New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Development

by sundial-org in sundial-org/awesome-openclaw-skills

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.

MITAuto-check passedAgent Workflows

Install Agent Development

skills CLI
$ npx skills add sundial-org/awesome-openclaw-skills --skill agent-development -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sundial-org/awesome-openclaw-skills agent-development --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sundial-org/awesome-openclaw-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-development .claude/skills/agent-development && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-development
GitHub stars
663
Token cost
~2.4k tokens
SKILL.md length
846 words
Files
8
Skills in repo
383
Repo updated
First seen
Licence
MIT

At a glance

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.

  • Works in 2 steps: Explicit: Task tool subagent_type:… → Automatic: Claude matches task to agent…
  • : creating custom agents
  • SKILL.md covers Agent Description Pattern, Tool Access Principle, Model Selection (Quality First) and Memory Limits, plus 10 more sections
  • Calls claude; reaches api.anthropic.com

What it does

Agent Development is an agent skill from sundial-org/awesome-openclaw-skills. Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files (for example `.claude-plugin/plugin.json`, `README.md` and `rules/agent-memory-limits.md`).

It sits in Agent Workflows, covering Building AI agents, Agent memory and Subagents. It works with Bash and Playwright. The repository describes itself as: Top OpenClaw skills, with the most popular and useful ones. The licence is MIT.

When your agent uses it

  • : creating custom agents
  • Designing agent descriptions for auto-delegation
  • Troubleshooting agent memory issues
  • Building agent pipelines

Example prompts

  • “/agent-development”

Requirements

  • Node.js

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Explicit: Task tool subagent_type: "agent-name" - always works
  2. Automatic: Claude matches task to agent description - requires strong phrasing

What it can do on your machine

Read from SKILL.md and the folder at commit b80cde2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.anthropic.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Development loads about 2.4k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 846 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sundial-org/awesome-openclaw-skills at commit b80cde2, republished under its MIT licence (© sundial-org). 846 words, ~2,438 tokens.

Download SKILL.mdSave it as .claude/skills/agent-development/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
agent-development
description
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.
license
MIT

Agent Development for Claude Code

Build effective custom agents for Claude Code with proper delegation, tool access, and prompt design.

Agent Description Pattern

The description field determines whether Claude will automatically delegate tasks.

Strong Trigger Pattern
yaml
---
name: agent-name
description: |
  [Role] specialist. MUST BE USED when [specific triggers].
  Use PROACTIVELY for [task category].
  Keywords: [trigger words]
tools: Read, Write, Edit, Glob, Grep, Bash
model: sonnet
---
Weak vs Strong Descriptions
Weak (won't auto-delegate)Strong (auto-delegates)
"Analyzes screenshots for issues""Visual QA specialist. MUST BE USED when analyzing screenshots. Use PROACTIVELY for visual QA."
"Runs Playwright scripts""Playwright specialist. MUST BE USED when running Playwright scripts. Use PROACTIVELY for browser automation."

Key phrases:

  • "MUST BE USED when..."
  • "Use PROACTIVELY for..."
  • Include trigger keywords
Delegation Mechanisms
  1. Explicit: Task tool subagent_type: "agent-name" - always works
  2. Automatic: Claude matches task to agent description - requires strong phrasing

Session restart required after creating/modifying agents.

Tool Access Principle

If an agent doesn't need Bash, don't give it Bash.

Agent needs to...Give toolsDon't give
Create files onlyRead, Write, Edit, Glob, GrepBash
Run scripts/CLIsRead, Write, Edit, Glob, Grep, Bash—
Read/audit onlyRead, Glob, GrepWrite, Edit, Bash

Why? Models default to cat > file << 'EOF' heredocs instead of Write tool. Each bash command requires approval, causing dozens of prompts per agent run.

Allowlist Pattern

Instead of restricting Bash, allowlist safe commands in .claude/settings.json:

json
{
  "permissions": {
    "allow": [
      "Write", "Edit", "WebFetch(domain:*)",
      "Bash(cd *)", "Bash(cp *)", "Bash(mkdir *)", "Bash(ls *)",
      "Bash(cat *)", "Bash(head *)", "Bash(tail *)", "Bash(grep *)",
      "Bash(diff *)", "Bash(mv *)", "Bash(touch *)", "Bash(file *)"
    ]
  }
}

Model Selection (Quality First)

Don't downgrade quality to work around issues - fix root causes instead.

ModelUse For
OpusCreative work (page building, design, content) - quality matters
SonnetMost agents - content, code, research (default)
HaikuOnly script runners where quality doesn't matter

Memory Limits

Root Cause Fix (REQUIRED)

Add to ~/.bashrc or ~/.zshrc:

bash
export NODE_OPTIONS="--max-old-space-size=16384"

Increases Node.js heap from 4GB to 16GB.

Parallel Limits (Even With Fix)
Agent TypeMax ParallelNotes
Any agents2-3Context accumulates; batch then pause
Heavy creative (Opus)1-2Uses more memory
Recovery
  1. source ~/.bashrc or restart terminal
  2. NODE_OPTIONS="--max-old-space-size=16384" claude
  3. Check what files exist, continue from there

Sub-Agent vs Remote API

Always prefer Task sub-agents over remote API calls.

AspectRemote API CallTask Sub-Agent
Tool accessNoneFull (Read, Grep, Write, Bash)
File readingMust pass all content in promptCan read files iteratively
Cross-referencingSingle context windowCan reason across documents
Decision qualityGeneric suggestionsSpecific decisions with rationale
Output quality~100 lines typical600+ lines with specifics
typescript
// ❌ WRONG - Remote API call
const response = await fetch('https://api.anthropic.com/v1/messages', {...})

// ✅ CORRECT - Use Task tool
// Invoke Task with subagent_type: "general-purpose"

Declarative Over Imperative

Describe what to accomplish, not how to use tools.

Wrong (Imperative)
markdown
### Check for placeholders
```bash
grep -r "PLACEHOLDER:" build/*.html

### Right (Declarative)

```markdown
### Check for placeholders
Search all HTML files in build/ for:
- PLACEHOLDER: comments
- TODO or TBD markers
- Template brackets like [Client Name]

Any match = incomplete content.
What to Include
IncludeSkip
Task goal and contextExplicit bash/tool commands
Input file paths"Use X tool to..."
Output file paths and formatStep-by-step tool invocations
Success/failure criteriaShell pipeline syntax
Blocking checks (prerequisites)Micromanaged workflows
Quality checklists

Self-Documentation Principle

"Agents that won't have your context must be able to reproduce the behaviour independently."

Every improvement must be encoded into the agent's prompt, not left as implicit knowledge.

What to Encode
DiscoveryWhere to Capture
Bug fix patternAgent's "Corrections" or "Common Issues" section
Quality requirementAgent's "Quality Checklist" section
File path conventionAgent's "Output" section
Tool usage patternAgent's "Process" section
Blocking prerequisiteAgent's "Blocking Check" section
Show full SKILL.md (358 more words)Show less
Test: Would a Fresh Agent Succeed?

Before completing any agent improvement:

  1. Read the agent prompt as if you have no context
  2. Ask: Could a new session follow this and produce the same quality?
  3. If no: Add missing instructions, patterns, or references
Anti-Patterns
Anti-PatternWhy It Fails
"As we discussed earlier..."No prior context exists
Relying on files read during devAgent may not read same files
Assuming knowledge from errorsAgent won't see your debugging
"Just like the home page"Agent hasn't built home page

Agent Prompt Structure

Effective agent prompts include:

markdown
## Your Role
[What the agent does]

## Blocking Check
[Prerequisites that must exist]

## Input
[What files to read]

## Process
[Step-by-step with encoded learnings]

## Output
[Exact file paths and formats]

## Quality Checklist
[Verification steps including learned gotchas]

## Common Issues
[Patterns discovered during development]

Pipeline Agents

When inserting a new agent into a numbered pipeline (e.g., HTML-01 → HTML-05 → HTML-11):

Must UpdateWhat
New agent"Workflow Position" diagram + "Next" field
Predecessor agentIts "Next" field to point to new agent

Common bug: New agent is "orphaned" because predecessor still points to old next agent.

