agentleFS
lukashouthoofdlukashouthoofd/cenekathon/.agents/skills/kickoff/SKILL.md

kickoff

Skill1 starsChanged 14 days agoMITView on GitHub

Use when the challenge brief just arrived or the team has no plan yet — turns the brief into one chosen idea, a minimal architecture, task split, and docs/PLAN.md within ~45 minutes.

36 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use standup, grill and 3 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.
  • AnthropicSkill

    standup

    Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into yesterday/today/blockers, or structuring a few rough notes into a shareable update.

    Also in 3 projects that use this

  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 5 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

Files
SKILL.md

Kickoff (brief → plan in 45 min)

Never start coding before steps 1–4 are written down. Time-box: 45 min total.

  1. Brief (5 min). Paste the brief into docs/CHALLENGE.md. Extract: who the user is, the problem, judging criteria, hard constraints (data, tech, time). Write unknowns as questions for the organisers.
  2. Diverge (10 min). Propose 3 distinct ideas (one line each: user · pain · magic moment). Include one "boring but certain" and one "ambitious".
  3. Converge (5 min). Pick ONE by: fits judging criteria · demoable in 5 min · buildable in ≤4 h by this team · has one wow moment. Record the choice and rejected ideas in docs/DECISIONS.md (decision, why, alternatives).
  4. Architecture (10 min). Smallest thing that works: ≤ 3 components, one language if possible, managed services over self-hosting. Draw an ASCII data flow. Fill docs/STACK.md (install, run, test, deploy commands).
  5. Walking skeleton first. Task 1 = deployable hello-world through the whole stack (see rapid-prototype, deploy-fast).
  6. Split (10 min). Cut into vertical slices, each ≤ 45 min, each demoable. Assign owners + folders in docs/TEAM.md. Create GitHub issues (gh issue create) from the slice list. Mark the cut line: what we drop first if behind at 17:30.
  7. Write docs/PLAN.md: idea · user · wow moment · architecture · slices with owners · cut line · demo story.

Done when: PLAN.md exists, every human has a first task, the walking-skeleton task is running. Avoid: scope creep, picking tech for CV reasons, building infra, debating > 10 min.

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.