agentleFS
luw2007luw2007/skills/skills/kickoff/SKILL.md

kickoff

Skill1 starsChanged 5 months agoMITView on GitHub

Freeze goal, path, execution, and acceptance before non-trivial implementation or agent dispatch. Use when requirements hide assumptions, multiple implementation paths exist, feasibility needs research/prototyping, work spans modules or agents, or the user asks to align requirements before building. Produces an accepted, versioned Kickoff Contract.

31 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

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 1

    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:

    Read workflow and contract schema.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 24 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

Kickoff

Turn intent into an accepted build contract before execution. Do not replace repository evidence with interview questions, and do not force ceremony onto trivial, fully specified changes.

Gate

Kickoff is required before non-trivial implementation or agent dispatch when any applies:

  • product behavior, failure semantics, boundaries, or acceptance remain implicit;
  • more than one materially different path is plausible;
  • feasibility depends on unknown code, runtime, library, API, cost, or permission facts;
  • work spans modules, agents, phases, or durable checkpoints;
  • changing direction after implementation would be costly.

Skip only for trivial, reversible, fully specified work with one evident path and direct verification. Record why the gate was skipped when an orchestration skill consumes the task.

Workflow

Read workflow and contract schema.

  1. Derive repository/runtime facts first. Ask only for material product or risk decisions tools cannot resolve.
  2. Freeze goal: problem, outcome, non-goals, invariants, user journeys, and observable acceptance.
  3. Freeze path: constraints, candidate routes, probes, selected route, rejected routes, decisions, consequences, and revalidation triggers.
  4. Freeze execution: accepted base, dependency nodes, exclusive scope, required evidence, minimal E2E smoke, and change-control triggers.
  5. Build traceability from every required goal/invariant to decision, execution node, and evidence producer. Reject or remove orphan nodes.
  6. Persist exact contract bytes in an owner-controlled artifact. Set status: accepted only after the user or authorized owner accepts every material decision; clear, already-authorized intent with no material unresolved choice may be owner-accepted without another prompt.
  7. Pin contract_id, version, and SHA-256 digest at dispatch. Workers receive read-only projections and cannot amend or accept the contract.

Unresolved material decisions mean needs-decision, never accepted. Execution discoveries that invalidate goal, path, scope, or acceptance stop affected nodes, create impact analysis, increment the version, and require renewed acceptance. Evidence may satisfy a contract; it cannot silently rewrite one.

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.