Guide for managing the Agent Registry - database-backed agent configuration system. Use when asked to "configure agents", "manage skills", "set tool permissions", "create — from…
Guide for managing the Agent Registry - database-backed agent configuration system. Use when asked to "configure agents", "manage skills", "set tool permissions", "create — from…
Real-time messaging across OpenClaw instances (channels, DMs, threads, reactions, search).
Create curated digests of agent conversations (e.g., Moltbook) by collecting posts, clustering themes, ranking signal, and producing a concise digest with takeaways,…
Run release agents that draft the changelog, scan risk, verify the candidate, and gate publish behind a go/no-go check.
Agent Reliability Patterns: retry with exponential backoff and jitter, timeout hierarchies (tool < agent < workflow), fallback chains, circuit breaker for agent calls, cost…
Agent reliability anti-patterns — retrying non-retryable errors, fixed sleep vs exponential backoff with jitter, single timeout for all call stack levels, aggressive circuit…
A two-phase repair skill that analyzes errors and suggests fixes before executing repairs. Phase one: user describes error, agent analyzes and proposes solution.
A two-phase repair skill that analyzes errors and suggests fixes before executing repairs. Phase one: user describes error, agent analyzes and proposes solution.
Extract and display the final message from a Claude agent JSONL file. Use when the user wants to see an agent report, view agent output, extract agent results, check what an agent…
Docs-only guide to Agent Republic. No bundled scripts, just clear workflows and HTTP examples so agents can register, manage bots, and monitor onboarding health after asking their…
Enhanced Request Router and gatekeeper (Layer 3 in the GAS Autonomous Agent Hierarchy). Evaluates incoming requests against the project blueprint before creating work orders.
Set up the restore-context hook so skills can survive /clear and /compact. Detects .claude/ vs .agents/ layout automatically.
Agrégation et synthèse des résultats de multiples sous-agents en un résultat cohérent. Se déclenche avec "agréger résultats", "fusionner résultats", "combiner outputs", " — from…
Expert en CV et recherche d'emploi (ATS optimization, action verbs, formatting, cover letters, LinkedIn)
Use when a paused, scheduled, interrupted, failed, or checkpointed AI agent may resume from saved state, pending tool calls, approvals, traces, or memory.
Expert en technologies retail avancées (omnichannel, inventory AI, dynamic pricing, cashierless, DZ context)
Use when an agent workflow needs retry limits, replanning limits, stop conditions, escalation triggers, and irreversible-action locks.
Stratégies de retry intelligentes pour sous-agents qui échouent — backoff, fallback, alternatives et recovery.
Generate evidence-linked Guided Review artifacts and deterministic local Agent benchmark summaries. Use when reviewing Agent-produced diffs by intent, recording structured…
Maintain a living register of business risks with agents that surface new ones, track mitigations, and force stale entries back to a decision.
Write role cards that pin each agent to one charter with declared inputs, outputs, refusal rules, and non-overlapping scope.
Join an Agent Room from Codex using a temporary room authorization code. Use when the user asks Codex to join/connect to an agent_room or Agent Room room without manually starting…
When the user has a task and many skills/subagents installed and wants the BEST one chosen automatically.
Decide which model (Haiku/Sonnet/Opus) and effort level each subagent gets, when to cascade cheap-first behind a verifier, and how to run improvement loops safely…
contemplative-agent をバックグラウンドで起動する。引数でセッション時間とバックエンド (ollama / cloud / mlx) を指定（例: /agent-run 4時間, /agent-run 30分 cloud openai, /agent-run 30分 mlx）
Review agent run traces, eval summaries, tool logs, and handoff evidence before accepting a workflow result or self-improvement proposal.
Run section orchestrators to coordinate multi-component workflows. Use when starting work on a section.
Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.
Show availability and typed readiness for the unified collaboration routes. Use when the user says "agent runtime status," "check agent runtimes," "list agent versions," "is a…
Legacy systems domain expert and modernization guide. Use when the codebase contains COBOL, Mainframe JCL, RPG, legacy Java (J2EE/EJB), legacy .NET (WCF/WebForms), or any system…
Operate E2B agent sandboxes using the CLI. Use when user needs to run code in isolation, test packages, execute commands safely, or work with binary files in a sandbox…
Create, read, validate, and clear edit-scope locks through the nils-cli `agent-scope-lock` command.
Generate semantic + keyword match score. Compares resume content against job description to calculate a fit score and identify gaps.
Code archaeologist agent for reading and documenting existing codebases. Use when you want to talk to Scout, onboard onto a new project, or need someone to reverse-engineer a…
Expert search specialist mastering advanced information retrieval, query optimization, and knowledge discovery.
Expert search specialist mastering advanced information retrieval, query optimization, and knowledge discovery.
Guidance for selecting appropriate AI model (sonnet vs haiku) based on task complexity, reasoning requirements, and performance needs.
Guidance for selecting appropriate AI model (sonnet vs haiku) based on task complexity, reasoning requirements, and performance needs.
Systematic framework for selecting the optimal specialized agent for any task. Use when delegating to subagents via the Task tool to ensure the most appropriate specialist is…
AI agent self-correction mechanisms: error detection, validation loops, recovery strategies, confidence scoring, and iterative refinement
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per…
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure…
Diagnose recurring communication failures in supplied or available agent conversations and stage minimal guidance corrections for approval. Use only when explicitly requested.
Workflow for agent self-improvement via isolated execution, evaluation, and process refinement. Use when evaluating historical bugs or self-correcting skills.
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
The operational circuit breaker for this agent. Enforces budget limits locally. **Sign up at agentsentinel.dev for real-time dashboards and human approval workflows.**
Use when an agent acts through a human browser session, broad user token, shared credential, or service account.
Use when configuring Claude Code or Codex sessions, hooks, skills, MCP servers, durable instructions, agent runners, or future-session defaults.
Maintain project continuity across coding-agent sessions (Claude Code and any AGENTS.md-style harness) using a markdown session briefing that pairs with the project's agent…
Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs +…
Manage long agent sessions with checkpoints, context resets, and clear task boundaries so quality does not decay. Use when working with an agent over an extended piece of work.
Piloter et SUPERVISER d'autres agents de code (claude-code, hermes, …) via le daemon agentproto depuis une session cowork : lancer des sessions, babysitter un agent débutant…
Check and configure outfitter marketplaces and plugins. Use when setting up a new project, checking plugin configuration, or when "setup outfitter", "configure plugins", or…
Offboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memory, revoke every credential and access grant, and write the…
Use when the user asks to update shared memory, initialize multi-agent memory, summarize decisions so far, identify open questions, or prepare a fresh session primer.
Diagnose, inspect, install, update, or remove the complete Codex Rig user-agent shim roster. Use when the user invokes agent-shims with exactly one action—doctor, status, install,…
Register with Signet to receive a trust score and API key. Look up agent trust scores, report transactions, and manage agent configuration.
Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.