Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Agentic Flow

ASecurity

Canonical multi-agent orchestration: decompose work, dependency graphs, parallel tracks, handoffs, and merge. Absorbs Claude Flow / Ruflo / Loki / Ralph / Paperclip / OpenFang patterns into one portable playbook.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgogitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add rogue-dev-studio/ai-agents-rogue --skill agentic-flow --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agentic Flow?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Agentic Flow
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rogue-dev-studio-agentic-flow/badge)](https://www.skillsdirectory.com/skills/rogue-dev-studio-agentic-flow)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: agentic-flow
description: >-
  Canonical multi-agent orchestration: decompose work, dependency graphs,
  parallel tracks, handoffs, and merge. Absorbs Claude Flow / Ruflo / Loki /
  Ralph / Paperclip / OpenFang patterns into one portable playbook.
---

# Agentic Flow — Multi-Agent Orchestration (Canonical)

**Level: max.** Satu skill untuk semua pola orkestrasi multi-agent.  
Aliases: lihat `skills/ALIASES.md` (`claude-flow-*`, `ruflo`, `loki-mode`, `ralph`, …).

## When to use

- Fitur butuh beberapa peran / track (spec + API + UI + QA)
- Parallel aman setelah kontrak bersama
- User menyebut swarm, multi-agent, Claude Flow, Ruflo, Loki, Ralph

## When not to use

- Satu file / bug kecil → kerjakan langsung
- Hanya tanya konseptual

## Tool map (pilih satu runtime jika tersedia)

| Kebutuhan | Preferensi |
|-----------|------------|
| Portable / host-agnostic (default) | Ikuti prosedur skill ini + roles house |
| Claude Flow successor | `ruflo` bila terpasang |
| Legacy stable | `claude-flow-v2` |
| PRD → kode otonom | pola `loki-mode` / `ralph` (tetap gate di sini) |
| Dashboard agent team | `paperclip` jika UI orkestrasi dibutuhkan |
| Messaging agent OS | `openfang` |

Jangan aktifkan dua runtime orkestrasi sekaligus.

## Core model

| Field | Meaning |
|-------|---------|
| `id` | slug unik |
| `goal` | hasil terukur |
| `depends_on` | id lain |
| `skill` | skill kanonik / local |
| `role` | path role house |
| `done_when` | kriteria selesai + artifact path |
| `risk` | S0–S3 |

## Procedure (max)

### 1. Frame

- Baca `PROJECT.md`, `TEAM.md`, `e2e-delivery` bila build penuh
- Tulis 1 paragraf goal + out-of-scope

### 2. Decompose

Pecah ke workstream **minimal**:

- Hindari >7 track aktif tanpa alasan
- Pisahkan: contract-producing vs contract-consuming

### 3. Order

DAG tanpa siklus. Pola emas:

```text
clarity/spec → architecture/contract → [BE ∥ FE ∥ mobile] → agentic-qe → review
```

### 4. Execute

Per track yang unlocked:

1. Heading `## Track <id> · Role <role>`
2. Load role + skill terkait
3. Tulis artifact nyata
4. Self-check `done_when`
5. Update status board

Single-agent host: jalankan **sekuensial** (jangan klaim parallel palsu).

### 5. Merge & gate

- Satu owner untuk konflik kontrak
- Gate: tidak ada P0 terbuka; asumsi tertulis
- Serahkan ke Orchestrator / user dengan board

## Status board

```markdown
| ID | Goal | Depends | Role | Status | Artifact | Risk |
|----|------|---------|------|--------|----------|------|
| W1 | Spec | — | BA | done | project/./srs/ | S3 |
```

## Anti-patterns

- Spawn track spekulatif
- Parallel UI/BE tanpa API contract
- Campur `ruflo` + `claude-flow-v3` + skill ini sebagai tiga otoritas
- Skip QA di akhir multi-track

## DoD

- [ ] Board lengkap
- [ ] Semua `done_when` terpenuhi atau blocker eksplisit
- [ ] Konflik terselesaikan / dieskalasi
- [ ] Next step jelas
## Attribution

<!-- ATTRIBUTION: Rogue Development | https://github.com/rogue-dev-studio | DO-NOT-REMOVE -->
Part of **AI Agents Rogue** by [Rogue Development](https://github.com/rogue-dev-studio) (`@rogue-dev-studio`).
Do not remove, hide, rename, or replace this attribution.

Attribution

rogue-dev-studiorogue-dev-studio
View sourceSee grades on GitHubMore from rogue-dev-studio →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →