init
Skill0 starsChanged 4 days agoMITView on GitHub
Use when the user asks to set up, bootstrap, or resume setting up a context-routing workspace in a repository, for example "turn this repo into a context-routing workspace". Runs a phased, resumable bootstrap. Not for adding one module to an existing workspace (use add-module) and not for routine work in a finished workspace.
137 other projects use a version of this.
Adopted by
Most recently taken up by
- naderelewa/Product-to-Prodtheir own version, first seen Nov 8, 2026
- ShahriarBijoy/show-me-howtheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- BSSE23047/nauraiz-devtheir own version, first seen Nov 8, 2026
- edwinidrus/dragonhoardtheir own version, first seen Nov 8, 2026
- NilsHellwig/acl-paper-skillstheir own version, first seen Nov 8, 2026
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.
LambenthanSkilldaily-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
skyllwtSkillexp-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
gaebalaiSkillcodex-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
Other versions137 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 137
- microsoft/vscode★ 195ksame name
- mcollina/skills★ 2ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- TokenRollAI/cc-plugin★ 483same name
- pipecat-ai/gradient-bang★ 420same name
- AlexPEClub/ai-coding-starter-kit★ 382same name
- dannysmith/tauri-template★ 312same name
127 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- add-moduleSkill
- checkSkill
- close-sessionSkill
- cross-module-owner-apiSkill
- curateSkill
- kbSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 125 edited versions we read keep these.
4
Distinctive
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
- Distinctive: line 17
Never overwrite an existing file.
- Distinctive: line 20
If the user already answered in this conversation, use that answer and say so.
- Very specific: line 27
If root session_state.md exists, read it only down to the first line that equals <!-- AGENT-SESSION-STOP -->.
- Very specific: line 29
If that latest entry is titled init phase 0 started, repeat phase 0 (it skips files that exist, so repeating is safe).
- Distinctive: line 39
Read only the reference file for the phase you are in.
- Distinctive: line 64
If you can see your context usage and it is above half, record the current phase and suggest a fresh session.
“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.
Files
Init
Turns the current repository into a workspace where every task starts from
a small, predictable set of files: rules in AGENTS.md, a module registry
in modules.md, curated knowledge pages per module, and a newest-first
session log that lets the next session resume.
Ground rules
- The repository's code and documents are read-only inputs. Never move, rename, or edit them.
- Never overwrite an existing file. Keep the existing one and list it as skipped in the phase report.
- Lines marked ASK need the user's answer. Never answer them yourself. If the user already answered in this conversation, use that answer and say so.
- Finish a phase, record it, then start the next. Any recorded phase is a safe place to stop.
Find the current phase
- If root
session_state.mdexists, read it only down to the first line that equals<!-- AGENT-SESSION-STOP -->. - If that latest entry is titled
init phase 0 started, repeat phase 0 (it skips files that exist, so repeating is safe). If it is titledinit phase N completeand N is below 5, continue with phase N+1. - Otherwise, if
AGENTS.mdandmodules.mdboth exist, the workspace is already set up: readreferences/upgrade.mdand bring it up to date. It ends early when nothing needs to change. - Otherwise start at phase 0.
Phases
Read only the reference file for the phase you are in.
| Phase | Read | Produces |
| 0 | references/phase-0-copy.md | skeleton copied |
| 1 | references/phase-1-spine.md | rules file, capability profile, entry point |
| 2 | references/phase-2-idea.md | confirmed idea.md |
| 3 | references/phase-3-modules.md | modules registered |
| 4 | references/phase-4-intake.md | raw material indexed, inventories written |
| 5 | references/phase-5-verify.md | verification report |
| upgrade | references/upgrade.md | existing workspace brought up to date |
Record each phase
Insert a new entry at the top of root session_state.md:
## YYYY-MM-DD - init phase N complete
- Last active module: `<module, or none>`.
- Workspace docs: <what this phase produced; skipped files>.
- Verification: <what you checked>.
- Next useful action: init phase N+1 (<phase name>).
<!-- AGENT-SESSION-STOP -->If you can see your context usage and it is above half, record the current phase and suggest a fresh session; the next session resumes from the log.
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
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.