SKILLEMALL.ai
GitHub ↗ RU Sign in

BD dev-factory

Automated software development agent using ChatDev 2.0 and GLM-5. Discovers topics from GitHub Trending, CVE databases, and security news → generates code with 7-agent ChatDev team → tests automatically → publishes to GitHub. Self-correction loop (error → fix → retry, max 3 times). Use when you want to automate development, create security tools, or generate DevOps utilities. Triggers: "자동 개발", "도구 생성", "builder agent", "chatdev".

ClawHub Agent Skills author: rebugui v1.1.1 MIT-0 50 files body ≈ 1 519 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorGitHubAI 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
77/100
safety, quality, tests
Safety 60%
77
Quality 40%
77
Run on models
none yet
Process rating
D
39/100
Unfinished process
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
This is a copy of a skill from another catalog; the rating counts the canonical one: dev-factory (ClawHub)

What is at stake

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

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 15

    ✓ No critical or high findings

    Medium and low: 15
    • medium Dangerous commands cmd-persistence check_status.py:160
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      print("  launchctl unload ~/Library/LaunchAgents/com.openclaw.builder-*.plist")
      code literal
    • medium Dangerous commands cmd-persistence check_status.py:163
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      print("  launchctl load ~/Library/LaunchAgents/com.openclaw.builder-*.plist")
      code literal
    • low Risky intent intent-offensive-security DISCOVERY_REPORT.md:41
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      2. **Security Tool: Ransomware Detector** (Security News)
    • low Risky intent intent-offensive-security discovery-integration.md:142
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      return "Ransomware Detector"
      detector
    • low Risky intent intent-offensive-security IMPROVEMENT_ANALYSIS.md:99
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      keywords = ['ransomware', 'vulnerability', 'malware', 'phishing']
      quoted
    • low Risky intent intent-offensive-security LIVE_EXECUTION_REPORT.md:48
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      2. Security Tool: Ransomware Detector (0.62점)
    • low Risky intent intent-offensive-security LIVE_EXECUTION_REPORT.md:125
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### 2. Security Tool: Ransomware Detector
    • low Risky intent intent-offensive-security LIVE_EXECUTION_REPORT.md:129
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      "title": "Security Tool: Ransomware Detector",
      detector
    • low Risky intent intent-offensive-security LIVE_EXECUTION_REPORT.md:139
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - Severity: 0.80 (ransomware)
      detector
    • low Risky intent intent-offensive-security OPERATION_START.md:84
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ✅ Security Tool: Ransomware Detector
    • low Risky intent intent-offensive-security OPERATION_START.md:182
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ransomware
    • low Dangerous commands cmd-cron-mention OPERATION_START.md:249
      Mentions editing / listing crontab (documentation of a security skill)
      1. ✅ Cron job 수동 설정 (crontab -e)
      security skill
    • low Risky intent intent-offensive-security PRODUCTION_DEPLOYMENT.md:85
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      "keywords": ["ransomware", "vulnerability", "malware", "phishing"],
      quoted
    • low Exfiltration read-dotenv SKILL.md:103
      Reads a .env file (documentation of a security skill)
      cp .env.example .env
      security skill
    • low Risky intent intent-offensive-security TEST_RESULTS.md:48
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      2. **Security Tool: Ransomware Detector** (점수: 0.62)
      fixture

    Files scanned: 50. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Automated software development agent using ChatDev 2.0 and GLM-5. … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

    Process rating: all ten parameters 39/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (dev-factory) differs from the folder (dev-factory-repo)
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 33 steps
    • 100Execution cost. Instruction body is 1519 tokens
    • low 14 top-level sections: this looks like several domains in one skill

    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
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 2 example trigger phrases
    • +3Description length 434: enough signal without eating the budget
    • +4Structure: 38 headings
    • +3Step-by-step instructions: 33 items
    • +4Has examples (18 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

    External checks

    ClawHub: suspicious
    This skill is a powerful automation tool that can run local commands, send code to external AI/cloud services, and update GitHub or Notion with limited approval controls.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026