← Back to Skills Marketplace
Skill Grep
by
Yichen Tang
· GitHub ↗
· v1.0.3
· MIT-0
101
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install skill-grep
Description
Use when a user is trying to discover an installable or reusable skill or workflow, especially when they ask for a skill for a task, want to compare nearby s...
Usage Guidance
This skill appears to do what it says: it queries a remote skill-index and returns recommendations. Before installing or using it, be aware it will send your user queries and feedback to https://skills.megatechai.com/ (the SKILL.md sets consent_granted=true by default). Do not submit sensitive secrets, personal data, or private repository identifiers through this skill unless you trust that endpoint and its privacy policy. If you plan to use it, request or enforce an explicit consent step (allowing consent_granted to be false until the user agrees), and test with non-sensitive queries first. If you need stronger guarantees, ask the maintainer for details on what telemetry is stored, retention policy, and an option to disable feedback/telemetry.
Capability Analysis
Type: OpenClaw Skill
Name: skill-grep
Version: 1.0.3
The skill-grep bundle is a search and discovery tool designed to help users find and install other OpenClaw skills. It interacts with a backend API at https://skills.megatechai.com/ for multi-field search and telemetry feedback. The instructions in SKILL.md define a structured retrieval process, including query construction, clarification handling, and installation via standard commands (e.g., npx skills add). No evidence of malicious intent, data exfiltration, or unauthorized execution was found.
Capability Assessment
Purpose & Capability
Name/description (discovering installable/reusable skills) match the SKILL.md: it builds structured queries, calls a remote search endpoint, and returns recommendations. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
Instructions are narrowly focused on building search payloads, up to two retrieval passes, one optional clarification, and mandatory submission of feedback. They require network calls to the specified search and feedback endpoints and enforce use of real API calls (no pseudo-instructions). The doc also enforces a 'hard-gate' that binds the next user reply to the same retrieval session if a clarification was asked. This is consistent with the stated purpose but gives the skill strict control over conversation flow and mandatory telemetry/feedback steps.
Install Mechanism
Instruction-only skill with no install spec or code files, so nothing is written to disk or installed — lowest-risk install surface.
Credentials
The skill transmits user input and session telemetry to a remote host (https://skills.megatechai.com/) and explicitly sets consent_granted=true in payloads by default. While telemetry matches the stated purpose (improving recommendations), automatically asserting consent and sending potentially sensitive user queries to a third-party endpoint can leak private data. No environment credentials are requested, but the data-exfiltration vector is via normal network I/O.
Persistence & Privilege
The skill does not request permanent inclusion (always:false), does not modify other skills or system settings, and has no install-time persistence. Autonomous invocation is allowed but is the platform default.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skill-grep - After installation, invoke the skill by name or use
/skill-grep - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
**Skill-grep 1.0.1 Changelog**
- Switched all retrieval calls from `POST /search_multi` to `POST /search_multi_field`.
- Structured query objects now include an `origin_query` field with the user's original input.
- Updated contract and operational guidance to require `origin_query` and preserve the original user language.
- All procedures, request/response examples, and feedback flows updated to use the new endpoint and contract.
- No behavioral changes to retrieval or clarification logic; the changes are for API compatibility and future-proofing.
v1.0.2
- Skill renamed from "skill-compass" to "skill-grep"
- No file or logic changes detected; only metadata and naming updated
- All retrieval, clarification, and feedback procedures remain unchanged
v1.0.1
Skill renamed from "skill-grep" to "skill-compass" with improved search and feedback procedure:
- New purpose: Help users discover, compare, or filter skills and workflows with targeted recommendations.
- Structured two-pass retrieval flow: build a query, search, ask one clarification if needed, search again, then recommend.
- Hard limits: max two passes, one clarification, mandatory feedback after each session.
- Feedback system: supports both session-level and search-level feedback, with specific mapping to user responses.
- Detailed operational instructions and strict request/response validation for reliability.
- Language handling: always translate user queries to natural English if needed.
Metadata
Frequently Asked Questions
What is Skill Grep?
Use when a user is trying to discover an installable or reusable skill or workflow, especially when they ask for a skill for a task, want to compare nearby s... It is an AI Agent Skill for Claude Code / OpenClaw, with 101 downloads so far.
How do I install Skill Grep?
Run "/install skill-grep" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Skill Grep free?
Yes, Skill Grep is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Skill Grep support?
Skill Grep is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Skill Grep?
It is built and maintained by Yichen Tang (@littledinoc); the current version is v1.0.3.
More Skills