Creates detailed TDD-first implementation plans from design documents. Every task follows red-green-refactor. Searches EC for relevant patterns. Use after brainstorming to write an implementation plan.
Creates detailed TDD-first implementation plans from design documents for engineers with zero context.
npx claudepluginhub merewhiplash/engram-cogitatorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Create implementation plans that an engineer with zero context can follow.
Announce: "I'm using the writing-plans skill to create the implementation plan."
docs/designs/YYYY-MM-DD-<topic>.mdGet project config and relevant patterns:
ec_search:
query: project config
type: config
ec_search:
query: [feature area] pattern
type: pattern
ec_search:
query: [feature area] implementation
type: learning
Note the configured test_command for TDD steps.
Plans go in docs/plans/YYYY-MM-DD-<topic>.md and cross-reference the design.
# [Feature Name] Implementation Plan
**Design:** [docs/designs/YYYY-MM-DD-<topic>.md](../designs/YYYY-MM-DD-<topic>.md)
**Goal:** [One sentence]
**Architecture:** [2-3 sentences about approach]
**EC Context:** [List any relevant memories consulted]
---
Each task is bite-sized (2-5 minutes) and follows @tdd:
### Task N: [Component Name] @tdd
**Files:**
- Create: `exact/path/to/file.ts`
- Modify: `exact/path/to/existing.ts`
- Test: `tests/path/to/test.ts`
**Step 1: Write failing test** (RED)
\`\`\`typescript
test('specific behavior', () => {
// exact test code
});
\`\`\`
**Step 2: Run test, verify it fails**
\`\`\`bash
{test_command} path/to/test
\`\`\`
Expected: FAIL - "function not defined"
**Step 3: Implement minimal code** (GREEN)
\`\`\`typescript
// exact implementation code
\`\`\`
**Step 4: Run test, verify it passes** @verifying
\`\`\`bash
{test_command} path/to/test
\`\`\`
Expected: PASS
**Step 5: Commit**
\`\`\`bash
git add . && git commit -m "feat: add specific feature"
\`\`\`
Reference patterns found during search:
**EC Context:**
- Pattern: [area] - [brief description of relevant pattern]
- Learning: [area] - [gotcha to be aware of]
If the plan establishes a new pattern, note it for storage after implementation:
**Patterns to Store:**
- [Description of new pattern established]
After saving the plan:
"Plan saved to
docs/plans/YYYY-MM-DD-<topic>.md. Ready to execute?"
If yes → Use @executing-plans
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.