agentleFS
NagiliantNagiliant/Genesis-Legacy-V2/skills/genesis-discover/SKILL.md

Discover

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Build the project profile through guided conversation — the grounding document every later phase reads. Establishes the mode and, for content projects, the work-unit registry.

57 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read project-state.md; extract the mode.

    line 20
  2. Very specific:

    If discovery already exists and --refine was not passed, ask redo-or-refine.

    line 21
  3. Distinctive:

    Run the mode-specific guided conversation (below).

    line 22
  4. Very specific:

    Write .genesis/discovery/context.md and ask the user to confirm.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 50 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

Discover — Build the Project Profile

A guided, conversational intake that produces .genesis/discovery/context.md — the single grounding document every later phase reads. Entry point of the pipeline; no prior approval required.

Inputs

  • .genesis/project-state.md (the mode)
  • .genesis/constitution/index.md (if it exists)
  • The mode-specific template: discovery-greenfield.md / discovery-brownfield.md / discovery-lowfield.md
  • An existing .genesis/discovery/context.md when --refine

Process

  1. Read project-state.md; extract the mode. Branch all behavior on it.
  2. If discovery already exists and --refine was not passed, ask redo-or-refine.
  3. Run the mode-specific guided conversation (below).
  4. Write .genesis/discovery/context.md and ask the user to confirm.

Greenfield — interview (7 areas)

Project Identity · Scope & Features · Constraints · Technology Preferences · Organizational Standards · Integration Points · Quality Expectations.

Brownfield — interview + scan + gap analysis

Greenfield's areas, plus:

  • Codebase scan: languages/extensions, directory structure, test infrastructure, dependency health, CI/config, recent history (git log --oneline -50), documentation state.
  • Human context: history, practices, pain points, tech debt, what works, improvement priorities.
  • Gap analysis: classify each area Missing / Partial / Present, with a priority-ordered convergence plan.

Lowfield — interview + content scan + unit registry

Conversation (7 areas): Your Domain · Information Architecture · Workflow Stages (each becomes a pipeline stage) · Quality Standards · Progressive Reveal (sequential-discovery domains only) · Reference Materials · Tools & Formats. Then teach how the pipeline maps onto the domain and define the custom stages.

Unit registry (--scan to seed from existing files): map content files to unit IDs using a naming convention (propose, confirm), ask which stage each unit has reached, and write units.json:

{
  "feature": "<feature-name>",
  "convention": { "prefix": "U", "digits": 3, "separator": ": ", "example": "U001: Sample Title" },
  "units": [
    { "id": "U001", "title": "Chapter 1: The Beginning",
      "status": "in-progress", "currentStage": "dev-edit",
      "entryStage": "dev-edit", "aliases": [], "notes": "Imported from chapters/ch-01.md" }
  ]
}

Units with no content yet are status: pending; imported units are in-progress with currentStage/entryStage set.

Output

  • .genesis/discovery/context.md — the structured profile. Brownfield appends scan results + gap analysis; lowfield appends content-type definitions, workflow descriptions, and a unit-registry summary.
  • .genesis/features/<feature>/units.json (lowfield only).

Next step

Run /genesis-constitute.

Natural language triggers

- "discover"
- "tell genesis about my project"
- "profile this project"

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.