Does openclaw-agent-skills auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Is openclaw-agent-skills free?

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

openclaw-agent-skills

Shared skills for coding agents that work on OpenClaw projects. This repo is the public canonical source for common workflows such as review closeout and remote validation.

FLOW.md

openclaw@openclaw

GitHub

Plugin Signal73/100Solid

maintained100

capable46

documented75

adopted64

Install

$ npx -y skills add openclaw/agent-skills --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript Node HTML

+5 tags

Bash Linux Git GitHub Anthropic

1,046

Stars

Forks

Active

Maintenance

Python

Language

MIT

License

5h ago

Last commit

2mo ago

Created

Repo: openclaw/agent-skills

In this plugin

8 skills

See everything inside

What's inside

Skills

/agent-transcriptGitHub PR/issue agent transcripts: redact, preview, and insert safely./autoreviewPre-commit/ship code review: Codex default; optional Claude, Pi, or Kimi./beamPublish a redacted local coding session to an authenticated read-only Beam catalog./behavior-validatorSource-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts./crabboxCrabbox/Testbox remote proof for OpenClaw: trusted-source routing, untrusted isolation, Linux/macOS/Windows/WSL2, live E2E, desktop, diagnostics, cleanup./handoffClipboard-ready handoff prompt for another agent to investigate or continue a task.

Show all 8 skills

/readme-standardHouse README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos./session-viewerRender Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.

README

Read on GitHub

OpenClaw Agent Skills

Shared skills for coding agents that work on OpenClaw projects.

This repo is the public canonical source for common workflows such as review closeout and remote validation. The goal is simple: write a workflow once, reuse it everywhere, and avoid hand-copying long SKILL.md files across every repo. See VISION.md for catalog boundaries and admission principles.

Included Skills

agent-transcript: local-only, redacted PR/issue transcript provenance.
autoreview: structured closeout/code-review workflow plus helper script.
behavior-validator: source-blind validation of user-visible behavior against a contract.
beam: self-contained, authenticated, redacted publication of local coding sessions to a read-only OpenClaw catalog.
crabbox: Crabbox/Testbox remote validation workflow for broad or CI-parity proof.
handoff: path-free prompt handoff workflow for delegating a task to another agent.
readme-standard: house README structure, badge row, tone, and verification gates for steipete/openclaw repos.
session-viewer: local searchable HTML viewer for agent session JSONL.

Repo-specific product skills should stay in the repo they describe. For example, an acpx usage skill belongs in openclaw/acpx; a general review helper belongs here.

Quick Start

Clone the repo:

git clone https://github.com/openclaw/agent-skills.git
cd agent-skills

List available skills:

scripts/install-skills --list

Preview an install without changing files:

scripts/install-skills --dry-run

Install all skills into the default agent skill directory:

scripts/install-skills

Install only selected skills:

scripts/install-skills autoreview crabbox

Install somewhere else:

scripts/install-skills --target ~/.codex/skills autoreview

Use copies instead of symlinks:

scripts/install-skills --mode copy --target ~/.agents/skills

Replace an existing installed skill:

scripts/install-skills --force autoreview

Symlinks are best for local development because changes in this checkout are immediately visible. Copies are better for portable or locked-down setups.

Codex And Claude

For Codex, symlink this repo into ~/.codex/skills:

mkdir -p ~/.codex/skills
ln -sfn "$(pwd)/skills" ~/.codex/skills/agent-skills

For Claude Code, symlink this repo into ~/.claude/skills:

mkdir -p ~/.claude
ln -sfn "$(pwd)/skills" ~/.claude/skills

If ~/.claude/skills already points at another shared skills folder, add symlinks inside that folder instead:

ln -sfn "$(pwd)/skills/autoreview" /path/to/shared-skills/autoreview
ln -sfn "$(pwd)/skills/crabbox" /path/to/shared-skills/crabbox

Recommended one-liner for repo AGENTS.md files:

Shared agent workflows: install or symlink https://github.com/openclaw/agent-skills for `autoreview`, `crabbox`, and other common skills; do not vendor shared skills here unless this repo intentionally needs a zero-setup snapshot.

Zero-Setup Repos

Some important repos should work for contributors who only cloned that repo and never installed shared skills. Those repos may vendor a generated snapshot under .agents/skills/<name>.

That snapshot is a distribution artifact, not the source of truth:

edit canonical skills here first
sync snapshots downstream after review
keep downstream copies small in number
add provenance and drift checks when a repo vendors a snapshot

autoreview is a good candidate for a zero-setup snapshot in flagship repos because review closeout is part of the contribution workflow. Large operational skills should be vendored only when the repo genuinely needs them available without setup.

