What makes Agent Skills notable?

2.6K downloads. Trust evidence available

How should Agent Skills be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Agent Skills

Agent Skills standard reference guide. Covers SKILL.md specification format, progressive loading, skill discovery and activation, authoring best practices, quality evaluation, description optimization Skill: Agent Skills Owner: openlark Summary: Agent Skills standard reference guide. Covers SKILL.md specification format, progressive loading, skill discovery and activation, authoring best practices, quality evaluation, description optimization Tags: latest:1.0.1 Version history: v1.0.1 | 2026-06-26T04:57:23.117Z | user - Streamlined the reference section, replacing multiple detailed documents with concise files foc

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.6k

Updated

Oct 9, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.6K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.6K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.1release · observed Jun 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1727wv2g20pc729snzcm4nf8183hy72:agent-skills

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-openlark-agent-skills/snapshot"

Documentation

CLAWHUB

42,081 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agent-skills
description: Agent Skills standard reference guide. Covers SKILL.md specification format, progressive loading, skill discovery and activation, authoring best practices, quality evaluation, description optimization, and more. 
---

# Agent Skills Standard

> A standardized way to equip AI Agents with new capabilities and domain expertise. Adopted by 35+ Agent products.

## Use Cases

Use when creating new skills, validating skill formats, optimizing existing skills, or learning about standardized skill system design.

## Reference File Routing

| Need | Read |
|------|------|
| Quick skill creation (5-step guide) | [quick-start.md](references/quick-start.md) |
| SKILL.md format spec + Agent integration | [spec.md](references/spec.md) |
| Authoring best practices + quality eval + description optimization | [authoring.md](references/authoring.md) |
| Common anti-patterns and fixes | [anti-patterns.md](references/anti-patterns.md) |
| Script binding and design | [using-scripts.md](references/using-scripts.md) |
| Supported product list | [products.md](references/products.md) |

## Minimal Example

```markdown
---
name: pdf-processing
description: Extract PDF text, fill forms, merge files. Use when handling PDFs.
---

## Workflow
1. Extract: `python scripts/extract.py input.pdf`
2. Fill: `python scripts/fill.py template.pdf data.json`

## Gotchas
- Scanned PDFs need OCR first — use `scripts/ocr.py`
```

## Validation

```bash
skills-ref validate ./my-skill
```

_meta.json

{
  "ownerId": "kn75qrtb885pznwsjwsh18dvf1813bv0",
  "slug": "agent-skills",
  "version": "1.0.1",
  "publishedAt": 1782449843117
}

references/anti-patterns.md

# Skill Authoring Anti-Patterns

## 1. Swiss-Army Skill

**Symptom:** Description covers many unrelated features. **Consequence:** Triggers on almost every conversation, wasting tokens and interfering with decisions. **Fix:** One Skill does one thing. Split into multiple Skills if functionality is broad.

## 2. Vague Description

**Symptom:** "Help with development", "Code assistant" — generic phrases. **Consequence:** Extremely high false-trigger rate; fails to trigger when actually needed. **Fix:** Description must include "what" + "when". ❌ "Help with development" → ✅ "Extract PDF text, fill forms. Use when handling PDFs."

## 3. Over-Prescription

**Symptom:** Every step locked down to exact commands and output wording. **Consequence:** Agent loses flexibility, gets stuck on minor deviations. **Fix:** Give direction, not scripts — list "what" (goals) not "how" (exact steps). Use "consider", "may" instead of "must".

## 4. Missing Gotchas

**Symptom:** Only documents happy paths, no known traps. **Consequence:** Agent repeats the same mistakes every new session. **Fix:** Add `## Gotchas` section. Format: problem → cause → solution. Update every time you hit one.

## 5. Monolithic File

**Symptom:** SKILL.md 2000+ lines. **Consequence:** Burns massive tokens on every activation, only 10% actually used. **Fix:** Split at >500 lines into `references/`; main file keeps skeleton + routing table.

