SKILLEMALL.ai
GitHub ↗ RU Sign in

BC ai-company-unified

Unified AI Company skill consolidating 16 department skills into one. Provides complete governance, finance, technology, security, legal, people, marketing, quality, intelligence, information, and translation capabilities for all-AI-employee technology companies. Includes 10 core code templates, 3 prompt frameworks (CRISPE/3WEH/Five-Element), L1-L6 harness engineering, CI/CD pipeline, ADR process, AIGC compliance, VirusTotal/ClawHub security verification, and progressive disclosure architecture. Use when any AI-Company department function is needed — this skill contains all of them.

ClawHub Agent Skills author: JohnSmithfan v1.0.4 MIT-0 26 files body ≈ 1 241 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
83/100
safety, quality, tests
Safety 60%
83
Quality 40%
82
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
20
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 · 13

    ✓ No critical or high findings

    Medium and low: 13
    • medium Broad scope meta-agent-memory-dump references/memory.md
      Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
      references/memory.md
    • low Secrets in code secret-high-entropy-token references/data-integration.md:1454
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "data_point_id": "quot…530",
      quoted
    • low Secrets in code secret-password-literal references/data-integration.md:2090
      Hard-coded password / key literal (may be an example)
      const apiKey = 'sk_l…xyz';
    • low Risky intent intent-offensive-security references/departments/intelligence.md:102
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | E - Privilege Escalation | | | | | |
    • low Risky intent intent-offensive-security references/departments/intelligence.md:170
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### SOP-A03: Red Team Analysis (Senior)
    • low Risky intent intent-offensive-security references/departments/intelligence.md:204
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Mirror Imaging | Adversary perspective check? | Red Team review |
    • low Risky intent intent-offensive-security references/departments/intelligence.md:843
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Analysis | Intelligence Assessment | Core assessment, ACH, Red Team, threat forecasting, bias checklist, reporting |
    • low Risky intent intent-offensive-security references/departments/platform-and-infrastructure.md:730
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | No admin/root requests | No privilege escalation |
    • low Risky intent intent-offensive-security references/departments/quality-and-operations.md:130
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Security Testing | Penetration testing | Quarterly |
    • low Secrets in code secret-password-literal references/integrations.md:490
      Hard-coded password / key literal (may be an example) (placeholder value)
      api_key = "sk-1…def"
      placeholder
    • low Risky intent intent-offensive-security references/memory.md:904
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Privilege escalation pattern | L1-L2 agent accessing L4+ memory | Immediate CISO alert |
    • low Risky intent intent-offensive-security references/memory.md:1566
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Access control accuracy | 100% | Penetration testing + audit review |
    • low Risky intent intent-offensive-security references/method-patterns.md:110
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Security: no dynamic code execution, no remote loading, no privilege escalation

    Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "slug"
    • note frontmatter-key unknown frontmatter key "dependencies"
    • note frontmatter-key unknown frontmatter key "triggers"
    • note frontmatter-key unknown frontmatter key "interface"
    • note frontmatter-key unknown frontmatter key "permissions"
    • note frontmatter-key unknown frontmatter key "quality"

    Process rating: all ten parameters 63/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 40Result and completion. Does not say what the result is
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. No external tools needed
    • 100Steps. 8 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1241 tokens
    • 100Progress reporting. Reports progress

    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
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • +2Single-language instructions
    • +3Description length 589: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 8 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (6 of 6)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: suspicious
    The skill is a broad enterprise-operations package with disclosed high-impact capabilities, but it also contains under-scoped automatic writes, silent setup instructions, auto-update behavior, and broad triggers that warrant manual review before installation.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026