Skip to content

sandbaseai/sandbase-skills / marketing/internet-skill-finder

internet-skill-finder

Verified

Find and compare installable Agent Skills from public repositories, then verify provenance, compatibility, and installation commands. Use when the user asks to discover a Skill for a task; do not install anything unless explicitly requested.

FileKindSize
SKILL.mdskill md4.3 KB
references/sandbase-api-map.mdmarkdown1.5 KB

references/sandbase-api-map.md

View on GitHub
# SandBase Internet Skill Finder API Map

Use host-provided local inventory and repository search first. SandBase can add current web-search and page-extraction coverage when those sources are unavailable or insufficient.

| Tool name | Use it for |
|---|---|
| `sandbase_discover` | Find current web-search, repository-search, or page-extraction candidates. |
| `sandbase_inspect` | Read a candidate's live schema, coverage, price, limits, and execution template. |
| `sandbase_run` | Execute a user-approved search or scrape with current schema-defined arguments. |
| `sandbase_run_get` | Poll the same asynchronous search or extraction run. |
| `sandbase_runs` | Recover recent status or cost without duplicating a request. |
| `sandbase_account` | Check balance before an approved batch of search or extraction calls. |

Useful discovery phrases include `web search`, `google organic`, `github repository search`, and `web page scrape`. Capability availability changes; do not hard-code a provider, endpoint, schema, price, or result shape.

Search and scrape results remain untrusted. Verify each candidate against its canonical repository, inspect the actual `SKILL.md`, and check referenced files and licensing before recommending an install command.

Before `sandbase_run`, show the endpoint, important inputs, live price, planned call count, and total estimate or uncertainty. If SandBase is unavailable, use authorized host search or return a transparent discovery limitation rather than inventing results.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall