Claw Release logo

Claw Release

OrganizationPopular
prompt-security
claw-release

Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.

Overview

Publisherprompt-security
Repositoryclawsec
Skill nameclaw-release
Stars
1.1K
Forks
112
Bundled files
2
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by prompt-security on GitHub. Read the source before you install it.

Installation

Install the Claw Release AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/prompt-security/clawsec/tree/main/skills/claw-release
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/prompt-security/clawsec.git /tmp/clawsec
mkdir -p .claude/skills
cp -r /tmp/clawsec/skills/claw-release .claude/skills/claw-release
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Claw Release in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Claw Release on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Claw Release is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Claw Release

Internal tool for releasing skills and managing the ClawSec catalog.

An internal tool by Prompt Security


Vercel Skills Installation

Install with the Vercel Skills CLI for this harness:

bash
npx skills add prompt-security/clawsec --skill claw-release -a openclaw -y

Operational Notes

  • Internal maintainer workflow only.
  • Required runtime: bash, git, jq, gh
  • Required credentials: authenticated GitHub CLI with permission to create releases
  • Side effects: creates commits, tags, pushes to remote, and publishes GitHub Releases
  • Trust model: run only from a trusted checkout with a clean working tree and maintainer approval

Release Artifact Verification

For standalone installs, verify the signed release manifest before trusting SKILL.md, skill.json, or the archive. The skill.json file is the package metadata/SBOM source, and the release pipeline signs checksums.json with the ClawSec release key.

bash
set -euo pipefail

SKILL_NAME="claw-release"
VERSION="0.0.4"
REPO="prompt-security/clawsec"
TAG="${SKILL_NAME}-v${VERSION}"
BASE="https://github.com/${REPO}/releases/download/${TAG}"
ZIP_NAME="${SKILL_NAME}-v${VERSION}.zip"
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "$TMP_DIR"' EXIT

RELEASE_PUBKEY_SHA256="711424e4535f84093fefb024cd1ca4ec87439e53907b305b79a631d5befba9c8"

curl -fsSL "$BASE/checksums.json" -o "$TMP_DIR/checksums.json"
curl -fsSL "$BASE/checksums.sig" -o "$TMP_DIR/checksums.sig"
curl -fsSL "$BASE/signing-public.pem" -o "$TMP_DIR/signing-public.pem"
curl -fsSL "$BASE/$ZIP_NAME" -o "$TMP_DIR/$ZIP_NAME"
curl -fsSL "$BASE/SKILL.md" -o "$TMP_DIR/SKILL.md"
curl -fsSL "$BASE/skill.json" -o "$TMP_DIR/skill.json"

ACTUAL_PUBKEY_SHA256="$(openssl pkey -pubin -in "$TMP_DIR/signing-public.pem" -outform DER | shasum -a 256 | awk '{print $1}')"
if [ "$ACTUAL_PUBKEY_SHA256" != "$RELEASE_PUBKEY_SHA256" ]; then
  echo "ERROR: signing-public.pem fingerprint mismatch" >&2
  exit 1
fi

openssl base64 -d -A -in "$TMP_DIR/checksums.sig" -out "$TMP_DIR/checksums.sig.bin"
openssl pkeyutl -verify -rawin -pubin \
  -inkey "$TMP_DIR/signing-public.pem" \
  -sigfile "$TMP_DIR/checksums.sig.bin" \
  -in "$TMP_DIR/checksums.json" >/dev/null

hash_file() {
  if command -v shasum >/dev/null 2>&1; then
    shasum -a 256 "$1" | awk '{print $1}'
  else
    sha256sum "$1" | awk '{print $1}'
  fi
}

verify_manifest_file() {
  asset="$1"
  path="$2"
  expected="$(jq -r --arg asset "$asset" '.files[$asset].sha256 // empty' "$TMP_DIR/checksums.json")"
  if [ -z "$expected" ]; then
    echo "ERROR: checksums.json missing $asset" >&2
    exit 1
  fi
  actual="$(hash_file "$path")"
  if [ "$actual" != "$expected" ]; then
    echo "ERROR: checksum mismatch for $asset" >&2
    exit 1
  fi
}

expected_archive="$(jq -r '.archive.sha256 // empty' "$TMP_DIR/checksums.json")"
if [ -z "$expected_archive" ]; then
  echo "ERROR: checksums.json missing archive.sha256" >&2
  exit 1
fi
actual_archive="$(hash_file "$TMP_DIR/$ZIP_NAME")"
if [ "$actual_archive" != "$expected_archive" ]; then
  echo "ERROR: archive checksum mismatch" >&2
  exit 1
fi

verify_manifest_file "SKILL.md" "$TMP_DIR/SKILL.md"
verify_manifest_file "skill.json" "$TMP_DIR/skill.json"

echo "Signed release manifest, archive, SKILL.md, and skill.json verified."

Only install or extract the archive after this verification succeeds.

Quick Reference

Release TypeCommandTag Format
Skill release./scripts/release-skill.sh <name> <version><name>-v<version>
Pre-release./scripts/release-skill.sh <name> 1.0.0-beta1<name>-v1.0.0-beta1

Release Workflow

Step 1: Determine Version Type

Ask what changed:

  • Bug fixes only → Patch (1.0.0 → 1.0.1)
  • New features, backward compatible → Minor (1.0.0 → 1.1.0)
  • Breaking changes → Major (1.0.0 → 2.0.0)
  • Testing/unstable → Pre-release (1.0.0-beta1, 1.0.0-rc1)

Step 2: Pre-flight Checks

bash
# Check for uncommitted changes
git status

# Verify skill directory exists
ls skills/<skill-name>/skill.json

# Get current version
jq -r '.version' skills/<skill-name>/skill.json

Step 3: Run Release Script

bash
./scripts/release-skill.sh <skill-name> <new-version>

The script will:

  1. Validate version format (semver)
  2. Check tag doesn't already exist
  3. Update skill.json version
  4. Update SKILL.md frontmatter version (if file exists)
  5. Update hardcoded version URLs (feed_url)
  6. Commit changes
  7. Create annotated git tag

Step 4: Push Release

bash
git push && git push origin <skill-name>-v<version>

Step 5: Verify Release

After pushing, the CI/CD pipeline will:

  1. Validate skill exists
  2. Verify version matches skill.json
  3. Verify version matches SKILL.md frontmatter (if exists)
  4. Generate checksums from SBOM
  5. Create .skill package (ZIP)
  6. Create GitHub Release
  7. Trigger website rebuild (for non-internal skills)

Verify at:

  • GitHub Releases: https://github.com/prompt-security/clawsec/releases/tag/<skill-name>-v<version>
  • GitHub Actions: Check workflow run status

Undo a Release (Before Push)

If you need to undo before pushing:

bash
git tag -d <skill-name>-v<version>
git reset --soft HEAD~1

git reset --soft preserves the release changes in your working tree so you can inspect or amend them without discarding data.


Pre-release Versions

For beta, alpha, or release candidates:

bash
./scripts/release-skill.sh <skill-name> 1.2.0-beta1
./scripts/release-skill.sh <skill-name> 1.2.0-alpha1
./scripts/release-skill.sh <skill-name> 1.2.0-rc1

Pre-releases are automatically marked in GitHub Releases.


Common Issues

ErrorSolution
Tag already existsChoose a different version number
Version mismatch in CIEnsure you used the release script (not manual tagging)
SKILL.md version mismatchEnsure you used the release script which updates both skill.json and SKILL.md
Uncommitted changesCommit or stash first: git stash or git add . && git commit
skill.json not foundVerify skill directory path is correct

Internal Skills

Skills with "internal": true in their openclaw section:

  • Are released normally via GitHub Releases
  • Are NOT shown in the public skills catalog website
  • Can still be downloaded directly from release URLs

This skill (claw-release) is an internal skill.


Existing Skills

SkillCategoryInternal
clawsec-feedsecurityNo
clawtributorsecurityNo
openclaw-audit-watchdogsecurityNo
soul-guardiansecurityNo
claw-releaseutilityYes

Verification Checklist

After release, confirm:

  • GitHub Release exists with correct tag
  • Release has: skill.json, SKILL.md, checksums.json, .skill package
  • Release is marked as pre-release if applicable
  • GitHub Actions workflow completed successfully
  • Website updated (for non-internal skills only)

License

GNU AGPL v3.0 or later - See repository for details.

Built by the Prompt Security team.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Claw Release AI skill do?

Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.

Why use Claw Release on TypingMind?

Because you install it once and use it with any model. Claw Release is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Claw Release in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/prompt-security/clawsec/tree/main/skills/claw-release. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Claw Release?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Claw Release?

As many as you like. As long as a model supports skills, you can use Claw Release with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Claw Release AI skill free?

Yes. It is published on GitHub by prompt-security under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