القائمة
Use when you have a spec or requirements for a multi-step task, before touching code
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Analyzes weight file diffs after benchmarks to flag significant regressions in ref_time, proof_size, and DB reads. Use when updating weights, running benchmarks, or reviewing weight changes.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when executing implementation plans with independent tasks in the current session
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: Discover the project's documentation structure before writing. See the Plan Location Discovery section below.
See plan-location-discovery for the full discovery process.
IMPORTANT: You MUST announce your chosen path and wait for the user to confirm before writing any files. Do NOT write the plan before the user confirms the location.
If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
When work is broken into sequential phases (e.g., "Phase 1: foundation, Phase 2: resilience, Phase 3: features"), write all phase plans before executing any of them. This ensures:
Each phase gets its own plan file. List them in order with cross-references (e.g., "Depends on: Phase 1 plan at <path>").
Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.
This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For Claude:** REQUIRED: Use core-engineering:subagent-driven-development (if subagents available) or core-engineering:executing-plans to implement this plan. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`
- [ ] **Step 1: Write the failing test**
```python
def test_specific_behavior():
result = function(input)
assert result == expected
```
- [ ] **Step 2: Run test to verify it fails**
Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"
- [ ] **Step 3: Write minimal implementation**
```python
def function(input):
return expected
```
- [ ] **Step 4: Run test to verify it passes**
Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS
- [ ] **Step 5: Commit**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
After completing each chunk of the plan:
plan-document-reviewer-prompt.md) with precisely crafted review context — never your session history. This keeps the reviewer focused on the plan, not your thought process.
Chunk boundaries: Use ## Chunk N: <name> headings to delimit chunks. Each chunk should be ≤1000 lines and logically self-contained.
Review loop guidance:
After saving the plan:
"Plan complete and saved to <discovered-path>/<filename>. Ready to execute?"
Execution path depends on harness capabilities:
If harness has subagents (Claude Code, Codex, etc.):
If harness does NOT have subagents: