What makes TinkerClaw Fork and Skill Scanner notable?

1.2K downloads. Trust evidence available

How should TinkerClaw Fork and Skill Scanner 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

TinkerClaw Fork and Skill Scanner

Reference material, not a runnable skill: a one-page outline of a workflow for scanning GitHub forks and ClawHub skills (bash pre-filter, sub-agent fan-out, scheduled reports). It ships no scripts and has no entry point. Read it only for the workflow shape; for working scanner code use the sibling skills/fork-scanner/ directory.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

1.1.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K 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: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 1.1.3release · observed Sep 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17324vfeqe0ptzp84z2z9vttx883zdg:fork-and-skill-scanner-ultimate

Install using `clawhub skill install s17324vfeqe0ptzp84z2z9vttx883zdg:fork-and-skill-scanner-ultimate` 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/globalcaos/fork-and-skill-scanner-ultimate before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-globalcaos-fork-and-skill-scanner-ultimate/snapshot"

Documentation

CLAWHUB

27,264 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: fork-and-skill-scanner-ultimate
version: 1.1.3
description: "Reference material, not a runnable skill: a one-page outline of a workflow for scanning GitHub forks and ClawHub skills (bash pre-filter, sub-agent fan-out, scheduled reports). It ships no scripts and has no entry point. Read it only for the workflow shape; for working scanner code use the sibling skills/fork-scanner/ directory."
---

# Fork and Skill Scanner (Ultimate)

## What this is

This directory is documentation, not an executable skill. It contains a single
README describing a two-part workflow the operator sketched out — scanning the
forks of a GitHub repository for interesting changes, and scanning ClawHub for
notable skills — plus an empty `data/` directory held open by a `.gitkeep`.

There is no code here. Earlier revisions of the README described a `scripts/`
directory, a `Cron_Tasks/` output directory and a "META" file "in the skill
package"; none of those ever existed — `README.md` and `data/.gitkeep` are the
only two files ever committed under this path — and as of 1.1.3 the README says
so rather than implying otherwise.

The workflow the README outlines, in its own terms:

- **Fork scanner** — pre-filter a large fork list in bash to drop inactive
forks, fan the surviving candidates out to sub-agents for parallel analysis,
reassemble a report in the main agent, run on a Monday/Thursday schedule.
- **Skill scanner** — score a batch of ten ClawHub skills on functionality,
relevance and maintenance, then look at the other skills by the top author,
then write up the findings.

Those are the described intentions. This directory does not implement or
perform any of them, and nothing here has been verified to work.

## When to use / when not to

**Use it** when you want the shape of that scanning workflow — the phase
breakdown, the pre-filter-then-fan-out structure, the scoring dimensions — as
a starting point for writing your own implementation.

**Do not use it** when you need to actually scan anything. There is no command
to run. An agent that loads this skill expecting a scanner will find prose and
an empty directory.

For working code, look at the sibling `skills/fork-scanner/` directory in this
repository instead. It contains a Python implementation under `scripts/`
(including `fork_scanner.py`, `tier1_metadata.py`, `tier2_commits.py`,
`tier3_diff.py`, `watchlist.py`, `reporter.py`, `database.py` and
`rate_limiter.py`), a `schema.sql`, a `requirements.txt`, a `setup_cron.sh`, an
`example_usage.sh`, and its own architecture and quickstart documents. This
SKILL.md makes no claim about whether that sibling code currently runs — it is
simply where the executable material is, and it should be read before being
relied on.

## Entry points

None. The complete file list is:

- `README.md` — the workflow description summarised above.
- `data/.gitkeep` — a placeholder keeping an otherwise empty `data/` directory
in version control. Its one line of content says t

README.md

# Fork & Skill Scanner — TinkerClaw

> One of dozens of skills and plugins in **[TinkerClaw](https://github.com/globalcaos/tinkerclaw)** — a self-improving OpenClaw fork that's been running 24/7 for months.

A thousand forks of the same repo. Which one quietly fixed the bug you've been chasing?