## 6. Untested Description

**Symptom:** Ships without ever validating trigger accuracy. **Consequence:** Frequent false triggers or missed triggers in production. **Fix:** Test with 5–10 real prompts before shipping. Ensure relevant scenarios trigger, irrelevant ones don't.

references/authoring.md

# Skill Authoring Guide

Complete methodology for creating high-quality Skills: best practices → description optimization → quality evaluation.

---

## I. Best Practices

### 1.1 Start from Real Experience

Extract reusable patterns from actual tasks (successful steps, human corrections, I/O formats), or synthesize from project docs/runbooks/API specs. Only distill Skills after completing real tasks — never design from scratch.

### 1.2 Refine Through Real Execution

After initial draft, run with real tasks and collect full traces. Look at execution traces, not just output — if the Agent spends time on useless steps, the instructions are too vague or inapplicable.

### 1.3 Context Efficiency

**Add what the Agent lacks, remove what it knows.** For every piece of content ask: "Would the Agent get this wrong without this instruction?" No → delete.

**Design cohesive units.** Too narrow → multiple Skills conflict; too broad → hard to activate precisely. Querying DB + formatting results is a reasonable unit; adding DB administration is too large.

**Use progressive disclosure for large Skills.** SKILL.md <500 lines. Put detailed content in `references/`; tell the Agent in the main file **when** to load them.

### 1.4 Calibration Control

- **Match specificity to fragility**: When multiple approaches work, explain _why_; for fragile operations (e.g., DB migrations), enforce strict sequence
- **Provide defaults, not menus**: Pick one default, briefly mention alternatives
- **Prefer process over declaration**: Teach the Agent **how to approach** problems, not what to produce for specific instances

### 1.5 Effective Instruction Patterns

- **Gotchas**: Most valuable — environment-specific traps the Agent won't know. Update every time you step on one
- **Output templates**: More reliable than descriptive language; short templates in SKILL.md, long ones in `assets/`
- **Checklists**: Checkbox format prevents omissions
- **Verify loop**: Do → run validator → fix → repeat
- **Plan-verify-execute**: For batch/destructive operations, create intermediate plan first
- **Package scripts**: Agent repeatedly writes same logic → write a tested script once in `scripts/`

---

## II. Description Optimization

### 2.1 Trigger Mechanism

Agent loads all `name` + `description` at startup (Tier 1). Match → read full SKILL.md. Complex domain tasks are where description delivers value.

### 2.2 Writing Tips

- Imperative tone: "Use this skill when..."
- Focus on user intent, not internal mechanics
- Be pushy — explicitly list applicable scenarios
- ≤1024 characters

### 2.3 Trigger Eval

~20 queries (8–10 should trigger + 8–10 should not). Most valuable negatives are **near-misses**: share keywords but need something different. Run each query 3×; should-trigger ≥0.5 pass, should-not <0.5 pass. 60% train + 40% validation to prevent overfitting.

### 2.4 Optimization Loop

1. Evaluate current description → 2. Modify using only train failures → 3. Too narrow: broaden; too br

references/products.md

# Products Supporting Agent Skills

Adopted by 35+ products across terminal agents, IDEs, cloud platforms, and frameworks.

| Product | Type |
|---------|------|
| Claude Code | Terminal/IDE |
| GitHub Copilot | IDE |
| Cursor | IDE |
| OpenAI Codex | Terminal/IDE |
| Pi | Terminal |
| Gemini CLI | Terminal |
| VS Code | IDE |
| OpenCode | Terminal/IDE |
| Roo Code | IDE |
| Goose | Terminal |
| Spring AI | Framework |
| Letta | Platform |
| fast-agent | Framework |
| Databricks Genie Code | Platform |
| Laravel Boost | Framework |

## Universal Compatibility Paths

- `~/.agents/skills/` — User-level
- `.agents/skills/` — Project-level

> Full list: [Agent Skills Official Documentation](https://agentskills.io)

Github ReposUpdated 4h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.