jacob-bd/universal-skills-manager

compatibility: "Requires python3, curl, and network access to skillsmp.com, skills.palebluedot.live, clawhub.ai, and github.com" metadata:   homepage: https://github.com/jacob-bd/universal-skills-manager

metadata:   homepage: https://github.com/jacob-bd/universal-skills-manager   disable-model-invocation: "true"

homepage: https://github.com/jacob-bd/universal-skills-manager   disable-model-invocation: "true"   requires-bins: "python3, curl"

[Credential-related source omitted]

**Workaround:** Use Claude Code CLI instead, which has unrestricted network access and works with all three skill sources. You can install via: `curl -fsSL https://raw.githubusercontent.com/jacob-bd/universal-skills-manager/main/install.sh 

**Workaround:** Use Claude Code CLI instead, which has unrestricted network access and works with all three skill sources. You can install via: `curl -fsSL https://raw.githubusercontent.com/jacob-bd/universal-skills-manager/main/install.sh 

```bash     python3 ~/.claude/skills/universal-skills-manager/scripts/install_skill.py \       --url "https://github.com/{owner}/{repo}/tree/{branch}/{skill-folder}" \

--url "https://github.com/{owner}/{repo}/tree/{branch}/{skill-folder}" \

rm -rf {target_skills_dir}/{skill-name}

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

*   **Key Validation:** SkillsMP API keys always start with `sk_live_skillsmp_`. If the user provides a key that does not match this prefix, reject it immediately:         > "That doesn't look like a valid SkillsMP API key. Keys start with 

> "That doesn't look like a valid SkillsMP API key. Keys start with `sk_live_skillsmp_`. You can get one at https://skillsmp.com — or choose SkillHub/ClawHub search instead (no key needed)."

-   **Keyword Search** (`/api/v1/skills/search`): For specific terms, exact matches         -   **AI Semantic Search** (`/api/v1/skills/ai-search`): For natural language queries (e.g., "help me debug code")     -   **IMPORTANT:** Always cap

-   **AI Semantic Search** (`/api/v1/skills/ai-search`): For natural language queries (e.g., "help me debug code")     -   **IMPORTANT:** Always capture the API key into a local variable first, then use it. Direct `$SKILLSMP_API_KEY` expans

[Credential-related source omitted]

[Credential-related source omitted]

-   **IMPORTANT:** Always include a `User-Agent` header. SkillsMP is behind Cloudflare, which blocks bare curl requests (403 Forbidden).

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

curl -X GET "https://skillsmp.com/api/v1/skills/search?q={query}&limit=20&sortBy=recent" \

[Credential-related source omitted]

# AI Semantic Search (for natural language queries)         curl -X GET "https://skillsmp.com/api/v1/skills/ai-search?q={query}" \

curl -X GET "https://skillsmp.com/api/v1/skills/ai-search?q={query}" \

[Credential-related source omitted]

```bash         # SkillHub Search (no authentication required)         curl -X GET "https://skills.palebluedot.live/api/skills?q={query}&limit=20" \

# SkillHub Search (no authentication required)         curl -X GET "https://skills.palebluedot.live/api/skills?q={query}&limit=20" \           -H "User-Agent: Universal-Skills-Manager"

