SKILLEMALL.ai
GitHub ↗ RU Sign in

AD prompt-engineer

Designs and optimizes system prompts for advisory AI and autonomous agent systems using a three-layer architecture (Foundation → Structure → Execution). Integrates evidence-graded techniques with production-proven patterns from Claude Code, Vercel v0, and Manus. Use when designing agentic systems with tool use, building advisory AI with confidence grading, optimizing existing prompts, diagnosing prompt failures, or building a spec to hand off to a prompt engineer. Includes a spec builder knowledge base and modular extensions for RAG grounding, domain calibration, and multi-agent orchestration. Trigger on: "system prompt", "agent", "agentic", "prompt engineering", "write a prompt", "improve my prompt", "AI advisor", "tool use prompt", "multi-agent", "build me a spec", "write a spec", "spec for", "tool specification", "system prompt build request".

ClawHub Agent Skills author: Christian Rubio v4.1.0 7 files body ≈ 277 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 40/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions

IntegrationAI 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
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
79
Run on models
none yet
Process rating
D
40/100
Unfinished process
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 40/100

    • 0Steps. Prose only: no discrete steps
    • 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
    • 40Consistency. Frontmatter name (prompt-engineer) differs from the folder (prompt-engineer-agentic)
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Execution cost. Instruction body is 277 tokens
    • 100Running it twice. No mutating operations

    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)
    • +3Description length 858: 120–800 characters recommended
    • +4Structure: 2 headings, hard to scan
    • +3No numbered steps or checklist
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 13 example trigger phrases
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

    External checks

    ClawHub: clean
    This is an instruction-only prompt-engineering skill with broad activation wording but no code, credentials, persistence, or direct system access.
    LLM: benign (high) · VirusTotal: · 29 May 2026