SKILLEMALL.ai
GitHub ↗ RU Sign in

CD web-search-plus

Unified multi-provider web search and URL extraction skill with intelligent auto-routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, You.com, SearXNG, SerpBase, and Keenable. Unified freshness/news filters, locale-aware defaults, spam/mirror filtering, and adaptive routing. Sends queries/URLs to the configured third-party provider APIs and caches results plus provider failure/performance history locally under .cache (configurable, can be disabled).

ClawHub Agent Skills author: Robby v4.0.0 MIT-0 17 files · 10 scripts body ≈ 3 283 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Unified multi-provider web search and URL extraction skill with intelligent auto-routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl…

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureResearchtype 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
83/100
safety, quality, tests
Safety 60%
98
Quality 40%
60
Run on models
none yet
Process rating
D
48/100
Unfinished process
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

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Exfiltration read-dotenv README.md:94
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv SKILL.md:69
    Reads a .env file
    cp .env.example .env

Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Flow map in block collection must be sufficiently indented and end with a } at line 5, column 1487: …health.json, and provider_stats.json (adaptive routing performance samples)"}}} ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 48/100

  • 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
  • 30Running it twice. 4 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 100Steps. 61 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3283 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill

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
  • -37 of 10 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 470: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 61 items
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

In the sandbox The scripts kept to themselves

The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

Запущено 10 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

Из них 3 не дошли до работы, и об их поведении мы ничего не узнали.

scripts/docker_detect.pyничего за пределами своей папки
scripts/extract.pyне запустился: "error": "No URLs provided",
scripts/provider_registry.pyничего за пределами своей папки
scripts/provider_stats.pyничего за пределами своей папки
scripts/quality.pyничего за пределами своей папки
scripts/research.pyничего за пределами своей папки
scripts/search_locale.pyничего за пределами своей папки
scripts/search.pyне запустился: search.py: error: --query is required (unless using --similar-url with Exa)
scripts/setup.pyне запустился: EOFError: EOF when reading a line
scripts/url_security.pyничего за пределами своей папки

19 Sept 2026

External checks

ClawHub: suspicious
The skill is a legitimate web search tool, but it needs review because its setup can save API keys locally despite the main skill text saying keys are not persisted.
LLM: suspicious (medium) · VirusTotal: · 31 Aug 2026