SKILLEMALL.ai
GitHub ↗ RU Sign in

AC unified-search

Unified web search + deep research suite. Default ordinary /unified_search queries route to deep search-layer mode (Exa + Tavily + Grok); the legacy merged three-engine search (Tavily + Exa + Google) remains available via --legacy or the legacy subcommand. Use when user asks for “综合搜索”, “三搜索”, “三引擎”, “/unified_search”, deep search, issue/PR thread tracing, content extraction, or URL→Markdown conversion.

ClawHub Agent Skills author: ccmxigua v0.1.0 MIT-0 30 files · 7 scripts body ≈ 1 716 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Unified web search + deep research suite.

As a process C 55/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

ProcedureGitHubSoftware developmenttype 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
91/100
safety, quality, tests
Safety 60%
93
Quality 40%
88
Run on models
none yet
Process rating
C
55/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Exfiltration net-redirectable-api-key scripts/load-search-env.sh:66
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Exfiltration read-dotenv vendor/openclaw-search-skills/docs/README_EN.md:276
      Reads a .env file
      cp mineru-extract/.env.example mineru-extract/.env
    • low Exfiltration read-dotenv vendor/openclaw-search-skills/README.md:260
      Reads a .env file
      cp mineru-extract/.env.example mineru-extract/.env

    Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 11, 25, 32, 38, 98, 104): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 55/100

    • 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
    • 40Consistency. Frontmatter name (unified-search) differs from the folder (unified-search-suite)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 49 steps
    • 100Execution cost. Instruction body is 1716 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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • -37 of 8 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 406: enough signal without eating the budget
    • +4Structure: 22 headings
    • +3Step-by-step instructions: 49 items
    • +3Output format is stated explicitly
    • +4Has examples (18 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    This appears to be a real search and extraction tool, but it needs review because it can silently use local GitHub credentials and send queries, snippets, URLs, and documents to several external services.
    LLM: suspicious (high) · VirusTotal: · 5 Jun 2026