Menu
SkillsMP a collecté 316 skills depuis ruvnet/ruflo. Ouvrez un skill pour examiner sa source et ses détails.
Copiez ce prompt dans l’assistant IA que vous utilisez.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/ruvnet/ruflo.Affichage de 40 skills collectés sur 316.
Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more). Use this skill when the user wants to (1) install/init ruflo in a project, (2) run multi-agent swarms with hierarchical…
Langue du texte source : anglais
Divide approved work among specialized RuFlo roles and keep task state synchronized.
Langue du texte source : anglais
Turn a reviewed goal into a bounded RuFlo AI team, run, and task plan without external side effects.
Langue du texte source : anglais
Pause, resume, or complete a RuFlo AI team while preserving its tenant-local evidence.
Langue du texte source : anglais
Report a RuFlo AI team's progress, blockers, task ownership, and remaining planned budget.
Langue du texte source : anglais
Store and retrieve approved tenant-local team context with RuVector-backed isolation and provenance.
Langue du texte source : anglais
Review RuFlo team results against acceptance criteria using the evidence bundle.
Langue du texte source : anglais
Sign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project — clone the toolkit, run init, register fixes, regen on each release.
Langue du texte source : anglais
Run `@metaharness/darwin evolve <repo>` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and promote only measured wins. The model is frozen; the harness…
Langue du texte source : anglais
Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript.…
Langue du texte source : anglais
Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the explicit spend opt-in. Requires a metaharness repo checkout…
Langue du texte source : anglais
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
Langue du texte source : anglais
5-dimension harness readiness scorecard from `metaharness score <path>`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd + scaffoldReady. Pure-read; subprocess invocation; degrades gracefully when…
Langue du texte source : anglais
Run `@metaharness/darwin security bench` (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-pass,…
Langue du texte source : anglais
Enterprise-review-grade threat model from `harness threat-model <path>`. Categorizes MCP-surface threats; emits `worst: 'clean'|'low'|'medium'|'high'` + per-threat findings. Pure-read.
Langue du texte source : anglais
Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security…
Langue du texte source : anglais
Coordinate with the open ruflo swarm federation at x.ruv.io (signed Nostr, membership-gated) and ask Seraphina — the swarm queen / primary coordinator — for guidance. Use when: seeing who is online across the internet, reading/assigning work, checking or…
Langue du texte source : anglais
Join and operate a signed cross-host agentbbs federation, and coordinate work claims across nodes. Use when: connecting ruflo agents across machines, sharing status/tasks/results between hosts, propagating work claims across a swarm, or standing up a…
Langue du texte source : anglais
One-time setup — mint a Cognitum Music personal access token and register the cogmusic MCP server with Claude Code
Langue du texte source : anglais
Generate a new song from a creative brief (genre, mood, language, BPM, theme) via the cogmusic MCP create_production tool
Langue du texte source : anglais
Fetch metadata and audio_url for a single production by id
Langue du texte source : anglais
List the account's saved music productions with metadata and audio_url
Langue du texte source : anglais
Run a mastering pass (LUFS loudness normalization + peak limiting) on an existing production
Langue du texte source : anglais
Extract MIDI/score from an existing production
Langue du texte source : anglais
Run 4-stem separation (vocals/drums/bass/other) on an existing production
Langue du texte source : anglais
One-shot chat completion against DeepSeek's `deepseek-chat` model via the OpenAI-compatible /v1/chat/completions endpoint. Reads DEEPSEEK_API_KEY from the environment; degrades gracefully (exit 0 with a JSON status:degraded envelope) when the key is missing…
Langue du texte source : anglais
Reasoning-mode completion against DeepSeek's `deepseek-reasoner` model (R1) via /v1/chat/completions. Surfaces the model's chain-of-thought (`reasoning_content`) separately from the final answer (`content`), so callers can display or discard the CoT without…
Langue du texte source : anglais
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
Langue du texte source : anglais
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
Langue du texte source : anglais
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced…
Langue du texte source : anglais
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
Langue du texte source : anglais
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
Langue du texte source : anglais
Show AGNTCY/SLIM/CASA integration status — whether upstream AGNTCY packages are installed, which transport (local vs SLIM) is active, and whether CASA enforcement is enabled. Use when the user asks "is AGNTCY configured?", "show SLIM/CASA status", or "is…
Langue du texte source : anglais
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
Langue du texte source : anglais
Build or rebuild the ADR index + dependency graph by running scripts/import.mjs (handles v3-style and plugin-style ADR formats; one Bash call vs hundreds of MCP round-trips)
Langue du texte source : anglais
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
Langue du texte source : anglais
Diagnose Ruflo health, then report system, MCP server, and active-agent status without changing the installation
Langue du texte source : anglais
GitHub workflow automation for issues, pull requests, CI, and releases. Use when: repository hosting actions are explicitly requested. Skip when: local git operations are sufficient or publishing is unauthorized.
Langue du texte source : anglais
Performance profiling, benchmarking, and optimization. Use when: slow operations, regressions, memory pressure, release validation. Skip when: early prototyping, documentation, configuration-only changes.
Langue du texte source : anglais
Reconcile the ADR index against a DELETED ADR file or relation line by dropping and rebuilding adr-patterns + adr-edges from scratch (scripts/reindex.mjs). Use when adr-index alone leaves stale rows behind.
Langue du texte source : anglais