SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ayao-workflow-agent

Multi-agent workflow orchestrator for coding, writing, analysis, and image tasks via tmux-driven Claude Code and Codex agents. Use when: (1) user requests a feature/fix that should be delegated to coding agents, (2) managing parallel coding tasks across front-end and back-end, (3) monitoring active agent sessions and coordinating review, (4) user says 'start task', 'assign to agents', 'swarm mode', or references the ayao-workflow-agent playbook. NOT for: simple one-liner edits (just edit directly), reading code (use read tool), or single quick questions about code.

ClawHub Agent Skills author: ayao99315 v1.7.0 MIT-0 39 files · 18 scripts body ≈ 7 044 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 44/100 · Will not run — References files that are not bundled: scripts/*.sh

ProcedureAI and agentsSoftware developmenttype 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
84/100
safety, quality, tests
Safety 60%
92
Quality 40%
73
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: scripts/*.sh
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Broad scope meta-agent-memory-dump memory/2026-03-22.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    memory/2026-03-22.md
  • low Exfiltration exfil-secret-in-url scripts/backends/nano-banana.sh:56
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    "https://generativelanguage.googleapis.com/v1beta/models/imag…ict?key=…" \
    placeholder
  • low Obfuscation obf-base64-blob scripts/backends/stub.sh:43
    Long base64-looking blob (quoted — discussed, not commanded)
    "iVBO…mNk+M9QD…ggg=="
    quoted
  • low Dangerous commands cmd-background-process scripts/dispatch.sh:335
    Starts a background / autostarted process
    disown "$HEARTBEAT_PID"

Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7044 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/*.sh

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: scripts/*.sh
  • 0Tools and files. 1 referenced file(s) missing: scripts/*.sh
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 52 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 7044 tokens
  • 85Steps. 124 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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
  • +3Output format is not stated: the model decides each time
  • -31 of 15 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 571: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 124 items
  • +4Has examples (26 code blocks)
  • +4Reference files are cited in the instructions (7 of 14)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
This is a real multi-agent coding workflow, but it grants agents broad unsandboxed authority to auto-commit, push, install persistent hooks, and deploy, so it needs careful review before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026