Repository Layout

skills/
  agent-transcript/
    SKILL.md
    scripts/
  autoreview/
    SKILL.md
    scripts/
  behavior-validator/
    SKILL.md
    references/
  beam/
    README.md
    SKILL.md
    references/
    scripts/
  crabbox/
    SKILL.md
  handoff/
    SKILL.md
  session-viewer/
    SKILL.md
    scripts/
scripts/
  install-skills
  validate-skills

Each skill lives in skills/<name>/ and must contain SKILL.md. Helper scripts belong inside that skill's scripts/ directory.

Validate

Run this after edits:

python3 -m venv .venv
. .venv/bin/activate
python -m pip install -r requirements-dev.txt
scripts/validate-skills
python3 -m py_compile scripts/install-skills scripts/install-skills.test.py scripts/validate-skills scripts/validate-skills.test.py
python3 scripts/install-skills.test.py
python3 scripts/validate-skills.test.py
bash -n skills/autoreview/scripts/test-review-harness
python3 -m py_compile skills/autoreview/scripts/autoreview skills/autoreview/scripts/test-review-harness.py skills/autoreview/scripts/autoreview_test.py
python3 skills/autoreview/scripts/autoreview --self-test-config-defaults
python3 skills/autoreview/scripts/autoreview --self-test-fallback-scope
python3 skills/autoreview/scripts/autoreview --self-test-engine-isolation
python3 skills/autoreview/scripts/autoreview --self-test-json-array-parser
python3 skills/autoreview/scripts/autoreview --self-test-opencode-jsonl-parser
python3 skills/autoreview/scripts/autoreview --self-test-opencode-isolation
python3 skills/autoreview/scripts/autoreview --self-test-cursor-jsonl-parser
python3 -m unittest skills/autoreview/scripts/autoreview_test.py skills.autoreview.tests.test_autoreview_hardening
node --check skills/agent-transcript/scripts/agent-transcript
node --check skills/beam/scripts/beam
node --check skills/beam/scripts/beam-session.js
node --test skills/agent-transcript/scripts/agent-transcript.test.mjs skills/beam/scripts/beam.test.mjs skills/session-viewer/scripts/session-viewer.test.ts

The validator checks every skills/*/SKILL.md for YAML frontmatter plus required name and description.

Session exports can contain sensitive conversation data. Treat session-viewer HTML as local/private output unless it has been separately redacted and reviewed.

Editing Rules

Keep descriptions short and useful for routing.
Keep skill bodies operational rather than essay-like.
Do not include secrets, private hostnames, private account IDs, or private URLs.
Prefer helper scripts for repeatable command logic.
Do not update vendored downstream snapshots by hand. Update this repo, then sync.

License

MIT.

File tree

openclaw/agent-skillsView on GitHub

.gitattributes
.github/
  workflows/
    clawsweeper-dispatch.yml
    validate.yml
.gitignore
AGENTS.md
docs/
  assets/
    readme-banner.jpg
LICENSE
README.md
requirements-dev.txt
scripts/
  install-skills
  install-skills.test.py
  validate-skills
  validate-skills.test.py
skills/
skills.sh.json
  agent-transcript/
    scripts/
      agent-transcript
      agent-transcript.test.mjs
    SKILL.md
  autoreview/
    AGENTS.md
    CLAUDE.md
    scripts/
      autoreview
      autoreview_test.py
      test-review-harness
      test-review-harness.ps1
      test-review-harness.py
    SKILL.md
    tests/
      fixtures/
        typescript-benign-config-path-references.ts
        typescript-benign-references.ts
        typescript-sensitive-literals.ts
      test_autoreview_hardening.py
  beam/
    README.md
    references/
      claude-code-hooks.json
      codex-hooks.toml
    scripts/
      beam
      beam-session.js
      beam.test.mjs
    SKILL.md
  behavior-validator/
    agents/
      openai.yaml
    references/
      contract-template.md
      report-schema.md
    SKILL.md
  crabbox/
    SKILL.md
  handoff/
    SKILL.md
  readme-standard/
    SKILL.md
  session-viewer/
    agents/
      openai.yaml
    scripts/
      core/
        detect.ts
        jsonl.ts
        types.ts
      html.ts
      importers/
        claude.ts
        codex.ts
        pi-openclaw.ts
      session-viewer.test.ts
      session-viewer.ts
    SKILL.md
    tsconfig.json
VISION.md

More Flows by @openclaw.

VerifiedPlugin

Testing

crabbox

Warm a box, sync the diff, run the suite. Crabbox is a generic remote software testing and execution control plane.

1 skill

@openclaw

View Plugin

FAQ

openclaw-agent-skills is a Claude Code plugin with 8 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes agent-transcript, autoreview, beam. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is openclaw-agent-skills?: Shared skills for coding agents that work on OpenClaw projects. This repo is the public canonical source for common workflows such as review closeout and remote validation.
How do I install openclaw-agent-skills?: Run these in Claude Code: npx -y skills add openclaw/agent-skills --agent claude-code. Then prompt normally.
Does openclaw-agent-skills auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is openclaw-agent-skills free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

openclaw-agent-skills

Shared skills for coding agents that work on OpenClaw projects. This repo is the public canonical source for common workflows such as review closeout and remote validation.

FLOW.md

openclaw@openclaw

GitHub

Plugin Signal73/100Solid

maintained100

capable46

documented75

adopted64

Install

$ npx -y skills add openclaw/agent-skills --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript Node HTML

+5 tags

Bash Linux Git GitHub Anthropic

1,046

Stars

Forks

Active

Maintenance

Python

Language

MIT

License

5h ago

Last commit

2mo ago

Created

Repo: openclaw/agent-skills

In this plugin

8 skills

See everything inside

What's inside

Skills

Show all 8 skills

README

Read on GitHub

OpenClaw Agent Skills

Shared skills for coding agents that work on OpenClaw projects.

Included Skills

agent-transcript: local-only, redacted PR/issue transcript provenance.
autoreview: structured closeout/code-review workflow plus helper script.
behavior-validator: source-blind validation of user-visible behavior against a contract.
beam: self-contained, authenticated, redacted publication of local coding sessions to a read-only OpenClaw catalog.
crabbox: Crabbox/Testbox remote validation workflow for broad or CI-parity proof.
handoff: path-free prompt handoff workflow for delegating a task to another agent.
readme-standard: house README structure, badge row, tone, and verification gates for steipete/openclaw repos.
session-viewer: local searchable HTML viewer for agent session JSONL.

Repo-specific product skills should stay in the repo they describe. For example, an acpx usage skill belongs in openclaw/acpx; a general review helper belongs here.

Quick Start

Clone the repo:

git clone https://github.com/openclaw/agent-skills.git
cd agent-skills

List available skills:

scripts/install-skills --list

Preview an install without changing files:

scripts/install-skills --dry-run

Install all skills into the default agent skill directory:

scripts/install-skills

Install only selected skills:

scripts/install-skills autoreview crabbox

Install somewhere else:

scripts/install-skills --target ~/.codex/skills autoreview

Use copies instead of symlinks:

scripts/install-skills --mode copy --target ~/.agents/skills

Replace an existing installed skill:

scripts/install-skills --force autoreview

Symlinks are best for local development because changes in this checkout are immediately visible. Copies are better for portable or locked-down setups.

Codex And Claude

For Codex, symlink this repo into ~/.codex/skills:

mkdir -p ~/.codex/skills
ln -sfn "$(pwd)/skills" ~/.codex/skills/agent-skills

For Claude Code, symlink this repo into ~/.claude/skills:

mkdir -p ~/.claude
ln -sfn "$(pwd)/skills" ~/.claude/skills

If ~/.claude/skills already points at another shared skills folder, add symlinks inside that folder instead:

ln -sfn "$(pwd)/skills/autoreview" /path/to/shared-skills/autoreview
ln -sfn "$(pwd)/skills/crabbox" /path/to/shared-skills/crabbox

Recommended one-liner for repo AGENTS.md files:

Shared agent workflows: install or symlink https://github.com/openclaw/agent-skills for `autoreview`, `crabbox`, and other common skills; do not vendor shared skills here unless this repo intentionally needs a zero-setup snapshot.

Zero-Setup Repos

Some important repos should work for contributors who only cloned that repo and never installed shared skills. Those repos may vendor a generated snapshot under .agents/skills/<name>.

That snapshot is a distribution artifact, not the source of truth:

edit canonical skills here first
sync snapshots downstream after review
keep downstream copies small in number
add provenance and drift checks when a repo vendors a snapshot

Repository Layout

skills/
  agent-transcript/
    SKILL.md
    scripts/
  autoreview/
    SKILL.md
    scripts/
  behavior-validator/
    SKILL.md
    references/
  beam/
    README.md
    SKILL.md
    references/
    scripts/
  crabbox/
    SKILL.md
  handoff/
    SKILL.md
  session-viewer/
    SKILL.md
    scripts/
scripts/
  install-skills
  validate-skills

Each skill lives in skills/<name>/ and must contain SKILL.md. Helper scripts belong inside that skill's scripts/ directory.

