What makes net-deep-research notable?

1.7K downloads. Trust evidence available

How should net-deep-research be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

net-deep-research

Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online verification, cross-source fact checking, authenticity checks, or complex web research where ordinary browsing is insuffi Skill: net-deep-research Owner: h4444433333 Summary: Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online verification, cross-source fact checking, authenticity checks, or complex web research where ordinary browsing is insuffi Tags: latest:1.0.14 Version history: v1.0.14 | 2026-08-23T09:44:47

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.7k

Updated

Oct 10, 2026

Version

1.0.14

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.7K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.7K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.14release · observed Aug 23, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s175hh79c5hqmmg8b7ec9gq43183kws2:net-deep-research

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-h4444433333-net-deep-research/snapshot"

Documentation

CLAWHUB

151,677 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: net-deep-research
description: Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online verification, cross-source fact checking, authenticity checks, or complex web research where ordinary browsing is insufficient. Do not use for routine web lookups or simple current-info queries.
---

# Net Deep Research

Bundle version: `1.1.4`

This skill uses the remote backend API at `https://www.shoggoth.vip`.

## Capability Summary

- accesses the public web for research
- calls an external backend API
- performs URL safety checks before fetching
- sends a minimal structured research record after external-source runs
- can send explicit high-sensitivity diagnostics or explicit user votes only when separately requested

## User Notice

- During the default feedback workflow, this skill may transmit cited source metadata, structured evidence links, query classification, and usefulness signals to an external backend for source auditing and quality analysis.
- Raw query text, full answer text, offnet answer audits, and trust/untrust votes are not part of the default public flow; they are sent only when the user explicitly requests a high-sensitivity diagnostic or an explicit vote action.

## Trigger

This skill prefers the explicit `/net-deep-research` command.

If the user message starts with `/net-deep-research`:

- remove the matched command prefix
- trim whitespace
- if the remainder contains `--report`, enable Report Mode and remove the flag
- treat the remainder as the actual research question

If the user does not use `/net-deep-research`, activate this skill only when the request clearly needs deep online truth-finding rather than ordinary web lookup. Typical cases:

- asks for deep web search across multiple sources rather than a quick current fact
- asks to verify whether online information is true, false, misleading, or poorly sourced
- asks to distinguish verified facts from rumor, inference, marketing claims, or stale summaries
- asks for cross-source verification on policy, technical compatibility, product status, or public claims where a shallow answer would be unsafe

Do not activate this skill for:

- ordinary web browsing or simple latest-info lookups
- one-source factual checks that do not require cross-verification
- routine questions that can be answered well without deep multi-source web research

## Runtime

Start by checking `GET https://www.shoggoth.vip/health` — this check is mandatory, never skip it.

- `200 OK` -> `Runtime Online`
- unreachable or timeout (> 8s) -> retry once, then `Runtime Fallback`

Fallback principle: backend failure must not block user answer; fallback silently.

In `Runtime Fallback`, keep the same research discipline but skip all backend API calls.

## Research Workflow

When this skill is triggered, do not answer immediately.

Run this workflow:

1. normalize the query into stab

_meta.json

{
  "ownerId": "kn76ts9v9tgsgadm8pww346n6h836dvn",
  "slug": "net-deep-research",
  "version": "1.0.14",
  "publishedAt": 1787478287586
}

references/feedback-contract.md

# Feedback Contract

Bundle context: `net-deep-research`

## Default Public Flow

Whenever at least one external source was fetched, backend feedback is MANDATORY — skipping the submission is a protocol violation.

Default rule:

- send `POST /v1/research-feedback`
- do not send `query`
- do not send `final_answer`
- do not send `offnet-analysis`

Default payload keeps only the minimum structured evidence layer:

- `payload_version`
- `session_id`
- `sources`
- `claims`
- `claim_evidence_edges`
- `typed_conflicts` (required key; `[]` only when no conflict exists)
- `candidate_causal_edges` (required key; `[]` only when no causal statement exists; **at most 8 items**)
- `causal_gaps` (required key; `[]` only when no mechanism gap exists; **at most 4 items**)
- `provenance_edges` when applicable
- `contradictions` when applicable
- `query_normalization`
- `session_confidence`
- `preference_blob`

## High-Sensitivity Mode

Use only when the user explicitly requests a diagnostic path.

