What makes agent-skills-setup notable?

3.2K downloads. Trust evidence available

How should agent-skills-setup 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

agent-skills-setup

Use when a user wants to migrate, back up, restore, compare, or move AI-coding-agent context across Cursor, Claude Code, Codex, Cline, Copilot, Windsurf, Gemini CLI, or another registered profile, including switching computers. Handles Skills, instructions/rules, and MCP with secret redaction, preview, verification, rollback, and portable bundles; compatible plugin packages and reviewed handoff are available by explicit opt-in.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

3.2k

Updated

Oct 9, 2026

Version

0.10.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 3.2K downloads reported by the source. Last updated 10/9/2026.

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 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 3.2K downloadsadoption · observed Oct 9, 2026
Latest release: 0.10.2release · observed Oct 3, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179fnaja3kqc64tnfyq6b5zb583p7d8:agent-skills-setup

Install using `clawhub skill install s179fnaja3kqc64tnfyq6b5zb583p7d8:agent-skills-setup` 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/luckycat133/agent-skills-setup before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-luckycat133-agent-skills-setup/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agent-skills-setup
version: "0.10.2"
compatibility: Requires local Bash, Python 3, environment lookup, and filesystem access; optional signing needs installed cryptography; no network access.
description: >-
  Use when a user wants to migrate, back up, restore, compare, or move
  AI-coding-agent context across Cursor, Claude Code, Codex, Cline,
  Copilot, Windsurf, Gemini CLI, or another registered profile, including
  switching computers. Handles Skills, instructions/rules, and MCP with
  secret redaction, preview, verification, rollback, and portable bundles;
  compatible plugin packages and reviewed handoff are available by explicit opt-in.
metadata:
  openclaw:
    requires:
      bins:
        - bash
        - python3
---
# Agent Skills Setup

## Permissions

- Run bundled local Bash/Python helpers and offline discovery only; network access is forbidden. No downloads, installations, or MCP connections.
- Read selected products, requested scopes, workspace, bundles, and named keys. Broad discovery needs a device-wide request; environment lookup resolves paths without exposing credentials.
- Write authorized targets, named plan/bundle/key outputs, and transaction state. `--yes` records existing user authorization for apply/restore/rollback; it does not grant authorization.

## Choose the workflow

- Infer products, objects, workspace, and scope from the request and established context. Project migration uses project scope; include user surfaces only when requested. Ask only for material information or authorization that cannot be inferred.
- An explicit move/apply/restore/rollback request authorizes that scoped action. Preserve prior authorization; preview-only requests stop after preview. Review exact destinations and losses before writing; ask for unresolved conflicts, unapproved losses, or broader scope.
- Save the plan, review its diff/rebuild manifest, and apply that exact file for execution. Changed inputs require a fresh plan and review.

| Request | Entry point and guidance |
| --- | --- |
| Detect or inventory context | `detect`, `inventory`; [registry](references/ide-registry.md) and [CLI guide](references/cli-workflow.md). |
| Compare or preview migration | `plan --json`; [migration safety](references/migration-safety.md). Saving `--output` writes a plan artifact. |
| Migrate context | Saved `plan` → `apply --yes` → `verify`; `migrate` orchestrates the same stages. [CLI guide](references/cli-workflow.md). |
| Back up or switch computers | `snapshot`, `bundle-verify`, `doctor`, `restore`; [bundle workflow](references/bundle-workflow.md). |
| Sign or authenticate a bundle | `bundle-keygen`, `bundle-sign`, `bundle-verify --trusted-key`; [bundle workflow](references/bundle-workflow.md). |
| Verify or undo applied changes | `verify`, `rollback --yes`; [verification](references/verification.md). |

Resolve both product profiles through [ide-registry.md](references/ide-registry.md) / [registry-v2.json](references/registry-v2.json

_meta.json

{
  "ownerId": "kn73ym4c6fp5b2vaa22t84v5fn83pt1p",
  "slug": "agent-skills-setup",
  "version": "0.10.2",
  "publishedAt": 1791015266890
}

references/bundle-workflow.md

# Portable bundle, restore, and signing workflow

Read for computer switching, portable backups, ACB restore, dependency checks,
or signing. Commands below use `migrator=/path/to/agent-skills-setup/scripts/smart-ide-migration.sh`;
substitute the installed Skill path and requested source, target, workspace,
scopes, and artifact paths. Run each command independently and inspect its result.
Use [migration-safety.md](migration-safety.md) for authorization and conflict rules.

## Capture and inspect

`snapshot` writes an ACB **directory**, not a compressed archive. Name the source
and output explicitly; the CLI's fallback product selectors are examples, not
permission to inspect or restore those products.

```bash
bash "$migrator" snapshot --source cursor/ide --target cursor/ide \
--workspace /path/to/project --scope project \
--objects skills,instructions,mcp --output /path/to/project.acb --json
bash "$migrator" bundle-verify /path/to/project.acb --json
bash "$migrator" doctor /path/to/project.acb --json
```

Review `manifest.json`, the collection summary, `rebuild.json`, and
`secrets.required.json`. ACB contains portable object bytes, sanitized inventory,
compatibility evidence, requirements, reauthentication actions, and checksums
binding every declared file. Failed, excluded, or manual objects are not
automatically backed up; report them. Credential values and private runtime
state must remain outside the bundle.

`objects_captured` counts captured product/profile/scope object surfaces;
`files_captured` counts their payload files. Compare these with the manifest's
file bindings and collection exclusions rather than treating file count as
the number of Skills or servers. ACB payload limits are 5,000 files, 10 MiB per
file, 100 MiB total, and 16 directory levels. Known image/font assets are
allowed; executable or unallowlisted binary files fail collection instead of
silently disappearing. The exact extensions are `SAFE_BINARY_EXTENSIONS` in
[acb/bundle.py](../scripts/acb/bundle.py).

New snapshots record optional integer `files[].mode` permission bits (`0..0o777`)
in the checksummed manifest. On POSIX, restore and opt-in extraction apply these
bits to copied files, preserving text helper scripts' executable bits while
dropping setuid, setgid, and sticky flags. Payload storage permissions need not
match the source. Older mode-less bundles remain readable but cannot establish
original executable permissions; Windows applies only permissions supported by
its filesystem. Verify required target file modes separately from content
hashes; directory permissions and script execution are outside this guarantee.
Recorded modes apply to copied Skill/plugin files and extracted payloads.
Generated instruction, MCP, and handoff files use their target writer's
permissions; for example, generated MCP configuration is private (`0600`).

For a requested device-wide backup, run `detect` and review eligible profiles,
then use `snapshot --all-installed --scope us

references/cli-workflow.md

# Public CLI workflow

Read for detection, inventory, comparison, profile-aware migration, and command
selection. `smart-ide-migration.sh` is the public wrapper. Set its path to the
installed Skill directory, independent of the project working directory:

```bash
migrator=/path/to/agent-skills-setup/scripts/smart-ide-migration.sh
```

Use concrete `<product>/<profile>` selectors from [Registry v2](registry-v2.json).
Profile aliases, supported surfaces, platforms, and manual boundaries come from
[ide-registry.md](ide-registry.md). Do not substitute paths from another product
or a different profile. Paths can use documented environment/platform overrides;
remote-host surfaces remain experimental.

| Command | Observable result |
| --- | --- |
| `detect` | Offline install/configuration/compatibility detection, with evidence. |
| `inventory` | Resolved surfaces, policy, precedence, and existence. |
| `plan` | Destination paths, statuses, diffs, losses, and rebuild actions. |
| `migrate` | Saved plan, apply manifest, and verification artifact in one flow. |
| `apply` | Execution of a saved, state-validated plan and transaction manifest. |
| `verify` | Whether recorded applied files still match their manifest. |
| `rollback` | Guarded undo using that apply manifest. |
| `snapshot` | Portable ACB directory and collection/exclusion summary. |
| `bundle-verify` | Closed-world checksum, binding, and secret checks; optional trusted signature. |
| `bundle-keygen`, `bundle-sign` | Offline Ed25519 key files or signature artifact. |
| `restore` | Destination-side plan from bundle bytes, optional apply and verify. |
| `doctor` | Complete recorded requirements, executable PATH checks, and reauthentication/rebuild actions. |
| `legacy` | Explicit lookup or zero-write dry-run compatibility only. |

Legacy preview reports stay on stdout, including when `--report` is supplied;
the named file is neither created nor changed. Use `plan --output` to save a
profile-aware plan for review and execution.

