SKILLEMALL.ai
GitHub ↗ RU Sign in

CC sa-pro-workbench-international

【Solution Architect & Presales Consultant Super Workbench — International Edition】 — Full-stack automation for Solution Architects, Presales Consultants, and Enterprise Architects worldwide. One Skill, replacing 80% of repetitive solution team labor.

ClawHub Agent Skills author: yinjianheng v1.2.0-intl MIT-0 16 files body ≈ 25 956 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

【Solution Architect & Presales Consultant Super Workbench — International Edition】 — Full-stack automation for Solution Architects, Presales Consultants, and…

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAWSGoogle CloudInfrastructureResearchWriting and documentstype 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
C
79/100
safety, quality, tests
Safety 60%
94
Quality 40%
57
Run on models
none yet
Process rating
C
56/100
Has gaps
Inputs and preconditions w 11
0
Execution cost w 6
10
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Risky intent intent-offensive-security SKILL.md:1047
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    ← Guardrails (Prompt Injection / Jailbreak Defense / Red Teaming) + AI Cost Governance (token/inference accounting) + Observability (vertical) →
    detector
  • low Risky intent intent-offensive-security SKILL.md:1072
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Red Teaming**: adversarial samples, jailbreak attempts, data-leak testing as pre-launch evaluation
  • low Risky intent intent-offensive-security SKILL.md:1244
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [ ] Red team review completed (independent reviewer simulates evaluator perspective)
  • low Risky intent intent-offensive-security SKILL.md:1652
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Digital Operational Resilience Testing** | Regular testing including TLPT (Threat-Led Penetration Testing) for critical entities | Proposals for financial clients must include resilience testing p
  • low Risky intent intent-offensive-security templates/ai-adr-template.md:39
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Guardrails & evaluation: {Prompt injection defense / jailbreak defense / red teaming / RAGAS threshold}
    detector
  • low Risky intent intent-offensive-security templates/ai-adr-template.md:63
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Pre-launch red team result**: {pass / open items}

Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 25956 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "language"
  • note frontmatter-key unknown frontmatter key "contact"
  • note edit-residue the text marks something as outdated (lines 1336, 1369, 1414, 1471): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 56/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 25956 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 60Steps. 184 steps, 11 vague phrases
  • 65Failures and branches. 3 branches
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 24 top-level sections: this looks like several domains in one skill
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model

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
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +3Description length 250: enough signal without eating the budget
  • +4Structure: 120 headings
  • +3Step-by-step instructions: 184 items
  • +4Has examples (22 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.

External checks

ClawHub: clean
This appears to be a presales/document-template skill with some overbroad trigger wording and legal-template caveats, but no evidence of malicious behavior.
LLM: benign (medium) · VirusTotal: · 10 Jul 2026