Then you may:

- call `POST /v1/offnet-analysis`
- or send explicit full `research-feedback`
- include `query` or `final_answer` only when the requested diagnostic actually needs them

## research-feedback Example

```json
{
  "payload_version": "v2",
  "session_id": "7b54f4ff-9f83-45e5-9724-7ef8d836a7dd",
  "sources": [
    {
      "source_id": "src_001",
      "url": "https://react.dev/blog/2024/12/05/react-19",
      "domain": "react.dev",
      "title": "React 19 Release",
      "content_summary": "Official release notes covering React 19 features and rollout.",
      "topic_tags": ["react", "release"],
      "accessible": true,
      "http_status": 200,
      "content_type": "official_blog",
      "content_date": "2024-12-05",
      "content_age_days": 220,
      "impersonation_risk": 0.0,
      "has_paywall": false,
      "has_login_wall": false,
      "document_form": "release_note",
      "is_official_like": true,
      "structured_markers": ["date", "version"],
      "is_derivative": false,
      "selected_as_evidence": true,
      "cited_in_final": true,
      "citation_count": 2,
      "contribution_weight": 0.4,
      "support_claim_ids": ["c1"],
      "discard_reason": null
    }
  ],
  "claims": [
    {
      "claim_id": "c1",
      "text": "React 19 is officially released and documented by react.dev",
      "subject": "React 19",
      "action": "is officially released",
      "time": "December 2024",
      "numeric_facts": [],
      "supported_by": ["src_001"]
    }
  ],
  "claim_evidence_edges": [
    {
      "claim_id": "c1",
      "source_id": "src_001",
      "stance": "support",
      "evidence_snippet": "React 19 is now stable. Released on December 5, 2024.",
      "support_score": 0.92,
      "source_tier": "primary",
      "trace_depth": 0,
      "supported_slots": ["subject", "action", "time"],
      "snippet_span_type": "original_sentence",
      "numeric_facts": [],
      "used_in_final": true
    }
  ],
  "provenance_edges": [],
  "contradic

references/research-playbook.md

# Research Playbook

## Runtime Split

### Runtime Online

- health-check backend first
- use backend-assisted source discovery
- security-check URLs before fetch
- send minimal structured feedback only when external sources were actually used

### Runtime Fallback

- skip all backend API calls
- keep the same research discipline
- never expose backend failure to the user

## Phase 0: Intent Decomposition

When online, decompose the user request into `2-5` angles.

Each angle should contain:

- `angle`
- `query`
- `category`
- `min_score`

Use search keywords, not a copy-paste of the raw user question.

## Question Normalization

Always normalize before researching.

Minimum fields:

- `raw_query`
- `normalized_query`
- `subject`
- `intent_type`
- `query_category`

Optional fields only when clearly supported:

- `time_scope`
- `region_scope`
- `version_scope`
- `target_capability`

## Tracks

Choose one `primary_track`. Add `supporting_tracks` only when they materially help.

- `Track 1`: current fact check
- `Track 2`: capability or compatibility verification
- `Track 3`: implementation or how-to
- `Track 4`: comparison, selection, or policy confirmation

## Subquestions And Claims

- build up to `6` subquestions
- split them into:
  - `core_subquestions`
  - `verification_subquestions`
  - `countercheck_subquestions`
- derive at most `3` critical claims

## Source Discovery

### Security Check

Before any online WebFetch, send candidate URLs to:

```text
POST https://www.shoggoth.vip/v1/sources/check
Content-Type: application/json

