Discover agentic
Automatically discover agentic workflow skills when building AI agents, implementing tool use patterns, managing context windows, decomposing complex tasks, or designing multi-step autonomous workflows. Activates for agentic AI development.From its SKILL.md
npx -y skills add kenantang/codex-and-claude-skills --skill discover-agenticAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
5.5 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it
Agentic Workflow Skills Discovery
Provides automatic access to skills for building autonomous AI agents, managing tool use, and orchestrating multi-step workflows.
When This Skill Activates
This skill auto-activates when you're working with:
- AI agent development and autonomous workflows
- Task decomposition for LLM agents
- Function calling and tool use patterns
- Context window management and summarization
- Working memory, scratchpads, and state tracking
- Long-term memory and persistence patterns
- Multi-step reasoning and planning
- Failure recovery and re-planning strategies
- Parallel vs sequential execution decisions
Available Skills
Quick Reference
The Agentic category contains 3 specialized skills:
- agentic-task-decomposition - Breaking complex goals into agent-executable steps, dependency graphs, re-planning
- agentic-tool-use - Function calling patterns, parallel tool use, error handling, tool selection heuristics
- agentic-memory - Context window management, working memory, long-term persistence, summarization
Load Full Category Details
For complete descriptions and workflows:
Read ../agentic/INDEX.md
This loads the full Agentic category index with:
- Detailed skill descriptions
- Usage triggers for each skill
- Common workflow combinations
- Cross-references to related skills
Load Specific Skills
Load individual skills as needed:
Task planning and decomposition
Read ../agentic/agentic-task-decomposition.md
Tool calling and execution
Read ../agentic/agentic-tool-use.md
Context and memory management
Read ../agentic/agentic-memory.md
Common Workflows
Building an Agent from Scratch
Sequence: Decomposition -> Tool Use -> Memory
Read ../agentic/agentic-task-decomposition.md # Plan the agent's task handling Read ../agentic/agentic-tool-use.md # Implement tool execution Read ../agentic/agentic-memory.md # Add context management
Adding Tool Use to an Agent
Sequence: Tool Use -> Decomposition
Read ../agentic/agentic-tool-use.md # Tool calling patterns Read ../agentic/agentic-task-decomposition.md # Multi-tool task planning
Scaling Agent Sessions
Sequence: Memory -> Decomposition
Read ../agentic/agentic-memory.md # Context management Read ../agentic/agentic-task-decomposition.md # Context-bounded task sizing
Complete Agentic Stack
Full implementation:
1. Planning layer
Read ../agentic/agentic-task-decomposition.md
2. Execution layer
Read ../agentic/agentic-tool-use.md
3. Memory layer
Read ../agentic/agentic-memory.md
Skill Selection Guide
Choose task decomposition when:
- Complex goal needs breaking into steps
- Tasks have dependencies or ordering constraints
- Need to handle ambiguous requirements
- Building a planning layer for an agent
Choose tool use when:
- Implementing function calling in an LLM agent
- Debugging tool call failures or inefficiency
- Designing tool schemas and structured outputs
- Optimizing multi-tool workflows
Choose memory when:
- Agent sessions are hitting context limits
- Need to persist state across turns or sessions
- Building multi-turn conversational agents
- Implementing retrieval-augmented generation
Integration with Other Skills
Agentic skills commonly combine with:
API skills (discover-api):
- Agents that call REST/GraphQL APIs
- Tool schemas for API endpoints
- Authentication handling in agent workflows
Testing skills (discover-testing):
- Testing agent behaviors and tool use
- Autonomous test generation
- Verifying agent task completion
Database skills (discover-database):
- Database-backed agent memory
- Agents that query and modify data
- Persistent state management
Infrastructure skills (discover-infra, discover-cloud):
- Deploying agent systems
- Scaling agent workloads
- Cost optimization for LLM calls
Usage Instructions
- Auto-activation: This skill loads automatically when Claude Code detects agentic workflow tasks
- Browse skills: Run
Read ../agentic/INDEX.mdfor full category overview - Load specific skills: Use commands above to load individual skills
- Follow workflows: Use recommended sequences for common agentic patterns
- Combine skills: Load multiple skills for comprehensive coverage
Progressive Loading
This gateway skill (~200 lines, ~2K tokens) enables progressive loading:
- Level 1: Gateway loads automatically (you're here now)
- Level 2: Load category INDEX.md (~3K tokens) for full overview
- Level 3: Load specific skills (~2-3K tokens each) as needed
Total context: 2K + 3K + skill(s) = 5-10K tokens vs 12K+ for entire category.
Quick Start Examples
"Build an autonomous coding agent": Read ../agentic/agentic-task-decomposition.md
"How should my agent call tools?": Read ../agentic/agentic-tool-use.md
"My agent is running out of context": Read ../agentic/agentic-memory.md
Next Steps: Run Read ../agentic/INDEX.md to see full category details, or load specific skills using the commands above.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in ~1.1k tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- read the agentic category index for full details
- load specific agentic skills as needed
- follow recommended sequences for common agentic patterns
- combine multiple agentic skills for comprehensive coverage
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.