curl -X GET "https://skills.palebluedot.live/api/skills?q={query}&limit=20" \

```bash         # Semantic Search (vector/similarity search)         curl -X GET "https://clawhub.ai/api/v1/search?q={query}&limit=20" \

# Semantic Search (vector/similarity search)         curl -X GET "https://clawhub.ai/api/v1/search?q={query}&limit=20" \           -H "User-Agent: Universal-Skills-Manager"

curl -X GET "https://clawhub.ai/api/v1/search?q={query}&limit=20" \

# Browse by stars, downloads, or trending         curl -X GET "https://clawhub.ai/api/v1/skills?limit=20&sort=stars" \

curl -X GET "https://clawhub.ai/api/v1/skills?limit=20&sort=stars" \

*   Ask: "Would you like to include your SkillsMP API key for curated search? This is optional — SkillHub and ClawHub work without a key. If you skip this, the packaged skill will still work for SkillHub and ClawHub searches."     *   If us

*   If user wants to include a key:         -   Ask: "Please provide your SkillsMP API key. You can get one at https://skillsmp.com"         -   Wait for user to provide the key

-   Ask: "Please provide your SkillsMP API key. You can get one at https://skillsmp.com"

[Credential-related source omitted]

[Credential-related source omitted]

2.  **Conflict Safety:** If a skill already exists at a target location, **always** ask before overwriting, unless the user explicitly requested a "Force Sync." 3.  **Sync Safety:** The `sync_skills.py` script is read-only — it only reports

3.  **Sync Safety:** The `sync_skills.py` script is read-only — it only reports status and never modifies files. All write operations (copy, overwrite, deploy, delete) are performed by the agent and require explicit user approval before exe

4.  **User-Agent Required:** Always include `-H "User-Agent: Universal-Skills-Manager"` in all curl requests. APIs behind Cloudflare (like SkillsMP) return 403 Forbidden for bare curl requests without a User-Agent header.

*   If OpenCode or Antigravity require a specific manifest (e.g., `manifest.json`), generate a basic one based on the `SKILL.md` frontmatter during installation. 7.  **Cloud Platform Frontmatter Compatibility Check (claude.ai / Claude Deskt

When a user wants to upload or package a skill for **claude.ai**, **Claude Desktop**, or **ChatGPT**, validate the SKILL.md frontmatter against the [Agent Skills specification](https://agentskills.io/specification). All three platforms use 

-   Convert `githubUrl` to raw content URL:         ```         Input:  https://github.com/{user}/{repo}/tree/{branch}/{path}

```         Input:  https://github.com/{user}/{repo}/tree/{branch}/{path}         Output: https://raw.githubusercontent.com/{user}/{repo}/{branch}/{path}/SKILL.md

Input:  https://github.com/{user}/{repo}/tree/{branch}/{path}

Output: https://raw.githubusercontent.com/{user}/{repo}/{branch}/{path}/SKILL.md         ```     -   Fetch the SKILL.md content using curl or web_fetch

-   Fetch the SKILL.md content using curl or web_fetch

-   Use the skill's `id` from the search result to get full details:         ```bash         curl -X GET "https://skills.palebluedot.live/api/skills/{id}"

```bash         curl -X GET "https://skills.palebluedot.live/api/skills/{id}"         ```

curl -X GET "https://skills.palebluedot.live/api/skills/{id}"

-   Build the GitHub tree URL from the detail response:         ```         https://github.com/{githubOwner}/{githubRepo}/tree/{branch}/{skillPath}

```         https://github.com/{githubOwner}/{githubRepo}/tree/{branch}/{skillPath}         ```

https://github.com/{githubOwner}/{githubRepo}/tree/{branch}/{skillPath}

-   Example: `https://github.com/wshobson/agents/tree/main/plugins/developer-essentials/skills/debugging-strategies`

```bash         python3 ~/.claude/skills/universal-skills-manager/scripts/install_skill.py \           --url "https://github.com/{githubOwner}/{githubRepo}/tree/{branch}/{skillPath}" \

--url "https://github.com/{githubOwner}/{githubRepo}/tree/{branch}/{skillPath}" \

-   Use ClawHub's file endpoint to get the raw SKILL.md:         ```bash         curl -s "https://clawhub.ai/api/v1/skills/{slug}/file?path=SKILL.md" \