{"urls": ["https://example.com/a", "https://example.org/b"]}
```

The request body MUST be `{"urls": [...]}` — an array of up to 20 URLs, not a single URL object. The response is `{"results": [{"url", "safe", ...}]}`; read each item's own `url` + `safe` verdict.

Rules:

- `safe: true` -> may fetch
- `safe: false` -> do not fetch
- if the endpoint is unavailable -> use conservative fallback and fetch only known high-reputation domains

### Three Paths

Run all three when online:

- `Path A`: targeted backend source search
- `Path B`: extended backend source search
- `Path C`: native WebSearch for independent coverage and discovery

Path C always runs.

## Research Rounds

Use staged research:

### Round 1: Primary Evidence

- establish strongest direct evidence

### Round 2: Independent Verification

- confirm scope, timing, version, or limits

### Round 3: Conflict Resolution

Run only if:

- strong sources disagree
- version or timing matters
- region or plan differences may explain the gap

### Round 4: Salvage Pass

Run only if a decisive gap still remains after Round 3.

## Stop Rules

Defaults:

- `standard_search_rounds = 3`
- `max_search_rounds = 4`
- `max_key_claims = 3`

Stop when:

- each core claim has direct support or a clear evidence gap
- no major unresolved conflict blocks the answer
- uncertainty is explicit

Hard stop:

- after Round 4, stop researching
- if a claim is unresolved, say so plainly in

references/source-scoring.md

# Source Scoring

Use two layers together when backend is online:

1. backend reputation
2. built-in 6-dimension scoring

In runtime fallback, use only the built-in layer.

## Layer 1: Backend Reputation

Query:

```text
GET https://www.shoggoth.vip/v1/sources?domain=<hostname>
```

Decision guide:

| Score Range | Confidence | Action |
| --- | --- | --- |
| `>= 1.5` | `>= 0.7` | prefer as primary reference |
| `>= 1.0` | `>= 0.5` | normal weight |
| `>= 0.5` | `>= 0.3` | cautious, requires stronger cross-check |
| `< 0.5` | any | low priority, use only if needed |
| any | `< 0.3` | downgrade to neutral |

If `found: false`, treat the domain as neutral and unverified.

## Layer 2: Built-in 6-Dimension Scoring

Score each dimension `0-2`. Total range `0-12`.

### 1. authority

| Condition | Score |
| --- | --- |
| official domain / official org repo / `.gov` / `.edu` / standards body | `2` |
| curated technical reference / official registry / verified maintainer / strong tech publication | `1` |
| otherwise | `0` |

### 2. stability

Prefer automated scoring:

```text
python3 tools/score_stability.py --json "<url>"
```

Manual fallback:

| Condition | Score |
| --- | --- |
| docs, permalinks, release pages, standards pages, registry pages | `2` |
| official blog post, reputable outlet, third-party technical blog | `1` |
| social post, personal blog, session URL, temporary token URL | `0` |

### 3. accessibility

| Condition | Score |
| --- | --- |
| public and readable without barriers | `2` |
| partial barrier such as free account or mild geo restriction | `1` |
| login wall / paywall / captcha gate | `0` |

### 4. freshness

Score relative to the question's time scope.

| Condition | Score |
| --- | --- |
| clearly within the relevant time window | `2` |
| probably current but partially ambiguous | `1` |
| clearly outdated or superseded | `0` |

### 5. relevance

| Condition | Score |
| --- | --- |
| directly addresses the claim | `2` |
| one inference step required | `1` |
| tangential or unrelated | `0` |

### 6. primacy

| Condition | Score |
| --- | --- |
| original source | `2` |
| useful secondary analysis | `1` |
| tertiary repost / summary-only / discussion echo | `0` |

## Shortcuts

- verified maintainer social post: authority stays low unless independently grounded
- content farm or AI slop: reject immediately
- official GitHub release page of the exact project: strong shortcut for authority, stability, and primacy

## Minimum Rules

- do not use a source below `5/12` as key evidence
- every important claim needs at least one source with `authority >= 1` and `relevance >= 1`
- every core conclusion should be anchored to at least one `primacy = 2` source whenever possible

## Output Rule

When runtime online:

- show backend reputation in `Sources`

When runtime fallback:

- show the 6-dimension breakdown in `Sources`

Github ReposUpdated 12h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.