Anvil 技能
Anvil 是除錯領域的「重砲級」工具。它能建立一個「Thunderdome」競技場，在其中複製多個獨立的 git worktree，並由多個代理程式同時競爭，嘗試修復錯誤。
指令
- 除錯（Debug）：
./run.sh debug run --issue "..." - 強化（Harden）：
./run.sh harden run - 清理（Cleanup）：
./run.sh cleanup run --run-id ...
重型「無震」除錯與強化協調器。適用於複雜、頑固的錯誤（當 `review-code` 失敗時）或對程式碼庫進行「紅隊演練」（強化）時使用。透過 git worktree 隔離技術，平行執行多個代理程式（Thunderdome）。
Anvil 是除錯領域的「重砲級」工具，專為處理 `review-code` 無效的頑固錯誤或需對程式碼庫進行全面紅隊演練（強化）的場合而設計。此技能的核心是建立一個「Thunderdome」競技場，在其中複製多個 git worktree 並啟動多個代理程式，平行且獨立地嘗試修復錯誤或尋找弱點。這種「無震」隔離機制確保每個代理程式的工作不會互相干擾，並能提供多種可能解決方案。支援 Debug（除錯）與 Harden（強化）兩種模式，並附帶清理功能以維護工作區整潔。主要用於 Claude Code 或類似支援 git worktree 的主流程式碼代理環境，是開發者在複雜除錯或正式上線前強化安全性的第一線工具。
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/anvilInstalled? Explore more 生產力與協作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
Anvil 是除錯領域的「重砲級」工具。它能建立一個「Thunderdome」競技場，在其中複製多個獨立的 git worktree，並由多個代理程式同時競爭，嘗試修復錯誤。
./run.sh debug run --issue "..."./run.sh harden run./run.sh cleanup run --run-id ...This repo contains 20 individual skills — each has its own dedicated page.
Turn a client brief, zip bundle, directory, or single requirements file into a typed acceptance-contract bundle with extracted requirements, acceptance checks, open questions, an immutable-goal draft, and a create-report-backed decision report. Use when users say acceptance contract, brief to requirements, freeze the goal, create immutable goal, amend immutable goal, build a Battle requirements bundle, or extract requirements from this bundle.
Canonical map and shared contracts for the agent-governance ecosystem: the pi.receipt_envelope.v1 boundary envelope, the component graph, and the rules for which component owns which schema. Use when wiring a skill or extension into the shared receipt world, when asking how shame, triage-error, tau, ask, project-watchdog, ops-herdr, ponytail, and Memory fit together, or when validating an envelope.
Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory validation, or readiness scoring for a skill workflow.
File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.
Generate and query the centralized agent identity registry. Scans .pi/agents/*/AGENTS.md, parses frontmatter, outputs agents-registry.json and optionally syncs to /memory for semantic search.
Artifact-driven status surfaces for long-running project-agent work. Maintains status.json, events.jsonl, proof manifests, and a stale-aware STATUS.html so humans can tell where the agent is, what passed, what is still unproven, and what decision or action is next — without dashboard theater.
Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow, high-stakes implementation, plan-iterate, project-infographic, or multi-review work.
Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.
Evaluate generated Chatterbox voice files as voice-quality artifacts: affect match, arousal/valence proxies, pause placement, intelligibility inputs, clipping, loudness, and discontinuity flags. Use when reviewing Chatterbox emotional tags, pauses, Turbo/base affect delivery, Persona Dream utterance renders, or whether generated speech matches an intended product-facing affect.
Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled JS/TS source.
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the oai-trial project. Use for anonymize data, pseudonymize exports, redact policy literals, or discover and explicitly approve fuzzy name aliases. The skill is a thin CLI/Docker interface, not another engine.
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.
Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.
Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, ask Pi-native subagents from within Pi, run persona/deep-review workflows, generate image prompts, check OS/project health through composed skills, or run an ask DAG. This skill is the executable /ask runtime; do not replace it with an informal subagent, plain web search, or hand-written review; inside Pi, explicit Pi-native subagent targets are routed through the pi-subagents tool as an Ask target type.
Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment analysis. Offer to run after major changes (don't auto-run).
Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.
Self-improvement workbench for /assistant. All the tools needed to diagnose, train, evaluate, and promote models in a continuous loop. The "warm pond" where /assistant evolves its own inference stack.
Pre-flight validation and quality gates for batch LLM operations. ACTUALLY tests samples through LLM before burning tokens. Uses SPARTA contracts for DuckDB validation queries. Integrates with task-monitor for enforced quality gates.
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.