Autonomous goal loop — give it ONE goal plus how to verify it, the agent runs check→fix→check itself and comes back only with the finished result (code with audit, research with fact-check, content with critique, audit/backtest). Self-verification instead of constant supervision, with hard safety guards. Vary the loop with a verification rubric designed before it runs. Triggers — "work autonomously to the result", "don't come back until it's done", "run the loop yourself", "drive it to done".

中文简介正在准备中。当前显示原文说明。

Council — 5 independent AI perspectives + mutual critique + synthesis (adapted from karpathy/llm-council for Claude Code). For high-stakes decisions where the answer does NOT follow unambiguously from the data — go/no-go before real consequences, critiquing a methodology, choosing between competing approaches, pressure-testing a conclusion you're attached to, designing risk controls. NOT for log/data analysis (the council has no data access) and not for factual lookups. Triggers — "convene the council", "run it past the council", "go/no-go", "pressure-test this".

中文简介正在准备中。当前显示原文说明。

Write an analytical longform piece — a 4-phase pipeline from raw idea to finished text, with research-backed facts and a devil's-advocate pass before publishing. Invoke /longread <topic>. Triggers — "write a longread about X", "write an analytical breakdown of Y", "write an expert post", "turn this into an article".

中文简介正在准备中。当前显示原文说明。

A gate before git push / deploy — assembled from your own tools (secret-grep + slop-scan + code-review + build/compile + optional worktree isolation), so AI junk (slop / bugs / secrets / uncompiled code) never reaches a remote or a production server. Turns "I hope it's clean" into a verifiable criterion. Branches: web/OSS (git push/PR) vs deploy-to-server service. Triggers — "check before push", "clean push", "gate before push", "finalize before commit", "run before deploy".

中文简介正在准备中。当前显示原文说明。

Prove — or honestly fail to prove — a specific technical claim: "the fix works", "it's deployed", "the service is running", "the site is done", "there are no vulnerabilities". Atomizes the claim, picks the shortest decisive signal on the evidence ladder, and returns a verdict from a fixed vocabulary (pass / partial / fail / skip) with an explicit coverage boundary. NOT code review, NOT a fix, NOT orchestration — only "what is proven, and what we merely hope". Triggers — "prove it works", "is it really done?", "are you sure?", "we deployed — is it live?", "verify that", "did we actually check?".

中文简介正在准备中。当前显示原文说明。

Security launch audit for a public web app BEFORE you ship or hand it to a client — "vibe coders are getting sued", systematized. An executable pipeline: classify (static / full-stack / AI) → run sections (secrets+supply-chain, DB, auth, infra+headers, legal, LLM/injection) orchestrating deterministic tools + manual checks → GO/NO-GO report. Adapted from Prajwal Tomar's playbook, extended with prompt-injection / supply-chain / secret-history / dependency-CVE layers. NOT the same as pre-push (that = clean push; this = is the product itself safe to launch). Triggers — "security checklist for the site", "audit before launch", "is the site safe", "check before handing to client".

中文简介正在准备中。当前显示原文说明。