nanocoai/nanoclaw / .claude/skills/add-tavily-tool
add-tavily-tool
VerifiedAdd Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.
| File | Kind | Size |
|---|---|---|
| REMOVE.md | markdown | 1.3 KB |
| SKILL.md | skill md | 7.7 KB |
| tavily-manifest.test.ts | script | 1.3 KB |
| upgrade-instructions.md | markdown | 2.8 KB |
REMOVE.md
View on GitHub# Remove Tavily Tool
Every step is idempotent. Apply it only to groups where `/add-tavily-tool` was
installed.
## 1. Unregister Tavily
List the groups and inspect their configurations:
```bash
ncl groups list
ncl groups config get --id <group-id>
```
For every group with a `tavily` MCP entry:
```bash
ncl groups config remove-mcp-server --id <group-id> --name tavily
```
## 2. Remove the dependency guard
```bash
rm -f src/tavily-manifest.test.ts
```
## 3. Remove the upgrade instructions
For every group whose `instructions.prepend.md` contains the `tavily-upgrade`
block:
```bash
perl -0pi -e 's/\n?<!-- tavily-upgrade:start -->.*?<!-- tavily-upgrade:end -->\n?//s' groups/<group-folder>/instructions.prepend.md
```
No-op when the block is absent.
## 4. Remove the MCP bridge
If `/add-tavily-tool` added `mcp-remote` and no other configured MCP server uses
that command, remove its complete object from `container/cli-tools.json`. Keep
the top-level array valid. Leave a pre-existing or shared entry in place.
Rebuild the image when the manifest changed:
```bash
./container/build.sh
```
## 5. Restart and verify
Restart every affected group:
```bash
ncl groups restart --id <group-id>
```
Confirm the server is absent:
```bash
ncl groups config get --id <group-id>
test ! -e src/tavily-manifest.test.ts
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |