com um clique
animus-skills
animus-skills contém 31 skills coletadas de launchapp-dev, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Authoring policy for producing Office documents (xlsx/pptx/docx) as `document` subjects. Used by the author-document workflow's generate phase — draft a spec, render+store via the animus-document-engine store_document tool, then record it with create_subject.
Operate Animus v0.7 execution environments — environment plugins and coder nodes, the cross-phase environment broker, workflow/phase `environment:` pinning, `environment_routing:` rules, `workspaces:` multi-repo checkout sets, lease records and the startup reaper, and animus-environment-railway. Use when pinning workflows to remote execution, debugging node acquisition or teardown, or authoring multi-repo runs.
Operate the Animus portal (animus-launchapp) — the flat-named portal MCP surface and admin-only tool visibility, Claude/Codex subscription Connections, the external MCP-server catalog with Connect handshake and ext.* subject projection, the durable script registry and phase_context_schema authoring loop, team_* workflow authoring over MCP, and trigger-event observability. Use when driving a portal deployment rather than a local CLI install.
Product lifecycle agents — product owner, architect, auditor, docs-writer, devops, researcher personas
Guide a project from idea to autonomous engineering setup — interview the user, write VISION.md, AGENT_PRINCIPLES.md, registry, agents/workflows/phases/schedules YAML, scripts, and a first runnable task. Use when standing up Animus in a new project beyond the minimal /animus-setup scaffold.
Set up .mcp.json, Claude Code permissions, and connect AI tools to Animus's MCP server
Build Animus workflow packs - `pack.toml`, workflow exports, runtime overlays, MCP server descriptors, schedules, and marketplace operations. Use when creating or updating installable Animus packs.
Inspect Animus execution history, Git repo and worktree state, and approval records — history search and cleanup, worktree listing and pruning, repo-scope resolution, and the approval gate for destructive operations. Use for post-run forensics, worktree housekeeping, or approval round-trips.
Build Animus skills - YAML skill definitions, prompts, tool policies, capabilities, adapters, and registries. Use when creating or updating Animus skill files under user or project skill definitions.
Inspect Animus token and USD spend, attribute cost to providers/models/phases, and operate workflow budget caps. Use when a question involves cost, spend, tokens, USD, budget caps or `budget:` blocks, budget breaches, paused-for-budget workflows, provider/model cost attribution, cost leaderboards, or `animus cost` commands.
Start, stop, restart, monitor the Animus daemon — plugin preflight, health verdict, observe front-door, events, logs, metrics, pool sizing, common issues
Inspect Animus status, daemon observe/health/metrics, structured streams, logs, run output, decision logs, artifacts, budget breaches, plugin status, web UI transports, and trigger events.
Deep reference for Animus human-in-the-loop (HITL) agent interactions — agent questions and approval requests, the pending-interaction inbox, paused workflows waiting for an answer, permission prompts, approval_policy routing, and suspend/resume mechanics. Use when an agent is parked on a pending interaction, a workflow is paused awaiting a human decision, an approval or permission prompt needs answering, or when configuring approvals for agents.
Run and inspect Animus agent executions, direct provider runs, agent control, status, project-scoped agent memory, agent message channels, and human-in-the-loop interactions.
Hold and manage multi-turn Animus chat conversations — interactive provider sessions, conversation history, resume semantics, transcript search and export, and per-conversation cost.
Connect agents to Context7, package-version, sequential-thinking, memory, GitHub MCP servers
Operate Animus flavors — curated plugin bundle manifests (`flavors/<name>.toml`), the `animus flavor` command group, manifest-driven `plugin install-defaults --flavor`, active-flavor persistence in `.animus/plugin-scope.yaml`, drift reports, required vs recommended plugin sets, and writing custom flavor manifests.
Choose models and verify provider readiness in Animus — provider plugin health, API-key and CLI-tool diagnostics, model/tool routing in workflow YAML, and per-model cost attribution. Use when selecting a model for a phase or agent, or when diagnosing why a provider or model fails to dispatch.
Common Animus issues and fixes — daemon crashes, plugin preflight, workflow failures, queue problems, merge conflicts
Animus plugin supply-chain security — sha256 checksums, cosign keyless signature verification, signature policy (strict/warn/disabled), trusted-signers allowlists, audited TOFU org trust with revocation, plugin lockfiles and fail-closed semantics, lock verify tamper detection, and CI verification gates. Use for questions about plugin security, lockfile integrity, signature verification, trusting or revoking orgs, or detecting tampered plugin binaries.
Install, inspect, update, lock, sign, scaffold, and troubleshoot Animus STDIO plugins — global and project-scoped installs, flavor-driven defaults, TOFU org trust auditing — covering provider, subject_backend, trigger, transport/web, workflow_runner, queue, and log-storage plugins.
Install Animus, initialize a project, create first task subject, run first workflow — core concepts and project structure
Set up Animus in the current project - initialize config, connect MCP, install required plugins, create a first workflow, and start the daemon. Use when bootstrapping Animus in a repo or fixing an incomplete Animus setup.
Animus project config, daemon config, plugin config, agent runtime, environment variables, and state layout
Animus MCP tool surface - agent, daemon, cost, subject, workflow, queue, output, skill, memory, plugin, logs, and tool-discovery tools, including pagination, batch behavior, and error remediation. Use when an Animus task needs exact MCP tool names, key parameters, or tool-selection guidance.
Dispatch queue operations — enqueue, hold, release, drop, reorder, and queue patterns
Work with Animus subjects and subject_backend plugins, including task, requirement, Linear, SQLite, Markdown, and custom subject kinds, default_subject_kind, wire ids, and status routing.
Task lifecycle through the unified subject surface - create, list, update, block/unblock, enqueue, and inspect task-like subjects via CLI and MCP
Battle-tested pipeline patterns — QA gates, command phases, conflict resolution, CI checks, stale PR handling, budget guardrails, human approval gates
Write or update Animus workflow YAML in `.animus/workflows.yaml` and `.animus/workflows/*.yaml` - workflow definitions, agents, phases, model registries, MCP bindings, schedules, triggers, daemon config, and related runtime sections. Use when defining a workflow or fixing workflow config.
Correction policy for cleaning raw meeting transcripts — fix ASR errors without altering meaning. Used by the transcript workflow's clean-transcript phase.