```bash         curl -s "https://clawhub.ai/api/v1/skills/{slug}/file?path=SKILL.md" \           -H "User-Agent: Universal-Skills-Manager" \

curl -s "https://clawhub.ai/api/v1/skills/{slug}/file?path=SKILL.md" \

-   If the skill has additional files (scripts, configs), use ClawHub's download endpoint:         ```bash         curl -s "https://clawhub.ai/api/v1/download?slug={slug}" \

```bash         curl -s "https://clawhub.ai/api/v1/download?slug={slug}" \           -H "User-Agent: Universal-Skills-Manager" \

curl -s "https://clawhub.ai/api/v1/download?slug={slug}" \

rm -rf /tmp/clawhub-{slug}/ /tmp/clawhub-{slug}.zip

rm -rf {target_skills_dir}/{skill-name}

**Base URL:** `https://skillsmp.com/api/v1`

[Credential-related source omitted]

"author": "AuthorName",         "description": "...",         "githubUrl": "https://github.com/user/repo/tree/main/path",

"description": "...",         "githubUrl": "https://github.com/user/repo/tree/main/path",         "skillUrl": "https://skillsmp.com/skills/...",

"githubUrl": "https://github.com/user/repo/tree/main/path",

"skillUrl": "https://skillsmp.com/skills/...",

**Base URL:** `https://skills.palebluedot.live/api`

**Base URL:** `https://clawhub.ai/api/v1`

[Credential-related source omitted]

#!/usr/bin/env python3

Usage:     python3 install_skill.py --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "~/.claude/skills/my-skill"

python3 install_skill.py --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "~/.claude/skills/my-skill"

[Credential-related source omitted]

Input:  https://github.com/{owner}/{repo}/tree/{branch}/{path}

https://github.com/{owner}/{repo}/tree/{branch}  (root level)

if path:         encoded_path = '/'.join(quote(p, safe='') for p in path.split('/'))         return f"https://raw.githubusercontent.com/{owner}/{repo}/{branch}/{encoded_path}/{encoded_filename}"

encoded_path = '/'.join(quote(p, safe='') for p in path.split('/'))         return f"https://raw.githubusercontent.com/{owner}/{repo}/{branch}/{encoded_path}/{encoded_filename}"     else:

return f"https://raw.githubusercontent.com/{owner}/{repo}/{branch}/{encoded_path}/{encoded_filename}"

return f"https://raw.githubusercontent.com/{owner}/{repo}/{branch}/{encoded_filename}"

if path:         return f"https://api.github.com/repos/{owner}/{repo}/contents/{path}?ref={branch}"

return f"https://api.github.com/repos/{owner}/{repo}/contents/{path}?ref={branch}"

return f"https://api.github.com/repos/{owner}/{repo}/contents?ref={branch}"

request = urllib.request.Request(url, headers=headers)

try:         with urllib.request.urlopen(request, timeout=30) as response:

with urllib.request.urlopen(request, timeout=30) as response:

request = urllib.request.Request(url, headers=headers)

try:         with urllib.request.urlopen(request, timeout=30) as response:

with urllib.request.urlopen(request, timeout=30) as response:

epilog=""" Examples:   %(prog)s --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "~/.claude/skills/my-skill"

Examples:   %(prog)s --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "~/.claude/skills/my-skill"   %(prog)s --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "/tmp/test" --dry-run

%(prog)s --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "~/.claude/skills/my-skill"

%(prog)s --url "https://github.com/user/repo/tree/main/skills/my-skill" --dest "/tmp/test" --dry-run

if not parsed:         print("Error: Invalid GitHub URL format", file=sys.stderr)         print("Expected: https://github.com/{owner}/{repo}/tree/{branch}/{path}", file=sys.stderr)

print("Error: Invalid GitHub URL format", file=sys.stderr)         print("Expected: https://github.com/{owner}/{repo}/tree/{branch}/{path}", file=sys.stderr)         sys.exit(2)

print("Expected: https://github.com/{owner}/{repo}/tree/{branch}/{path}", file=sys.stderr)

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

"Obfuscated execution via eval(base64...) — supply chain / code injection risk (SC3)"),

"Obfuscated remote code execution via exec(urllib/requests) — supply chain risk (SC3)"),

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

#!/usr/bin/env python3

Validates and optionally fixes SKILL.md YAML frontmatter to comply with the Agent Skills specification (https://agentskills.io/specification).

Agent Skills specification (https://agentskills.io/specification).

[Credential-related source omitted]

Executable file