agentleFS
Sign inStart free
treylomtreylom/ThisCode/skills/init/SKILL.md

init

Skill41 starsChanged 2 months agoMITView on GitHub

Use when the user runs /thiscode:init or first-time installs thiscode — detects env (vault state / tools / resources) and recommends an 8-Phase progressive install.

137 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

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 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

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

  • 0

    Common

    Most of the 125 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use --non-interactive (and any CI / automation env) only on the user's explicit opt-out, never as the default or step 1.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 125 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

init

obsidian-cli → GraphRAG 점진 진행을 학생이 자연스럽게 따라가도록 wizard 형 install 진입점.

Repo-handoff contract (read first)

Shared, normative: contracts/repo-handoff-install-contract.md (in lockstep with ThisCodex). In short:

Default = interactive guided onboarding. This init wizard asks one question at a time; that is the default path for both humans and AI agents handed the repo. If you are an AI agent: run the guided wizard and relay each question to the user through your session/TUI — do not auto-run a non-interactive install, do not self-answer or fabricate an answers file to skip questions, and do not report "copied = installed" or placement as completed onboarding. Use --non-interactive (and any CI / automation env) only on the user's explicit opt-out, never as the default or step 1. On a missing required decision the installer safe-stops with interactive recovery — relay that to the user and let them choose; never self-answer to push past it.

Prereq

  • jq (JSON 처리)
  • python3 (Phase 추천 알고리즘)

Workflow

  1. env detect — ../../scripts/claude-discode-init.sh --detect-only --json 호출, OS / vault / tools / resources 9 keys JSON 출력
  2. Phase 추천 — note_count + 도구 + 자원 multi-axis 알고리즘:
    • current: 현재 가능 (의무 install)
    • recommended: 권장 (사용자 y/n)
    • later: 조건 미충족 / advanced
  3. wizard 대화 — recommended Phase 별 y/n prompt, 사용자 선택 install dispatch
  4. install dispatch — 선택한 Phase 마다 ../../scripts/install-*.sh 호출
  5. healthcheck — install 후 bash scripts/healthcheck.sh

8 Phase 매핑

(commands/init.md 참조)

Non-interactive (CI/headless)

  • init.sh --non-interactive → Phase 추천만, install skip
  • CLAUDE_DISCODE_INIT_AUTO=phase-X,phase-Y env → auto install (prompt skip)

옵션 언제나 (사용자 spec Q2)

GraphRAG 노트 수 미충족 시도 사용자 force install 가능. preflight (Python/disk/port) 만 의무.

How to Use This Skill

Use this skill during initial setup to run the interactive wizard that detects your environment (vault state, installed tools, system resources) and progressively recommends which local-tool phases to install next (ripgrep, obsidian-cli, vault-search MCP, GraphRAG, dense embeddings). The optional vault-search MCP installer is separate from the km plugin's /km:search fallback, whose order is GraphRAG → Obsidian CLI → Obsidian MCP → text search. Follow the wizard's prompts to match your setup stage.

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.

Check your setup, free