tool-discovery
npx machina-cli add skill aiskillstore/marketplace/tool-discovery --openclawTool Discovery
Recommend the right agents and skills for any task.
Decision Flowchart
Is this a reference/lookup task?
├── YES → Use a SKILL (lightweight, auto-injects)
└── NO → Does it require reasoning/decisions?
├── YES → Use an AGENT (heavyweight, spawns subagent)
└── MAYBE → Check catalogs below
Rule: Skills = patterns/reference. Agents = decisions/expertise.
Quick Skill Reference
| Skill | Triggers |
|---|---|
| file-search | fd, rg, fzf, find files |
| find-replace | sd, batch replace |
| code-stats | tokei, difft, line counts |
| data-processing | jq, yq, json, yaml |
| structural-search | ast-grep, sg, ast pattern |
| git-workflow | lazygit, gh, delta, rebase |
| python-env | uv, venv, pyproject |
| rest-patterns | http methods, status codes |
| sql-patterns | cte, window functions |
| sqlite-ops | sqlite, aiosqlite |
| tailwind-patterns | tailwind, tw classes |
| mcp-patterns | mcp server, protocol |
Quick Agent Reference
| Agent | Triggers |
|---|---|
| python-expert | Python, async, pytest |
| typescript-expert | TypeScript, types, generics |
| react-expert | React, hooks, state |
| postgres-expert | PostgreSQL, query optimization |
| cloudflare-expert | Workers, KV, D1, R2 |
| Explore | "where is", "find" |
| Plan | design, architect |
How to Launch
Skills:
Skill tool → skill: "file-search"
Agents:
Task tool → subagent_type: "python-expert"
→ prompt: "Your task"
Match by Task Type
| Task | Skill First | Agent If Needed |
|---|---|---|
| "How to write a CTE?" | sql-patterns | sql-expert |
| "Optimize this query" | — | postgres-expert |
| "Find files named X" | file-search | Explore |
| "Set up Python project" | python-env | python-expert |
| "What HTTP status for X?" | rest-patterns | — |
Tips
- Skills are cheaper - Use for lookups, patterns
- Agents are powerful - Use for decisions, optimization
- Don't over-recommend - Max 2-3 tools per task
Additional Resources
For complete catalogs, load:
./references/agents-catalog.md- All agents with capabilities./references/skills-catalog.md- All skills with details
Source
git clone https://github.com/aiskillstore/marketplace/blob/main/skills/0xdarkmatter/tool-discovery/SKILL.mdView on GitHub Overview
tool-discovery guides you to pick the right execution unit for a task, whether a lightweight Skill for quick lookups or a heavyweight Agent for decisions. It clarifies triggers like which agent, which skill, what tool to use, and how to launch the chosen option, helping teams avoid under- or over-engineering their tooling.
How This Skill Works
tool-discovery applies a simple decision flow: is this a reference/lookup task? If YES, use a SKILL (lightweight, auto-injects). If NO, does it require reasoning/decisions? YES → use an AGENT (heavyweight, spawns subagent); otherwise check catalogs below. Skills handle patterns and references, while Agents handle decisions and expertise. Launching is done via the Skill tool for skills and via the Task tool to start an agent.
When to Use It
- When the task is a reference/lookup (e.g., finding files, scanning code, simple data lookups), use a Skill.
- When the task requires reasoning or decisions (e.g., optimizing a query, designing an architecture), use an Agent.
- When you're unsure which path to take, consult the catalogs to guide the match.
- When you want to keep tooling lean, limit to 2-3 tools per task.
- When launching, use the Skill tool to invoke a Skill and the Task tool to spawn an Agent.
Quick Start
- Step 1: Assess the task with the decision flow: is it reference/lookup or does it require reasoning?
- Step 2: If lookup, run Skill tool to invoke a lightweight Skill (for example, file-search). If not, launch a heavyweight Agent with Task tool (subagent_type: python-expert, prompt: Your task).
- Step 3: Optionally consult catalogs and cap recommendations at 2-3 tools.
Best Practices
- Skills are cheaper — prefer Skills for lookups and patterns.
- Agents are powerful — use them for decisions and optimization.
- Don't over-recommend — cap at 2-3 tools per task.
- Use catalogs to guide matching when unsure.
- Launch with correct triggers: Skill tool → skill, Task tool → subagent_type.
Example Use Cases
- Find files named X using the file-search Skill.
- Replace strings across a codebase with the find-replace Skill.
- Optimize this SQL query by routing to the postgres-expert Agent.
- Set up a Python project by selecting python-env for lightweight setup or python-expert for deeper tailoring.
- Evaluate HTTP status strategy with the rest-patterns Skill.