`--json` emits one JSON document on stdout; diagnostics go to stderr. Inspect
exit status, item statuses, and applied counts, not merely `ok`. Use
`bash "$migrator" <command> --help` for that command's accepted flags.

## Detect and preview the named project

```bash
bash "$migrator" detect --product cursor --profile ide \
    --workspace /path/to/project --json
bash "$migrator" inventory --product cursor --profile ide \
    --workspace /path/to/project --json
bash "$migrator" plan --source cursor/ide --target claude/code-cli \
    --workspace /path/to/project --scope project \
    --objects skills,instructions,mcp --json
```

The final command emits a preview without saving an artifact. To prepare an
authorized execution, add `--output /path/to/plan.json`, read that file's
`review_preview`, `loss_report`, and `rebuild_manifest`, and apply the same file.
Do not claim a migration from detection, plan output, or an empty inventory.
Broad `detect`/`inventory` without a product

references/doc-freshness-checks.json

{
  "schema_version": 1,
  "verified_at": "2026-08-15",
  "checks": [
    {
      "id": "agent-skills-spec",
      "url": "https://raw.githubusercontent.com/agentskills/agentskills/main/docs/specification.mdx",
      "required_terms": [
        "name",
        "description",
        "metadata"
      ]
    },
    {
      "id": "cline-config",
      "url": "https://docs.cline.bot/getting-started/config",
      "required_terms": [
        "cline",
        "configuration"
      ]
    },
    {
      "id": "forgecode-docs",
      "url": "https://forgecode.dev/docs/",
      "required_terms": [
        "forge",
        "agent"
      ]
    },
    {
      "id": "qoder-docs",
      "url": "https://docs.qoder.com/",
      "required_terms": [
        "qoder"
      ]
    },
    {
      "id": "codex-docs",
      "url": "https://learn.chatgpt.com/docs/llms.txt",
      "required_terms": [
        "codex"
      ]
    },
    {
      "id": "openhands-docs",
      "url": "https://docs.openhands.dev/overview/introduction",
      "required_terms": [
        "openhands"
      ]
    },
    {
      "id": "amp-manual",
      "url": "https://ampcode.com/manual",
      "required_terms": [
        "agent skills",
        "mcp"
      ]
    },
    {
      "id": "monkeycode-readme",
      "url": "https://raw.githubusercontent.com/chaitin/MonkeyCode/main/README.md",
      "required_terms": [
        "monkeycode",
        "development platform"
      ]
    },
    {
      "id": "cursor-rules",
      "url": "https://docs.cursor.com/context/rules",
      "required_terms": [
        "cursor",
        "rule"
      ]
    },
    {
      "id": "claude-code-skills",
      "url": "https://code.claude.com/docs/en/skills",
      "required_terms": [
        "skill"
      ]
    },
    {
      "id": "github-copilot-cli",
      "url": "https://docs.github.com/en/copilot/how-tos/copilot-cli",
      "required_terms": [
        "copilot",
        "cli"
      ]
    },
    {
      "id": "vscode-agent-skills",
      "url": "https://code.visualstudio.com/docs/agent-customization/agent-skills",
      "required_terms": [
        "skill"
      ]
    },
    {
      "id": "gemini-cli-skills",
      "url": "https://github.com/google-gemini/gemini-cli/blob/main/docs/skills.md",
      "required_terms": [
        "gemini",
        "skill"
      ]
    },
    {
      "id": "kiro-steering",
      "url": "https://kiro.dev/docs/steering",
      "required_terms": [
        "kiro",
        "steering"
      ]
    },
    {
      "id": "rovodev-cli-skills",
      "url": "https://support.atlassian.com/rovo/docs/use-agent-skills-in-rovo-dev-cli/",
      "required_terms": [
        "rovo",
        "skill"
      ]
    },
    {
      "id": "ibm-bob-docs",
      "url": "https://www.ibm.com/docs/en/bob",
      "required_terms": [
        "bob",
        "agent"
      ]
    },
    {
      "id": "warp-drive-prompts",
      "url": "https://docs.warp.dev/agents/prompts",
      "required_terms": [
        "warp",
        "prompt"

Github ReposUpdated 2h 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.