Validate

Run this after edits:

python3 -m venv .venv
. .venv/bin/activate
python -m pip install -r requirements-dev.txt
scripts/validate-skills
python3 -m py_compile scripts/install-skills scripts/install-skills.test.py scripts/validate-skills scripts/validate-skills.test.py
python3 scripts/install-skills.test.py
python3 scripts/validate-skills.test.py
bash -n skills/autoreview/scripts/test-review-harness
python3 -m py_compile skills/autoreview/scripts/autoreview skills/autoreview/scripts/test-review-harness.py skills/autoreview/scripts/autoreview_test.py
python3 skills/autoreview/scripts/autoreview --self-test-config-defaults
python3 skills/autoreview/scripts/autoreview --self-test-fallback-scope
python3 skills/autoreview/scripts/autoreview --self-test-engine-isolation
python3 skills/autoreview/scripts/autoreview --self-test-json-array-parser
python3 skills/autoreview/scripts/autoreview --self-test-opencode-jsonl-parser
python3 skills/autoreview/scripts/autoreview --self-test-opencode-isolation
python3 skills/autoreview/scripts/autoreview --self-test-cursor-jsonl-parser
python3 -m unittest skills/autoreview/scripts/autoreview_test.py skills.autoreview.tests.test_autoreview_hardening
node --check skills/agent-transcript/scripts/agent-transcript
node --check skills/beam/scripts/beam
node --check skills/beam/scripts/beam-session.js
node --test skills/agent-transcript/scripts/agent-transcript.test.mjs skills/beam/scripts/beam.test.mjs skills/session-viewer/scripts/session-viewer.test.ts

The validator checks every skills/*/SKILL.md for YAML frontmatter plus required name and description.

Session exports can contain sensitive conversation data. Treat session-viewer HTML as local/private output unless it has been separately redacted and reviewed.

Editing Rules

Keep descriptions short and useful for routing.
Keep skill bodies operational rather than essay-like.
Do not include secrets, private hostnames, private account IDs, or private URLs.
Prefer helper scripts for repeatable command logic.
Do not update vendored downstream snapshots by hand. Update this repo, then sync.

License

MIT.

File tree

openclaw/agent-skillsView on GitHub

.gitattributes
.github/
  workflows/
    clawsweeper-dispatch.yml
    validate.yml
.gitignore
AGENTS.md
docs/
  assets/
    readme-banner.jpg
LICENSE
README.md
requirements-dev.txt
scripts/
  install-skills
  install-skills.test.py
  validate-skills
  validate-skills.test.py
skills/
skills.sh.json
  agent-transcript/
    scripts/
      agent-transcript
      agent-transcript.test.mjs
    SKILL.md
  autoreview/
    AGENTS.md
    CLAUDE.md
    scripts/
      autoreview
      autoreview_test.py
      test-review-harness
      test-review-harness.ps1
      test-review-harness.py
    SKILL.md
    tests/
      fixtures/
        typescript-benign-config-path-references.ts
        typescript-benign-references.ts
        typescript-sensitive-literals.ts
      test_autoreview_hardening.py
  beam/
    README.md
    references/
      claude-code-hooks.json
      codex-hooks.toml
    scripts/
      beam
      beam-session.js
      beam.test.mjs
    SKILL.md
  behavior-validator/
    agents/
      openai.yaml
    references/
      contract-template.md
      report-schema.md
    SKILL.md
  crabbox/
    SKILL.md
  handoff/
    SKILL.md
  readme-standard/
    SKILL.md
  session-viewer/
    agents/
      openai.yaml
    scripts/
      core/
        detect.ts
        jsonl.ts
        types.ts
      html.ts
      importers/
        claude.ts
        codex.ts
        pi-openclaw.ts
      session-viewer.test.ts
      session-viewer.ts
    SKILL.md
    tsconfig.json
VISION.md

More Flows by @openclaw.

VerifiedPlugin

Testing

crabbox

Warm a box, sync the diff, run the suite. Crabbox is a generic remote software testing and execution control plane.

1 skill

@openclaw

View Plugin

FAQ

What is openclaw-agent-skills?: Shared skills for coding agents that work on OpenClaw projects. This repo is the public canonical source for common workflows such as review closeout and remote validation.
How do I install openclaw-agent-skills?: Run these in Claude Code: npx -y skills add openclaw/agent-skills --agent claude-code. Then prompt normally.
Does openclaw-agent-skills auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is openclaw-agent-skills free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.