$ loading_
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
The material indicates a prompt-only skill for creating and maintaining skill files, with no required secrets and no declared remote endpoints. It comes from a highly adopted open-source GitHub repository, so overall risk is low; although the README mentions local validation scripts, there is no sign of extra privileges, data exfiltration, or suspicious behavior.
The material explicitly states that no keys or environment variables are required, and the README does not request login, API tokens, or other sensitive credentials, so credential exposure and misuse risk is low.
No remote endpoints are declared; the content focuses on local skill file structure and validation workflows, with no indication that user data is sent to external services.
The system checks mark it as prompt-only. While the README includes local `python` validation command examples, these are instructional documentation and do not show that the skill itself actively executes code or requests system capabilities.
The description shows that it is used to create, edit, audit, and tidy `AgentSkills` and `SKILL.md` files, so its scope is limited to skill-related text and directory structure guidance; there is no sign of broad access to local data, system configuration, or sensitive resources.
The source is an open-source GitHub repository with extremely high community adoption (about 377k stars), giving it strong auditability and source credibility. The license and maintenance status are not clearly stated, which is a minor information gap but not enough on its own to raise the risk level.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skill-creator" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/skill-creator/SKILL.md 2. Save it as ~/.claude/skills/skill-creator/SKILL.md 3. Reload skills and tell me it's ready
Create a complete SKILL.md for a 'meeting notes assistant', including purpose, inputs/outputs, usage steps, caveats, and examples.
A complete, ready-to-use first draft of a SKILL.md file.
Review this AgentSkill definition for missing fields, inconsistent naming, duplicated explanations, or messy structure, then provide a corrected version.
A list of issues plus a corrected, standardized skill definition.
Restructure this overly long SKILL.md into a clearer hierarchy, preserving meaning while improving readability and maintainability.
A cleaner, better-structured skill document with improved readability.
Skills are compact triggerable workflows. Metadata is always visible; body loads only after trigger; references/scripts/assets load only as needed.
SKILL.md lean; Codex is already capable.description.description.name + description; local OpenClaw skills may also use metadata, homepage, allowed-tools, user-invocable, license.references/; scripts to scripts/; templates/media to assets/.skill-name/
SKILL.md
scripts/ optional deterministic helpers
references/ optional docs loaded only when needed
assets/ optional output resources/templates
agents/ optional UI metadata
---
name: pdf-tools
description: "Inspect, split, merge, OCR, redact, or convert PDFs with local CLI tools."
---
# PDF tools
Use for PDF manipulation. Prefer deterministic scripts for page edits.
## Workflow
1. Inspect file/page count.
2. Choose exact operation.
3. Write output beside input unless user asked otherwise.
4. Render/verify changed pages.
python skills/skill-creator/scripts/quick_validate.py skills/<name>
python - <<'PY'
from pathlib import Path
import yaml
for p in Path("skills").glob("*/SKILL.md"):
text=p.read_text()
if not text.startswith("---\n"):
raise SystemExit(f"missing frontmatter: {p}")
fm=text.split("---",2)[1]
yaml.safe_load(fm)
print("ok")
PY
quick_validate.py is conservative; repo-local frontmatter may allow keys beyond public skill bundles.
Automate OpenClaw nightly releases, branch maintenance, and forward-porting to main.
Debug Node.js apps with inspect, breakpoints, heap, and CPU profiling.
Audit and harden OpenClaw hosts for security and operational health.
List chats, review message history, and send iMessage or SMS from CLI.
Summarize or transcribe URLs, videos, PDFs, and local files quickly.
Generate shareable code or text diffs for review and collaboration.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Turn a repeated workflow into a reusable skill file from the current session.
Compile websites, docs, and repos into SKILL.md packages for coding agents.
Generate reusable AI agent skills and draft configs from website documentation.
Create or refine AI skills with scope, workflows, and tool integrations.