills add ed3dai/ed3d-plugins --skill starting-an-implementation-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/starting-an-implementation-planContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when beginning implementation from a design plan - orchestrates branch creation, detailed planning, and hands off to execution with all necessary context
name: starting-an-implementation-plan description: Use when beginning implementation from a design plan - orchestrates branch creation, detailed planning, and hands off to execution with all necessary context user-invocable: false
Orchestrate the transition from design document to executable implementation through planning and execution handoff.
**Core principle:** Branch -> Plan -> Execute. Isolate work, create detailed tasks, hand off to execution.
**Announce at start:** "I'm using the starting-an-implementation-plan skill to create the implementation plan from your design."
**DO NOT GUESS.** If the user has not provided a path to a design plan, you MUST ask for it.
Use AskUserQuestion:
Question: "Which design plan should I create an implementation plan for?" Options: - [list any design plans you find in docs/design-plans/] - "Let me provide the path"
If `docs/design-plans/` doesn't exist or is empty, ask the user to provide the path directly.
**Never assume, infer, or guess which design plan to use.** The user must explicitly tell you.
This skill has three steps:
1. **Branch Setup:** Select and create branch for implementation 2. **Planning:** Create detailed implementation plan 3. **Execution Handoff:** Direct user to execute the plan
**Step 0: Create orchestration task tracker**
Use TaskCreate to track the orchestration steps:
TaskCreate: "Branch setup" (conditional) TaskCreate: "Read project implementation guidance from [absolute path]" → TaskUpdate: addBlockedBy: [Branch setup] → (only if .ed3d/implementation-plan-guidance.md exists) TaskCreate: "Create implementation plan" → TaskUpdate: addBlockedBy: [Branch setup] (or [Read guidance] if it exists) TaskCreate: "Re-read starting-an-implementation-plan skill (restore context)" → (DO NOT set blockedBy yet - will be updated after granular tasks are created) TaskCreate: "Execution handoff" → TaskUpdate: addBlockedBy: [Re-read skill]
**CRITICAL: The "Re-read skill" task must be re-pointed AFTER writing-implementation-plans creates the Finalization task.** See "After Planning: Update Dependencies" below.
The "Create implementation plan" task wraps the granular tasks created by writing-implementation-plans. The "Re-read skill" step ensures context is restored after potential compaction before handoff.
Mark "Branch setup" task as in_progress.
Before planning, set up the branch and workspace for implementation work.
Extract the **slug** from the design plan filename (everything after `YYYY-MM-DD-`, excluding `.md`). For example, `oauth2-svc-authn` from `2025-01-18-oauth2-svc-authn.md`.
This slug is used for: 1. Implementation plan directory name (`docs/implementation-plans/YYYY-MM-DD-{slug}/`) 2. Worktree directory name (`.worktrees/{slug}`) 3. **Scoping all AC identifiers** — every acceptance criterion uses the format `{slug}.AC{N}.{M}`
The slug ensures AC identifiers are globally unique across multiple plan-and-execute rounds.
**Step 1: Ask about worktree**
**REQUIRED: Use AskUserQuestion tool**
Ask:
Question: "Do you want to use a git worktree for this implementation?" Options: - "Yes - create worktree" (isolated workspace in .worktrees/[friendly-name]) - "No - work in current directory" (standard branch workflow)
**Step 2: Set up workspace based on choice**
**If user chooses "Yes - create worktree":**
1. **REQUIRED SUB-SKILL:** Use ed3d-plan-and-execute:using-git-worktrees 2. **CONDITIONAL SKILLS:** Activate any project-specific git worktree skills if they exist 3. Announce: "I'm using the using-git-worktrees skill to create an isolated workspace." 4. Ask user which branch to use for the worktree:
Question: "Which branch should I use for this worktree?"
Options:
- "[friendly-name]" (e.g., oauth2-svc-authn)
- "$(whoami)/[friendly-name]" (e.g., ed/oauth2-svc-authn)5. Create worktree:
6. Change to worktree directory 7. Announce: "Worktree created at `.worktrees/[friendly-name]` on branch `[branch-name]`"
**If user chooses "No - work in current directory":**
1. Ask user which branch to use:
Question: "Which branch should I use for this implementation?"
Options:
- "Use current branch" (stay on current branch, no branch creation)
- "[friendly-name]" (e.g., oauth2-svc-authn)
- "$(whoami)/[friendly-name]" (e.g., ed/oauth2-svc-authn)2. **If "Use current branch":** Continue with current branch (no git commands) 3. **If branch name provided:**
4. **If branch creation fails:** Report error to user and ask if they want to use current branch instead
Mark "Branch setup" task as completed. **THEN proceed to Planning.**
After branch setup, check for project-specific implementation guidance.
**Check if `.ed3d/implementation-plan-guidance.md` exists:**
Use the Read tool to check if `.ed3d/implementation-plan-guidance.md` exists in the session's working directory.
**If the file exists:**
1. Use TaskCreate to add: "Read project implementation guidance from [absolute path to .ed3d/implementation-plan-guidance.md]"
2. Mark the task in_progress 3. Read the file and incorporate the guidance into your understanding 4. Mark the task completed 5. Proceed to Planning
Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.
Repo: ed3dai/ed3d-plugins
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic…
Use when creating a new Claude Code plugin or setting up plugin structure - provides complete file organization, manifest format, and component definitions for…
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt…
Use when creating, releasing, or maintaining a Claude Code Plugin Marketplace - covers marketplace.json schema, version management, release checklists,…
Use when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale - analyzes what changed,…