What makes DevTool Answer Monitor notable?

1.7K downloads. Trust evidence available

How should DevTool Answer Monitor 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

DevTool Answer Monitor

Use when the user wants to monitor how ChatGPT, Claude, Gemini, and other LLMs describe a developer tool, API, SDK, or open-source project. DevTool Answer Mo...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.7k

Updated

Oct 10, 2026

Version

0.3.0

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: 0.3.0release · observed Apr 23, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b190tf85c34fs78qx3mh12n83g7at:devtool-answer-monitor

Install using `clawhub skill install s17b190tf85c34fs78qx3mh12n83g7at:devtool-answer-monitor` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/veeicwgy/devtool-answer-monitor before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-veeicwgy-devtool-answer-monitor/snapshot"

Documentation

CLAWHUB

28,838 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: devtool-answer-monitor
description: >
  Use when the user wants to monitor how ChatGPT, Claude, Gemini, and other LLMs describe a developer tool, API, SDK, or open-source project. DevTool Answer Monitor is the companion skill for the devtool-answer-monitor repo and covers query pool design, four-metric monitoring, model-specific content placement, content checks, negative-answer repair, activation analysis, and T+7 or T+14 regression validation.
license: MIT
allowed-tools: Read
metadata:
  openclaw:
    emoji: "📈"
    author: "veeicwgy"
    homepage: "https://github.com/veeicwgy/devtool-answer-monitor"
    requires:
      env:
        - OPENAI_API_KEY
        - OPENAI_BASE_URL
      bins:
        - python3
        - bash
    primaryEnv: OPENAI_API_KEY
    env:
      - name: OPENAI_API_KEY
        description: "Optional provider API key for API collection mode only. Quickstart replay and manual paste mode do not need it."
        required: false
        sensitive: true
      - name: OPENAI_BASE_URL
        description: "Optional OpenAI-compatible gateway URL for multi-provider API collection mode."
        required: false
        sensitive: false
---

# Monitor What LLMs Say Before Users Choose Your Dev Tool

Use this skill as the **main visibility workflow router** for developer tools and open-source products.

**Brand:** DevTool Answer Monitor

**Companion repo:** [`devtool-answer-monitor`](https://github.com/veeicwgy/devtool-answer-monitor)

Use this when you want an agent to help you monitor how LLMs describe your product, build a reusable query pool, diagnose negative or outdated answers, and plan what to fix next.

## Safety First

- Treat this root skill as a **read-only workflow router**.
- Default to `quickstart replay` or `manual paste mode` when you only need examples or scoring help.
- Do not ask users to paste API keys into chat. If API collection mode is needed, tell them to configure local environment variables themselves and then hand off execution to `visibility-monitor`.
- Review local scripts such as `install.sh`, `quickstart.sh`, and the selected runner before executing shell commands.

## Start Here

Copy one of these prompts to begin:

- `Analyze how ChatGPT and Claude describe my API docs`
- `Build a developer-tool answer monitoring query pool for my SDK`
- `Find negative or outdated LLM claims about my project`

## 30-Second Result

**Typical input**

- product truth such as a README, docs, changelog, integrations, or positioning page
- answer evidence such as copied model answers, screenshots, or cited URLs
- scope such as target models, languages, regions, or a repeated query set

**What this skill returns**

- a reusable query pool
- raw evidence and a score draft plan
- a monitoring summary and report outline
- a repair backlog with T+7 or T+14 validation points

**Companion demo and sample outputs**

- Zero-install demo: [sample-run viewer](https://cdn.jsdelivr.net/gh/veeicwgy/devtool-answer-monitor@main/doc

skills/visibility-content-check/SKILL.md

---
name: visibility-content-check
description: >
  Use when the user wants to quality-check a draft before publishing it to improve AI visibility. Covers citation friendliness, Q&A structure, factual density, entity clarity, authority signals, and release readiness for developer-tool or open-source content.
---

# visibility-content-check

Use this skill to decide whether a draft is ready to influence LLM answers.

## Trigger

Use this skill before publishing a tutorial, comparison article, FAQ page, changelog summary, or product page update.