Reading them by hand is a weekend you'll never get back — and the good change is buried on page forty.

There's a faster way to find the one fork, and the one skill, that actually matter.

This is your scout. Every run it triages a thousand GitHub forks, throws out the dead and the duplicate ones, and hands the survivors to a fan of sub-agents that read them in parallel — so you get back the handful with real changes instead of a wall of noise. Twice a week, on a Monday and Thursday cron, it also scores the top skills on ClawHub, so you see what's trending before everyone else does. You wake up to a short report of what's worth your attention, not a tab graveyard.

**Part of [TinkerClaw](https://github.com/globalcaos/tinkerclaw)** — real-time token tracking, self-improving crons, persistent cognitive memory. This is one piece of that stack; the repo has dozens more.

👉 **https://github.com/globalcaos/tinkerclaw**

_Clone it. Fork it. Break it. Make it yours._

## Setup

This is a written workflow, not a program. To use it, implement the phases below
in your own agent: scan the forks of a repository you care about, and review the
top skills on a registry. Automate the runs with cron once you have something that
works.

## What's in this package

Two documents and an empty directory. There is no code here:

- `README.md` — this file: the workflow, and what it does and does not do.
- `SKILL.md` — the same workflow stated for an agent, including the plain warning
that there is nothing here to execute.
- `data/` — an empty directory held open by a `.gitkeep`, a place for *you* to put
scan output. Nothing in this package writes to it, or to anywhere else.

## Key Phases

### Fork Scanner

1. **Bash Pre-Filter:** Triage 1,000 forks, discard non-active.
2. **Sub-Agent Fan-Out:** Distribute candidate analysis for parallel processing.
3. **Main Agent Assembly:** Finalize report and insights.
4. **Scheduled Runs:** Mon/Thu.

### Skill Scanner

1. **Evaluate 10 Skills:** Score by functionality, relevance, and maintenance.
2. **In-Depth Author Scan:** Check top author's other skills.
3. **Compile Insights:** Lay practical improvement steps.

## Keeping your interests current

The "interests" this workflow tracks are **your** list of what to watch — the repos,
authors and topics you care about — kept in a file you own and edit. Refining that
list between runs is the point of running it repeatedly.

Stating it plainly, because "continuous improvement" inside an agent skill reads the
wrong way otherwise: **this skill does not modify itself.** It has no code, no
installer, no update step, and no write path to its own files or to your agent's
configuration. The only t

_meta.json

{
  "ownerId": "kn7623hrcwt6rg73a67xw3wyx580asdw",
  "slug": "fork-and-skill-scanner-ultimate",
  "version": "1.1.3",
  "publishedAt": 1788944203249
}

skill-card.md

## Description:

Reference material, not a runnable skill: a one-page outline of a workflow for scanning GitHub forks and ClawHub skills (bash pre-filter, sub-agent fan-out, scheduled reports). It ships no scripts and has no entry point. Read it only for the workflow shape; for working scanner code use the sibling skills/fork-scanner/ directory.

This skill is ready for commercial/non-commercial use.

## Publisher:

[globalcaos](https://clawhub.ai/user/globalcaos)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agents use this as reference material for designing a fork-and-skill scanning workflow. It outlines pre-filtering, sub-agent fan-out, scoring, and report assembly, but it does not run scans itself.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Users may mistake the package for a working scanner.

Mitigation: Confirm there is no entry point before use; treat the artifact as workflow reference material only.

Risk: A separate implementation of the described workflow may introduce token handling, network access, scheduled jobs, and output path risks.

Mitigation: Review that separate implementation for credential handling, network behavior, cron configuration, and output locations before running it.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/globalcaos/skills/fork-and-skill-scanner-ultimate)
- [TinkerClaw repository referenced by artifact](https://github.com/globalcaos/tinkerclaw)

## Skill Output:

**Output Type(s):** [Markdown, Guidance]

**Output Format:** [Markdown reference material]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Documentation-only package; it produces no files, shell commands, API calls, or automated scanner output.]

## Skill Version(s):

1.1.3 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d 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.