agentleFS
karim-bhalwanikarim-bhalwani/agent-skills-collection/skills/concise-planning/SKILL.md

concise-planning

Skill0 starsChanged 10 months agoMITView on GitHub

Generate clear, actionable, and atomic checklists for coding tasks with minimal interaction and reasonable assumptions. Use when creating implementation plans, breaking down tasks into steps, generating task checklists, or planning project workflows.

5 other projects use a version of this, 5 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 3 are common, 2 are distinctive, and 0 are very specific to this project.

  • 3

    Common

    Most of the 5 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. Common:

    Read README.md, docs, and relevant code files.

    line 24
  2. Common:

    Ask at most 1–2 questions and only if truly blocking.

    line 29
  3. Common:

    Use the following structure:

    line 34
  4. Distinctive:

    Technical Constraints: Do not implement code in this step.

    line 81
  5. Distinctive:

    Assuming All Context: Not reading existing code/docs leads to redundant or conflicting plans.

    line 92

“Common” is measured: kept by at least 6 in 10 of the 5 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

Concise Planning

Goal

Turn a user request into a single, actionable plan with atomic steps.

Workflow

1. Scan Context

  • Read README.md, docs, and relevant code files.
  • Identify constraints (language, frameworks, tests).

2. Minimal Interaction

  • Ask at most 1–2 questions and only if truly blocking.
  • Make reasonable assumptions for non-blocking unknowns.

3. Generate Plan

Use the following structure:

  • Approach: 1-3 sentences on what and why.
  • Scope: Bullet points for "In" and "Out".
  • Action Items: A list of 6-10 atomic, ordered tasks (Verb-first).
  • Validation: At least one item for testing.

Plan Template

# Plan

<High-level approach>

## Scope

- In:
- Out:

## Action Items

[ ] <Step 1: Discovery>
[ ] <Step 2: Implementation>
[ ] <Step 3: Implementation>
[ ] <Step 4: Validation/Testing>
[ ] <Step 5: Rollout/Commit>

## Open Questions

- <Question 1 (max 3)>

Checklist Guidelines

  • Atomic: Each step should be a single logical unit of work.
  • Verb-first: "Add...", "Refactor...", "Verify...".
  • Concrete: Name specific files or modules when possible.

Outputs & Deliverables

  • Primary Output: A single plan.md following the Plan Template
  • Secondary Output: Open questions and assumptions list
  • Success Criteria: Plan has atomic action items and at most 3 blocking questions
  • Quality Gate: Plan reviewed and approved by requester or implementer

Constraints

  • Technical Constraints: Do not implement code in this step; produce a plan only.
  • Scope Constraints: Plans should be limited to the requested scope; avoid speculative features.
  • Governance Constraints: Align plan with project-context.md and spec.md if present.

Common Pitfalls

  • Over-Planning: Creating 30+ atomic steps when 6-10 suffice. Keep it concise; details emerge during execution.
  • Vague Action Items: "Implement feature" isn't actionable. "Add payment processing to checkout flow" is specific.
  • Missing Validation Steps: A plan without testing/verification sets up for rework. Always include a validation checkpoint.
  • Ignoring Dependencies: Listing steps in random order instead of respecting precedence. Steps must be executable in sequence.
  • Scope Creep: Including "nice-to-haves" in the main plan. Use "Out of Scope" section to acknowledge but exclude them.
  • Assuming All Context: Not reading existing code/docs leads to redundant or conflicting plans. Always scan context first.

Integration Points

PhaseInput FromOutput ToContext
InputUser request + contextPlan generationScan code, README, and constraints
Design Specsarchitect specificationsImplementation stepsUse spec.md to guide atomic tasks
ExecutionApproved planimplementerHand off actionable checklist
MonitoringProgress updatesStatus trackingAdjust if blockers emerge

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.