init
Skill5 starsChanged 12 days agoMITView on GitHub
Stand up a kraken coordination repo end to end — verify or create the private repo, install the bundled task template, remove everything an earlier release installed to be executed server-side, and create the canonical labels. Strictly setup, the write-side twin of status's read-only console; it reads and writes no issues.
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
LambenthanSkillexp-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
skyllwtSkillexp-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.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
When the repo does not exist yet, init creates it under the account the token authenticates as — so if that account is not the slug's …
- Very specific: line 103
Print the settings reminder: Do NOT write, create, or touch any settings.json — clobbering an existing one is a real footgun, and the …
- Very specific: line 114
Nothing else: No issues are read or written.
“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
Kraken — raise the head
You are the setup step for kraken: given a coordination-repo slug, you make that repo
ready to receive tasks — the private repo exists, the task template is committed,
everything an earlier release installed to be executed there is deleted, and the
state-machine labels are created. Under kraken-protocol/9 the coordination repo
runs nothing of its own, so it needs no GitHub Actions and carries no copy of the
transition program. This is the symmetric partner
to status (the read-only console): init builds the queue, status reads it. You
touch no issues — none read, none written.
Invocation
/kraken:init OWNER/tasks [--project <name>]The prefix is the harness's spelling (Pi: /skill:init); the arguments are the
same everywhere.
The OWNER/tasks argument is REQUIRED — the coordination repo to stand up. Missing? Do
not guess. Ask for it and stop.
A slug that is still the doc placeholder (OWNER/..., or anything wearing </>) is
refused by the program itself, before any read or write: substitute your real
owner/repo and re-run.
When the repo does not exist yet, init creates it under the account the token
authenticates as — so if that account is not the slug's owner, it refuses (exit 2)
and names both, instead of creating a repo nobody asked for. Relay that message:
the operator switches account (gh auth switch) or creates the repo under the owner
first, then re-runs.
--project <name> is optional. When passed, also create the project:<name> label so
the first project is ready to queue against.
There is no repair flag, and no version handshake between the plugin and the
coordination repo: under kraken-protocol/9 the repo holds no copy of the transition
program, so there is no second copy to fall out of date.
Design decisions
- The mechanics live in
kraken.py init, not in this prose. Standing a repo up — verify-or-create it private, install the bundled assets, upsert the canonical labels — is deterministic, zero-judgment work, so it is executed by the bundledkraken.py(the same programunleashandstatususe), once, identically, token-free, and testable against the conformance stub. This skill only invokes it, renders its report, and prints the settings reminder. Same rule that producedclaim-nextandstatus. - Assets ship in the plugin, never fetched from the network.
task-template.ymllives in this plugin'sskills/unleash/folder —kraken.py initreads it from there and commits it via the GitHub contents API. The bundled copies match the installed plugin version and work offline. Nevercurlfromraw.githubusercontent.com. - Idempotent and non-destructive by construction.
kraken.py initcreates the repo only if absent, creates each asset only if absent, and upserts the labels with their canonical color/description. An existing file is reportedpresentand left exactly as it is. Re-running is safe. - Nothing installed is executed, so nothing has to stay in sync. The one
asset is an issue form — it shapes a task on the way in and runs no code.
A template the operator tuned is their business, not drift to police, which is
why there is no
--upgrade, no byte comparison and no refusal path. - Re-running init is the migration. A coordination repo stood up by an older release still carries the workflows and the vendored program that release installed; a cron left running against retired semantics keeps mutating labels behind every worker's back. So init DELETES them — gated on kraken's own file header, so something the operator wrote at one of those paths is never destroyed by a bootstrap command.
Protocol
Run the bootstrap.
kraken.py initdoes the whole deterministic gesture — verify-or-create the repo private, install the bundledtask.ymlissue-form template via the contents API, delete everything an earlier release installed to be executed server-side, and upsert the canonical state-machine labels (kraken-task,in-progress,needs-decision,awaiting-merge) plus thepriority:highscheduling label with their canonical colors and descriptions:python3 "<this skill's folder>/../unleash/kraken.py" init OWNER/tasks [--project <name>]Pass
--project <name>to also upsert theproject:<name>routing label a worker's--projectfilters on. Branch on the exit code:0— bootstrapped (render its report);20— a gh/network failure, state may be partial, re-run after checking (init is idempotent, so a re-run resumes safely).- Render the report.
kraken.py initprints one line per repo/asset/label decision (created/present/removed/upserted) and a summary line. Relay it. Call out anything reported removed — that is a workflow (or the vendored program) an earlier release installed and this protocol revision retired, deleted so it stops running against semantics the workers no longer implement. - Print the settings reminder. Do NOT write, create, or touch any
settings.json— clobbering an existing one is a real footgun, and the permissions belong to each worker's prepared environment, not the coordination repo. Instead print a one-line reminder: before launching a worker, pre-allow the delivery commands in that environment's.claude/settings.json— see the worker-environment permissions example inREADME.md, which stays the source of truth. A GitHub Copilot CLI worker takes its permissions as launch flags instead: point the operator atscripts/kraken-copilot.sh(interactive) orscripts/kraken-loop.sh(the ambush, on every harness —--harness claudepasses Claude Code's own) in a kraken checkout, which pass them. - Nothing else. No issues are read or written; no worker is launched. Point
the operator at
status(the queue's console, with ready-to-paste launch lines) orunleash(to start draining) as the next step.
Authorization boundaries
- Invoking this skill is my authorization to, on the coordination repo only:
(a) create the repo private if it does not exist;
(b) commit the bundled
task.ymltemplate via the contents API, creating it only — never overwriting a file that already exists; (b2) delete everything an earlier release installed to run server-side (reclaim-stale.yml,requeue-on-reply.yml,cleanup-closed.yml,validate-task.yml, and the vendored.github/kraken.pythey exec'd — their jobs are now derived by the reader on the queue read it already performs, PROTOCOL.md §2.1 and §6), and only when the file still carries kraken's own header, so something I wrote at that path is never touched; (c) upsert the canonical labels (and theproject:<name>label when--projectis passed). - It is NOT authorization to read or write issues, modify
settings.json, delete anything, change repo visibility on an existing repo, or launch a worker. - init never overwrites an existing file, and never deletes one that does not
carry kraken's own header —
kraken.py initenforces both, it is not left to judgment.
Coordination repo / flags / extra context: $ARGUMENTS (if that reads as a literal placeholder, they follow this skill as the request text)
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.

