SKILLEMALL.ai
GitHub ↗ RU Sign in

BB epic-ai-swarm-orchestration

Production playbook and portable runtime for parallel AI coding swarms using Codex, Gemini, DeepSeek, and optional Claude. Use when orchestrating multi-agent coding work, packaging/installing the swarm on another OpenClaw host, spawning parallel builders with review/integration loops, managing duty-table model rotation, or diagnosing swarm runtime health. Triggers on phrases like "run the swarm", "spawn agents", "AI swarm", "multi-agent build", "package the swarm", "install swarm", "duty table", "model rotation", "parallel coding agents".

ClawHub Agent Skills author: linkbag v3.3.1 MIT-0 41 files · 26 scripts body ≈ 1 378 tokens Open the sourceclawhub.ai↗ analyzed 10 d ago

Production playbook and portable runtime for parallel AI coding swarms using Codex, Gemini, DeepSeek, and optional Claude.

As a process B 66/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting

ProcedureSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
94
Quality 40%
90
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Broad scope meta-agent-memory-dump roles/swarm-lead/HEARTBEAT.md
      Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
      roles/swarm-lead/HEARTBEAT.md
    • low Dangerous commands cmd-background-process scripts/spawn-batch.sh:223
      Starts a background / autostarted process
      nohup "$QUEUE_WATCHER" "$QUEUE_FILE" >> "$QUEUE_LOG" 2>&1 &

    Files scanned: 41. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 78): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 66/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 3 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 47 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1378 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -311 of 22 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 9 example trigger phrases
    • +3Description length 544: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 47 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: suspicious
    This is a real multi-agent coding swarm tool, but it gives autonomous agents broad execution, network, git, and persistence authority with several unsafe defaults.
    LLM: suspicious (high) · VirusTotal: · 16 Sept 2026