SKILLEMALL.ai
GitHub ↗ RU Sign in

BC ruflo

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 coordination, (3) use ruflo's 314+ MCP tools for memory, routing, hooks, sub-agents, or workflows, (4) check ruflo status/version/doctor health, or (5) discover which of ruflo's 30+ plugins fits their task.

The skillemall take

Ruflo promises to orchestrate AI coder swarms across Claude Code, Cursor, Copilot, and a dozen more platforms through a single interface. Claims 314 MCP tools for routing, memory, and multi-agent chains. In reality: 80 files and 5 scripts, but install.sh fails immediately with a missing Claude Code CLI error. Other scripts stay quiet within their directories. Code quality scores 84, but process metrics hit 52—a sign the architecture works better on paper than in practice. One medium-level finding, no critical issues.

Install if you're ready to debug: multi-agent workflow logic is there, but tooling depends on Claude Code being pre-installed. Useful for prototyping complex orchestration, but verify your environment first before production use.

ruvnet/claude-flow Agent Skills author: ruvnet MIT 80 files · 5 scripts body ≈ 853 tokens Open the sourcegithub.com↗ analyzed 4 h ago

Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more).

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
99
Quality 40%
84
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security .claude/agents/consensus/security-manager.md:553
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Penetration Testing Framework

    Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 52/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (ruflo) differs from the folder (claude-flow)
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 21 steps
    • 100Execution cost. Instruction body is 853 tokens

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 455: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 21 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    In the sandbox The scripts kept to themselves

    The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

    Запущено 5 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

    Из них 3 не дошли до работы, и об их поведении мы ничего не узнали.

    .claude-plugin/scripts/install.shне запустился: ✗ Claude Code CLI not found. Please install it first:
    .claude-plugin/scripts/ruflo-hook.cjsничего за пределами своей папки
    .claude-plugin/scripts/ruflo-hook.shничего за пределами своей папки
    .claude-plugin/scripts/uninstall.shне запустился: ⚠ This will remove Claude Flow commands, agents, and configuration.
    .claude-plugin/scripts/verify.shне запустился: ✗ Claude Code CLI not found

    4 Oct 2026