agentleFS
Kikobazz123Kikobazz123/lordgen-competition-demo/.claude/skills/execution-plan/SKILL.md

execution-plan

Skill0 starsChanged 3 months agoMITView on GitHub

Populate the predefined LordGen execution-plan template (docs/execution-plan-template.md) from data/proposal.json. Use after proposal-generator has produced data/proposal.json.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every section of docs/execution-plan-template.md has a corresponding, non-empty section in execution-plan.md.

    line 41
  2. Very specific:

    Every integrations entry not already connected per docs/architecture.md appears in open_dependencies too.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Execution Plan

Purpose

Turn the approved proposal into the one predefined execution-plan template — never a bespoke format per business (CLAUDE.md §13). This is where the automation gets specified concretely enough for automation-builder (Phase 6) to build from, without yet building anything itself.

Input

data/proposal.json (problem, opportunity, proposed_solution, workflow_concept, risks, confidence_caveat) and docs/architecture.md (what services/integrations are actually approved/connected).

Rule: surface integration gaps, don't paper over them

If the proposed workflow needs a capability that isn't in the approved architecture (e.g. a customer-notification channel, when Gmail was cut in Phase 1), the execution plan must say so explicitly under Integrations/Error Handling — as an open dependency to resolve at automation-builder or Integrations phase — rather than silently assuming it exists or quietly building around it. This is the same "don't upgrade confidence silently" discipline as Phases 2-4, applied to architecture instead of evidence.

Required Output

Two artifacts:

  1. data/execution-plan.json — structured, for automation-builder (Phase 6) to consume:
{
  "objective": "", "problem": "", "proposed_solution": "", "trigger": "",
  "inputs": [""], "ai_processing": "", "workflow_steps": [""],
  "integrations": [{"name": "", "status": "connected|not_connected|to_decide", "note": ""}],
  "data_requirements": [""], "human_approval_points": [""], "outputs": [""],
  "error_handling": [{"case": "", "handling": ""}],
  "testing_plan": [{"category": "", "test": ""}],
  "deployment": "", "success_criteria": [""],
  "open_dependencies": [""], "confidence_caveat": ""
}
  1. execution-plan.md (repo root) — filled version of docs/execution-plan-template.md, human-readable, matching the structured data exactly.

Validation (run before reporting results)

  • Every section of docs/execution-plan-template.md has a corresponding, non-empty section in execution-plan.md.
  • problem and proposed_solution are consistent with data/proposal.json (not re-litigated or reworded into something stronger than the proposal supports).
  • confidence_caveat from the proposal is carried forward, not dropped.
  • The required CLAUDE.md §15 test categories (happy path, missing input, external failure, AI failure, duplicate execution, approval gate, configuration) all appear in testing_plan.
  • Every integrations entry not already connected per docs/architecture.md appears in open_dependencies too.

Out of Scope

This skill does not build the workflow — that's automation-builder (Phase 6). It also does not resolve open integration dependencies; it documents them for a human decision.

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.