Verification:

bash
grep -n "Next:.*→\|Then.*runs next" .claude/agents/*.md

The Sweet Spot

Best use case: Tasks that are repetitive but require judgment.

Example: Auditing 70 skills manually = tedious. But each audit needs intelligence (check docs, compare versions, decide what to fix). Perfect for parallel agents with clear instructions.

Not good for:

  • Simple tasks (just do them)
  • Highly creative tasks (need human direction)
  • Tasks requiring cross-file coordination (agents work independently)

Effective Prompt Template

For each [item]:
1. Read [source file]
2. Verify with [external check - npm view, API call, etc.]
3. Check [authoritative source]
4. Score/evaluate
5. FIX issues found ← Critical instruction

Key elements:

  • "FIX issues found" - Without this, agents only report. With it, they take action.
  • Exact file paths - Prevents ambiguity
  • Output format template - Ensures consistent, parseable reports
  • Batch size ~5 items - Enough work to be efficient, not so much that failures cascade

Workflow Pattern

1. ME: Launch 2-3 parallel agents with identical prompt, different item lists
2. AGENTS: Work in parallel (read → verify → check → edit → report)
3. AGENTS: Return structured reports (score, status, fixes applied, files modified)
4. ME: Review changes (git status, spot-check diffs)
5. ME: Commit in batches with meaningful changelog
6. ME: Push and update progress tracking

Why agents don't commit: Allows human review, batching, and clean commit history.

Signs a Task Fits This Pattern

Good fit:

  • Same steps repeated for many items
  • Each item requires judgment (not just transformation)
  • Items are independent (no cross-item dependencies)
  • Clear success criteria (score, pass/fail, etc.)
  • Authoritative source exists to verify against

Bad fit:

  • Items depend on each other's results
  • Requires creative/subjective decisions
  • Single complex task (use regular agent instead)
  • Needs human input mid-process

Quick Reference

Agent Frontmatter Template
yaml
---
name: my-agent
description: |
  [Role] specialist. MUST BE USED when [triggers].
  Use PROACTIVELY for [task category].
  Keywords: [trigger words]
tools: Read, Write, Edit, Glob, Grep, Bash
model: sonnet
---
Fix Bash Approval Spam
  1. Remove Bash from tools if not needed
  2. Put critical instructions FIRST (right after frontmatter)
  3. Use allowlists in .claude/settings.json
Memory Crash Recovery
bash
export NODE_OPTIONS="--max-old-space-size=16384"
source ~/.bashrc && claude

© sundial-org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files in skills/agent-development of sundial-org/awesome-openclaw-skills.

  • SKILL.md
  • .claude-plugin/plugin.json
  • README.md
  • rules/agent-memory-limits.md
  • rules/agent-pattern.md
  • rules/agent-self-documentation.md
  • rules/custom-agent-descriptions.md
  • rules/custom-agent-instructions.md

Open the folder on GitHubat commit b80cde2

Compare with similar skills

Agent Development next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Development this skillsundial-org/awesome-openclaw-skills663—~2.4kAutomated safety check: PassMIT
Create Agentvectorize-io/hindsight47k—~1.1kAutomated safety check: PassMIT
Deep Agents Corelangchain-ai/langchain-skills1.3k—~3.1kAutomated safety check: PassMIT
Deep Agentslangchain-ai/docs426—~1.1kAutomated safety check: PassMIT
QAKiln-AI/Kiln5.2k—~3.6kAutomated safety check: PassCustom licence
Agentic Harness Design and ReviewNateBJones-Projects/OB14.7k—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • Create Agent

    vectorize-io/hindsight

    Create a new Hindsight-powered subagent with long-term memory.

    47k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Deep Agents Core

    langchain-ai/langchain-skills

    Official

    Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.

    1.3k GitHub stars~3.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Deep Agents

    langchain-ai/docs

    Official

    Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.

