agentleFS
darrenCWJdarrenCWJ/agent-skills-scaffold/.claude/skills/planning/SKILL.md

planning

Skill0 starsChanged 3 months agoMITView on GitHub

Produce a phased, verifiable plan before any non-trivial work. Use at the start of every M/L-tier task (any task with more than one step) — whenever the user says plan, build, create, implement, refactor, or describes multi-part work — and again when scope changes mid-task. If unsure whether a task needs a plan, it needs a plan.

74 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use Problem-Solving Techniques, ads-management and 10 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 6 projects that use this

  • OpenAnalystIncSkill

    ads-management

    Activate for paid advertising campaigns on Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads. Includes ad copywriting, audience targeting, budget optimization, A/B testing, and ROAS tracking. Used by ads-specialist and campaign-manager agents.

    Also in 3 projects that use this

  • OpenAnalystIncSkill

    ai-artist

    Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.

    Also in 3 projects that use this

  • LucasDuysSkill

    executing

    Autonomous task implementation workflow — implement, test, review, commit for each task in the frontier

    Also in 3 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 6 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 6 projects that use this

  • +4 more from OpenAnalystInc
  • +2 more from mrgoonie

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 2

    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:

    Order phases by risk: Do the riskiest, most uncertain phase first — if the plan is going to die, find out early.

    line 20
  2. Distinctive:

    Every phase has a falsifiable exit criterion — not "improve X" but "X passes test Y".

    line 28

“Common” is measured: kept by at least 6 in 10 of the 66 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

When to plan

Any task with >1 step, any ambiguity, or any risk of rework. If unsure whether it needs a plan, it needs a plan. Trivial single-step tasks (S tier) are exempt.

Procedure

  1. Restate the goal in one sentence. If you can't, you don't understand the task — go back to the user.
  2. List non-goals. Explicitly name adjacent things you will NOT do. This is the main defense against scope creep.
  3. List unknowns and assumptions. For each unknown: resolvable by investigation (do it now via the research skill, or assign to a fan-out agent) or only by the user (batch all user questions into one ask)? Run the orient skill first if the territory is unfamiliar.
  4. Break into phases. Each phase must have:
    • A deliverable — a thing that exists afterward
    • Exit criteria — an objective test (command passes, file exists with X, critic approves against checklist Y)
    • A size of roughly one comfortable work session; split anything bigger
  5. Order phases by risk. Do the riskiest, most uncertain phase first — if the plan is going to die, find out early.
  6. Plan verification per phase, not just at the end: "How will I know this phase actually worked?"
  7. Define abort/rollback. What condition means "stop and re-plan"? What gets reverted?
  8. Plan the fan-out. Mark subtasks parallelizable vs sequential. Independent + exploratory = candidate for subagents (see fan-out skill).
  9. Write the plan to docs/plans/YYYY-MM-DD-<slug>.md using templates/plan.md, then mirror phases into the task list tool.

Quality bar

  • A stranger could execute the plan without asking you anything.
  • Every phase has a falsifiable exit criterion — not "improve X" but "X passes test Y".
  • It states what you will NOT do.

Plan amendments

Plans are living documents. When reality diverges: stop, append an amendment (what changed, why, impact on remaining phases), record a design decision if a choice was involved, then continue. Silent divergence is a protocol violation.

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.