SKILLEMALL.ai
GitHub ↗ RU Sign in

BC develop-and-deploy-web-app

Build, run, and share a simple full-stack web application with a TypeScript Express backend, React frontend, and SQLite database. Use when a user wants a working web app or explicitly asks for a LiteApp / 轻应用 scaffolded in the current workspace, started locally, and exposed through a public URL for demos, testing, or review.

ClawHub Agent Skills author: 宁伟 v1.0.6 MIT-0 28 files body ≈ 2 143 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorSoftware developmentInfrastructuretype 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
85/100
safety, quality, tests
Safety 60%
88
Quality 40%
80
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Exfiltration net-credential-use references/stack.md:80
      Credential used in a network call (verify the destination is the intended service)
      4. Confirm the page loads locally through `/${token}/`.
    • medium Exfiltration net-credential-use references/stack.md:81
      Credential used in a network call (verify the destination is the intended service)
      5. Confirm the API responds locally through `/${token}/api/...`.
    • low Risky intent intent-offensive-security SKILL.md:44
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Keep deployment automation local and explicit. Do not add scripts that fetch remote code, manage secrets, alter unrelated system state, or attempt privilege escalation.
    • low Concealment en-hide-from-user SKILL.md:45
      Instruction to hide actions from the user (negated — the text forbids it)
      - Support restart recovery through registry-driven restore scripts, but do not silently install OS startup hooks or scheduled tasks.
      negated

    Files scanned: 28. 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 51/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
    • 70Failures and branches. 7 branches
    • 85Steps. 90 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2143 tokens
    • 100Running it twice. Mutating operations check current state
    • low The response is described with custom markup (4 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -5TODO / placeholder text left in the skill
    • -36 of 18 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 326: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 90 items
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: clean
    This skill is a coherent web-app builder that intentionally installs dependencies, starts local servers, and exposes a public demo URL, so users should avoid sensitive data unless they add protection.
    LLM: benign (high) · VirusTotal: · 29 May 2026