    426 GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • QA

    Kiln-AI/Kiln

    Multi-agent, browser-driven QA pass over a branch or PR — scope it, plan it, fan out one subagent per testing area in its own isolated sandbox, compile a severity-ranked markdown report.

    5.2k GitHub stars~3.6k tokensUpdated today
    Testing & QAAuto-check passed

  • Agentic Harness Design and Review

    NateBJones-Projects/OB1

    Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

    4.7k GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Create Agent

    Apocrathia/home-assistant-config

    Create a new agent persona under .agents/agents/. An agent skill from Apocrathia/home-assistant-config.

    179 GitHub stars~1.1k tokensUpdated 17 days ago
    Agent WorkflowsAuto-check passed

More from sundial-org/awesome-openclaw-skills

All 383 skills in this repo

  • UI UX Pro Max

    sundial-org/awesome-openclaw-skills

    UI/UX design intelligence and implementation guidance for building polished interfaces.

    663 GitHub starsUsed in 2 repos~657 tokens
    Auto-check passed

  • Web Deploy GitHub

    sundial-org/awesome-openclaw-skills

    Create and deploy single-page static websites to GitHub Pages with autonomous workflow.

    663 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Clawd Modifier

    sundial-org/awesome-openclaw-skills

    Modify Clawd, the Claude Code mascot. An agent skill from sundial-org/awesome-openclaw-skills.

    663 GitHub stars~625 tokensUpdated 7 mo ago
    Auto-check passed

  • Figma

    sundial-org/awesome-openclaw-skills

    Professional Figma design analysis and asset export. An agent skill from sundial-org/awesome-openclaw-skills.

    663 GitHub stars~1.7k tokensUpdated 7 mo ago
    Auto-check: notes

  • Habit Flow

    sundial-org/awesome-openclaw-skills

    AI-powered atomic habit tracker with natural language logging, streak tracking, smart reminders, and coaching.

    663 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

  • Edge Tts

    sundial-org/awesome-openclaw-skills

    Text-to-speech conversion using node-edge-tts npm package for generating audio from text.

    663 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

Works with

Categories

Questions about Agent Development

What does Agent Development do?

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Agent Development is an agent skill from sundial-org/awesome-openclaw-skills. Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.

When should I use Agent Development?

Agent Development fits situations like: : creating custom agents; designing agent descriptions for auto-delegation; troubleshooting agent memory issues; building agent pipelines.

How do I install Agent Development in Claude Code?

Run `npx skills add sundial-org/awesome-openclaw-skills --skill agent-development -a claude-code`. Or copy the skill folder (skills/agent-development in sundial-org/awesome-openclaw-skills) into .claude/skills/agent-development in your project. Claude Code loads it when a task matches its description.

How do I install Agent Development in Codex?

Run `npx skills add sundial-org/awesome-openclaw-skills --skill agent-development -a codex`. Or copy the skill folder (skills/agent-development in sundial-org/awesome-openclaw-skills) into .agents/skills/agent-development in your project. Codex loads it when a task matches its description.

Can I use Agent Development in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sundial-org/awesome-openclaw-skills --skill agent-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-development, .gemini/skills/agent-development, .github/skills/agent-development and .opencode/skills/agent-development in your project.

What does Agent Development need to run?

Going by SKILL.md and its folder, Agent Development needs the command-line tools its instructions call (claude). Our summary lists: Node.js.

Does Agent Development access the network?

SKILL.md names 1 domain. In commands or code: api.anthropic.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Agent Development safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Development use?

Agent Development is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Development use?

About 2.4k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Development?

Skills that share tags, products or a category with Agent Development: Create Agent (vectorize-io/hindsight, 47k stars), Deep Agents Core (langchain-ai/langchain-skills, 1.3k stars), Deep Agents (langchain-ai/docs, 426 stars) and QA (Kiln-AI/Kiln, 5.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Development?

sundial-org (a GitHub organization) maintains it in sundial-org/awesome-openclaw-skills, which has 663 GitHub stars. The repository holds 383 skills in this directory. The repository was last updated on March 7, 2026.

Source: sundial-org/awesome-openclaw-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.