agentleFS
renathoazrenathoaz/arsyn/skills/planning/SKILL.md

planning

Skill2 starsChanged 8 months agoMITView on GitHub

Decompose specs into executable task sequences.

69 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use Problem-Solving Techniques, web-frameworks and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 5 projects that use this

  • mrgoonieSkill

    web-frameworks

    Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons in outlined/filled styles). Use when creating React applications, implementing server-side rendering, setting up monorepos with multiple packages, optimizing build performance and caching strategies, adding icon libraries, managing shared dependencies, or working with TypeScript full-stack projects.

    Also in 5 projects that use this

  • mrgoonieSkill

    mcp-management

    Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

    Also in 5 projects that use this

  • truongtv22Skill

    mobile-development

    Build modern mobile applications with React Native, Flutter, Swift/SwiftUI, and Kotlin/Jetpack Compose. Covers mobile-first design principles, performance optimization (battery, memory, network), offline-first architecture, platform-specific guidelines (iOS HIG, Material Design), testing strategies, security best practices, accessibility, app store deployment, and mobile development mindset. Use when building mobile apps, implementing mobile UX patterns, optimizing for mobile constraints, or making native vs cross-platform decisions.

    Also in 4 projects that use this

  • +6 more from mrgoonie

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 62 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the spec covers multiple independent subsystems, it should have been split during ideation.

    line 16
  2. Distinctive:

    Before defining tasks, enumerate every file that will be created or modified and its responsibility.

    line 20
  3. Distinctive:

    Follow existing codebase patterns.

    line 24
  4. Distinctive:

    Every plan starts with:

    line 40
  5. Distinctive:

    If loop exceeds 3 iterations, surface to user.

    line 103
  6. Distinctive:

    After saving and committing the plan:

    line 109

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Planning

Transform an approved spec into a step-by-step implementation plan that an engineer with zero project context can follow.

Announce at start: "Generating implementation plan using arsyn:planning."

Save to: docs/arsyn/plans/YYYY-MM-DD-<feature-name>.md (user preference overrides)

Scope Gate

If the spec covers multiple independent subsystems, it should have been split during ideation. If it was not, recommend separate plans — one per subsystem. Each plan must produce working, testable software on its own.

File Map

Before defining tasks, enumerate every file that will be created or modified and its responsibility. This locks in decomposition decisions.

  • One clear responsibility per file. Prefer focused files over large ones.
  • Files that change together live together. Split by responsibility, not by layer.
  • Follow existing codebase patterns. If a file you are modifying has grown unwieldy, include a split in the plan.

Task Granularity

Each step is a single action (2-5 minutes):

StepExample
Write failing testtest_user_creates_account
Run test, confirm failurepytest ... -v -> FAIL
Implement minimal codefunction body
Run test, confirm passpytest ... -v -> PASS
Commitgit commit -m "feat: ..."

Plan Header

Every plan starts with:

# [Feature] Implementation Plan

> **For agents:** Use arsyn:orchestrating (preferred) or arsyn:executing to run this plan. Steps use `- [ ]` checkboxes.

**Goal:** [One sentence]

**Architecture:** [2-3 sentences]

**Tech Stack:** [Key technologies]

---

Task Format

### Task N: [Name] `[CONFIDENCE: HIGH|MEDIUM|LOW]`

**Files:**
- Create: `src/exact/path.py`
- Modify: `src/existing/file.py:40-55`
- Test: `tests/exact/test_path.py`

- [ ] **N.1 Write failing test**

```python
def test_behavior():
    assert function(input) == expected
```

- [ ] **N.2 Confirm failure**

Run: `pytest tests/path/test.py::test_behavior -v`
Expect: FAIL — `NameError: function not defined`

- [ ] **N.3 Implement**

```python
def function(input):
    return expected
```

- [ ] **N.4 Confirm pass**

Run: `pytest tests/path/test.py::test_behavior -v`
Expect: PASS

- [ ] **N.5 Commit**

```bash
git add src/exact/path.py tests/exact/test_path.py
git commit -m "feat: add behavior"
```

Review Loop

  1. Dispatch plan-document-reviewer subagent (see references/plan-document-reviewer-prompt.md) with crafted context — never raw session history. Provide plan path and spec path.
  2. Issues found: fix and re-dispatch.
  3. Approved: proceed to handoff.
  4. If loop exceeds 3 iterations, surface to user.

Reviewers are advisory. Explain disagreements if you believe feedback is wrong.

Execution Handoff

After saving and committing the plan:

"Plan saved to docs/arsyn/plans/<filename>.md. Two execution modes:

1. Orchestrated (recommended) — Fresh subagent per task with review between tasks.

2. Inline — Execute tasks sequentially in this session with checkpoint reviews.

Which approach?"

  • Orchestrated: invoke arsyn:orchestrating
  • Inline: invoke arsyn:executing

Gotchas

  • Vague steps — "Add validation" is not a step. Every step contains complete, copy-pasteable code or an exact command with expected output.
  • Oversized tasks — If a task takes longer than 5 minutes, split it.
  • Missing verification commands — Every "confirm" step needs the exact command and expected result.
  • Fabricated paths — Verify file paths against the actual project tree before writing them into the plan.
  • Implementation before tests — Every feature task starts with a failing test.
  • Missing commit steps — Each red-green cycle ends with a commit.
  • Assumed context — Plans must be self-contained. Do not write "follow the existing pattern" — show the pattern.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.