CommunityPesquisa e Análise de Dadosgithub.com

grahama1970/analyze-elf

Faz engenharia reversa de recursos de binários ELF. Extrai comandos CLI, máquinas de estado, protocolos, esquemas Zod e modelos de dados. Gera automaticamente um relatório de acusação /create-walkthrough com diagramas Mermaid. Usa /treesitter para análise AST de código JS/TS empacotado.

O que é analyze-elf?

O analyze-elf é uma habilidade especializada para engenharia reversa de binários ELF compilados, focando em extrair recursos de alto nível — como comandos CLI, máquinas de estado, tipos de evento, métodos JSON-RPC, esquemas Zod e modelos de dados — em vez de apenas desmontar código de máquina. Ele é particularmente útil para entender rapidamente o que um binário compilado faz, seja ele gerado por Bun SEA, Go, Rust ou C/C++. A habilidade suporta extração de texto de ajuda, padrões de atribuição de enum, literais de tipo e análise de AST através de /treesitter para JS/TS empacotado. Os resultados podem ser gerados em formato JSON ou como um relatório de acusação (/create-walkthrough) com diagramas Mermaid. O analyze-elf é ideal para desenvolvedores, analistas de segurança e engenheiros de plataforma que precisam documentar ou auditar o comportamento de ferramentas CLI compiladas, sistemas de missão ou protocolos embarcados.

Funciona com✓Claude Code~Codex CLI~Cursor✓Antigravity
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/analyze-elf

Installed? Explore more Pesquisa e Análise de Dados skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

PARE. LEIA ESTE SKILL.MD COMPLETO ANTES DE CHAMAR QUALQUER ENDPOINT.

O que analyze-elf faz?

Faça engenharia reversa de recursos de binários ELF compilados. Não é um desmontador — é um extrator de recursos que responde "o que este binário faz?"

Quando Usar

  • Entender o que uma ferramenta CLI compilada faz (Bun SEA, Go, Rust, C/C++)
  • Extrair comandos CLI, flags e texto de ajuda
  • Recuperar máquinas de estado, esquemas de protocolo e tipos de evento
  • Mapear métodos JSON-RPC e modelos de dados Zod
  • Produzir um relatório de acusação com diagramas Mermaid

Início Rápido

# Comando principal — extrair recursos, gerar relatório de acusação
.pi/skills/analyze-elf/run.sh features /caminho/para/binario --goal "entender o sistema de missão"

# Com análise AST via /treesitter (mais lento, mais profundo)
.pi/skills/analyze-elf/run.sh features /caminho/para/binario --ast --goal "encontrar todos os métodos RPC"

# Saída JSON para uso programático
.pi/skills/analyze-elf/run.sh features /caminho/para/binario --output-format json

# Informações ELF de baixo nível (cabeçalhos, símbolos, detecção de runtime)
.pi/skills/analyze-elf/run.sh elf /caminho/para/binario

# Extração de strings com regex
.pi/skills/analyze-elf/run.sh strings /caminho/para/binario --pattern "missão|worker"

Comandos

ComandoDescrição
featuresPrincipal. Extrair recursos → gerar relatório de acusação com diagramas Mermaid
elfBaixo nível: cabeçalhos, seções, símbolos, detecção de runtime
stringsExtração de strings com filtro regex

O que features Extrai

CategoriaMétodoExemplo
Comandos CLICorrespondência de padrões de texto de ajudaexec, daemon, mcp
Máquinas de estadoPadrões de atribuição de enum (M.State="valor")orchestrator_turn, paused
Tipos de eventoPadrões KH.literal("nome_tipo")mission_accepted, worker_completed
Métodos JSON-RPCPadrões method: KH.literal("nome")droid.session_notification
Esquemas ZodExtração de campos KH.object({...})Feature, WorkerHandoff, State
Pacotes npm"name": "pkg" em package.json empacotado@grpc/grpc-js
Rotas de APILiterais de caminho /api/ e /v1//api/auth/login
Classes/funçõesAST via /treesitter (com flag --ast)MissionRunner, spawnWorker

Composição

/treesitter (Análise AST)

Quando --ast é passado, a habilidade:

  1. Extrai strings fonte JS de .rodata
  2. Filtra linhas com padrões JS (function/class/import/Zod)
  3. Envia chunks através de /treesitter parse --language javascript
  4. Extrai classes, funções e assinaturas de método

/create-walkthrough (Gerado automaticamente)

O comando features produz um relatório de acusação com:

  • Árvore de comandos CLI Mermaid
  • Diagramas de máquina de estado Mermaid
  • Taxonomia de tipos de evento Mermaid
  • Tabelas de esquema com tipos de campo
  • Avaliação de risco ("O Que Poderia Dar Errado")

/create-figure

Diagramas de dependência e módulo no formato DOT estão disponíveis via o comando elf para renderização através de /create-figure.

Dependências

  • pyelftools — análise estruturada de ELF
  • httpx — chamadas de API /scillm
  • typer — CLI
  • loguru — logging
  • Sistema: binutils (readelf, nm, strings)

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

grahama1970/acceptance-contract

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.

grahama1970/agent-ecosystem

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.

grahama1970/agentic-evals

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.

grahama1970/agent-inbox

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.

grahama1970/agents-registry

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.

grahama1970/agent-status

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.

grahama1970/align

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.

grahama1970/analytics

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

grahama1970/analyze-chatterbox-emotions

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.

grahama1970/animation-vocabulary

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.

grahama1970/anonymize-data

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.

grahama1970/anvil

Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.

grahama1970/apple-design

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.

grahama1970/argue

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

grahama1970/arxiv

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

grahama1970/ask

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.

grahama1970/assess

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).

grahama1970/assistant

Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

grahama1970/assistant-lab

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.

grahama1970/batch-quality

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.

Habilidades Relacionadas