Zerobounce Automation
Automate Zerobounce tasks via Rube MCP (Composio). Always search tools first for current schemas.
Claude assistants and Claude Code workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.
Automate Zerobounce tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zoho tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zoho Bigin tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zoho Invoice tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zoho Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zoominfo tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zylvie tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Zyte API tasks via Rube MCP (Composio). Always search tools first for current schemas.
Plan and produce Chinese WeChat articles and spoken-video scripts, from news-topic selection and drafting to HTML formatting, publishing steps, and updates to the workflow’s content records.
Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.
Verify a named artifact, workflow, deployment, or script against observable evidence. Read-only by default, bounded to the requested target, and explicit when evidence is incomplete.
Use Cloudflare API credentials bound in Nuphos to inspect or change Cloudflare account resources.
Hill-climb the benchmarks in elizaOS/asi, a JAX continual-reinforcement-learning framework, with optional public payout registration. Use when an agent is asked to improve a measured result, port a method from the literature, fix something that corrupts measurement, decisively close a research direction with paired evidence, or register a public Solana payout address.
Create a new issue file from a test262 failure pattern. Includes smoke test, sample extraction, and proper frontmatter.
Measure whether a Topping Out rule actually binds, by tempting it at three prompt strictness levels in a throwaway working directory and grading what the session executed, deterministically. Use for /f-comply, "does this rule actually work", "test the NEVERs", "is RULES.md being followed", before trusting a new builder, or before promoting a rule to a hook. Measures existing rules: not for writing them (f-distill promotes a card into the constitution). Not a code gate.
Validate one plan against the codebase with COLD seats (the owner's standing choice, or the one-shot picker the first time and on request: 1-5 models from families different than the Player that authored the plan (codex/Astra, Claude, Grok CLIs at $0 subscription; OpenRouter doors from a curated roster), so the read is genuinely independent. Every seat runs at high reasoning, dispatched in parallel, and findings are merged across seats with seat attribution, never voted. Read-only but for two residues: the saved seat choice in the repo profile (the first pick, or a change) and the gate: plancheck line, written on request and always for a plan under or headed for the repo's ready-to-build plans folder. Use when the user runs /f-plancheck or /cv, wants a plan checked before building, or asks for cross-validation. This is the cold-seat protocol, not the validator itself, it dispatches plan-validator; reach for that directly only when cross-family independence does not matter. Also answers
Break a decision-complete plan (a /f-blueprint BLUEPRINT, or any plan too big for one job) into a PROJECT: one ticket file per job, a dependency graph, and the first project board (BOARD.json + a generated board page). Use when the user runs /f-schedule, says "break this plan into tickets", "decompose this into jobs", "turn this plan into a project", or when a plan has more than one PR's worth of work. Proposed-first: shows the cut and waits for the owner's go before writing. Not for writing the plan (f-blueprint), not for planning one ticket's job (the foreman's scoping + PLAN.md), not for board updates after that (f-board). Also answers to its old name, /f-decompose.
Topping Out's first step: turn a fuzzy ask into a decision-complete, codebase-grounded commission block by settling every open question first. Use when the owner runs /f-survey, says "survey this", "groom this" (the old name), "this is still vague", "tighten this before we build", "what am I missing", or hands over work whose scope or approach is not yet decided. Add --voice (or say "survey this out loud", "talk me through it") to run it aloud as a colleague conversation, one short turn at a time. Also answers to its old name, /f-groom. Next step: /f-blueprint. Not the site walk (the machine check at the start of a job, METHOD §2). Not for writing the plan (f-blueprint) or cutting it into tickets (f-schedule).
Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.
Manage Multica resources (issues, agents, autopilots, skills, workspaces) and the local agent runtime daemon via the multica CLI. Use when the user runs multica, mentions Multica issues/agents/autopilots/skills/runtimes/workspaces, or needs to script Multica workflows.
Manage model API keys, default models and per-agent vault secrets with the penguin CLI.
分析当前分支的全部变更,自动生成或更新 PR 标题和正文。聚焦内容质量:解释 why、归纳 what、标注测试方式,遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述,或已有 PR 需要更新描述。
Project-specific skill template covering architecture, patterns, testing, and deployment guidance.
Launch and verify AgentMux's own task dev build on Windows — the MAXPATH subst workaround, a real free-port check instead of trusting the hash, how to confirm the window is actually ready (poll state, not logs), and a safe cleanup pattern for a host running several agents' dev sessions at once.