## Outputs

| Output | Description |
|---|---|
| Visibility readiness verdict | go, revise, or block |
| Issue list | missing signals, weak structure, entity ambiguity, thin evidence |
| Revision priorities | top fixes before publish |

## Next Best Skill

If the draft is blocked because of negative framing or wrong facts, use `visibility-repair`.

skills/visibility-monitor/SKILL.md

---
name: visibility-monitor
description: >
Use when the user wants to run or design AI visibility monitoring for a developer tool, API, SDK, or open-source project. Covers Query Pool execution, evidence logging, four-metric scoring, weekly reporting, anomaly detection, and action prioritization across multiple LLMs and languages.
allowed-tools: Read, Write, Edit, Bash
metadata:
openclaw:
author: "veeicwgy"
homepage: "https://github.com/veeicwgy/devtool-answer-monitor"
requires:
env:
- OPENAI_API_KEY
- OPENAI_BASE_URL
bins:
- python3
- bash
primaryEnv: OPENAI_API_KEY
env:
- name: OPENAI_API_KEY
description: "Optional provider API key for API collection mode. Not needed for quickstart replay or manual paste mode."
required: false
sensitive: true
- name: OPENAI_BASE_URL
description: "Optional OpenAI-compatible gateway URL for multi-provider monitoring."
required: false
sensitive: false
---

# visibility-monitor

Use this skill to turn repeated model checks into a consistent visibility monitoring workflow.

## Safety

- Use `quickstart replay` or `manual paste mode` first when the user does not need live API calls.
- Keep provider keys in local shell environment variables. Do not ask users to paste secrets into chat.
- Inspect `install.sh`, `quickstart.sh`, and the selected runner before executing Bash commands.

## Trigger

Use this skill when the user already has, or is ready to create, a Query Pool and wants to know:

1. whether the product is being mentioned;
2. whether mentions are positive, neutral, or negative;
3. whether the model understands the product's capabilities;
4. whether the model understands the product's ecosystem and integrations.

## Quick Start

### Zero-key paths first

- `bash quickstart.sh` replays sample data and does not require provider keys.
- `python -m devtool_answer_monitor run --manual-responses ...` scores copied answers without live API calls.

### Choose the right runner

| Runner | API Type | Works with | Use when |
|---|---|---|---|
| `scripts/run_monitor.py` | Responses API | OpenAI models only | GPT-4o, GPT-4.1 and variants |
| `scripts/run_chat_completions.py` | Chat Completions API | Any OpenAI-compatible provider | Claude, Gemini, DeepSeek, Qwen, MiniMax, GLM, or any gateway |

**For multi-model coverage across providers, always use `run_chat_completions.py`.**

```bash
python scripts/run_chat_completions.py \
--query-pool data/query-pools/mineru-example.json \
--model-config data/models.sample.json \
--out-dir data/runs/my-run
```

Before running the command above, verify that `OPENAI_API_KEY` is configured in the local shell. `OPENAI_BASE_URL` is optional and only needed for gateways or proxies.

Then annotate scores and generate the report:

```bash
python -m devtool_answer_monitor report \
--input data/runs/my-run/raw_responses.jsonl \
--output-dir data/run

skills/visibility-query-matrix/SKILL.md

---
name: visibility-query-matrix
description: >
  Use when the user wants to turn a product description into a visibility query matrix and Query Pool. Covers task-scenario mapping, multilingual keyword expansion, three-level clustering, competitor comparison queries, and model-validation loops for developer tools and open-source projects.
---

# visibility-query-matrix

Use this skill to build the query foundation for visibility monitoring and content planning.

## Trigger

Use this skill when the user has product context but does not yet have a robust Query Pool.

## Outputs

| Output | Description |
|---|---|
| Scenario matrix | user jobs to bilingual query language |
| Three-layer keyword set | core, scenario, and long-tail clusters |
| Query Pool seeds | reusable monitoring prompts |
| Validation notes | where the brand is missing or weak |

## Next Best Skill

After the Query Pool is ready, use `visibility-monitor`.

skills/visibility-repair/SKILL.md

---
name: visibility-repair
description: >
  Use when the user has a wrong, negative, outdated, or competitor-only LLM answer and needs a structured repair plan. Covers negative-type classification, source tracing, authority coverage, channel-specific repair actions, and regression checks.
---

# visibility-repair

Use this skill to turn a bad model answer into a repair backlog instead of reacting ad hoc.

## Trigger

Use this skill when an LLM answer contains any of the following:

1. factual error;
2. negative recommendation against the product;
3. outdated product description;
4. competitor-only recommendation in a strategic query.

## Outputs

| Output | Description |
|---|---|
| Problem type | one of the four negative categories |
| Repair actions | source fixes, content moves, authority pages, feedback actions |
| Regression plan | repeat checks for the affected queries |

## Next Best Skill

If the next task is to quality-check the newly repaired content, use `visibility-content-check`.

Github ReposUpdated 15h 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.