SKILLEMALL.ai
GitHub ↗ RU Sign in

BB ifq-app-builder

Use this OpenClaw / ClawHub skill when the user wants to turn three ordinary sentences into a verified build-ready prompt bundle for a real app: PC desktop, macOS, Windows, iOS, Android, HarmonyOS, WeChat MiniProgram, self-hosted local web, PWA, or CLI. It routes to one of 12 platform modes, forks a prompt template, fills acceptance / packaging / security / IFQ ambient requirements, and verifies the bundle without installing platform SDKs. Do not use for visual-only design deliverables, SEO pages, backend-only services, or pure copy edits.

Not recommendedcritical or high security findings
ClawHub Hermes author: peixl v1.0.1 MIT-0 52 files body ≈ 1 569 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

IntegrationAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
81
Quality 40%
80
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

  • high Secrets in code secret-private-key scripts/lib/bundle-scanner.mjs:27
    Private key material (key header without key body)
    ['private-key-pem', /-----BEGIN (?:RSA |DSA |EC |OPENSSH )?PRIVATE KEY-----|-----BEGIN PGP PRIVATE KEY BLOCK-----/],
    header only
Medium and low: 1
  • low Concealment en-hide-from-user README.en.md:5
    Instruction to hide actions from the user (negated — the text forbids it)
    A ClawHub-safe OpenClaw skill: **three sentences in, one verified build-ready app prompt bundle out**. It does not silently install SDKs or pretend store submission has happened. It turns a short app
    negated

Files scanned: 51. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 545 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "entrypoint"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "repository"

Process rating: all ten parameters 70/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 60Failures and branches. 2 branches
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 42 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100When it triggers. States when to use and when not to
  • 100Execution cost. Instruction body is 1569 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • 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
  • +4No input/output examples
  • -36 of 6 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 545: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 42 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (10 of 12)
  • +1License stated

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

External checks

ClawHub: clean
This skill is a prompt-bundle generator for app projects, and its disclosed file, shell, and downstream build behavior is coherent with that purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026