AGENT SKILL

toolkits-integrations

Guides SuperAGI built-in tools, custom toolkits, marketplace tools, tool execution, and toolkit configuration troubleshooting.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
toolkits-integrations
license
MIT
metadata
{ "disco-role": "operating" }
description
Guides SuperAGI built-in tools, custom toolkits, marketplace tools, tool execution, and toolkit configuration troubleshooting.
disable-model-invocation
true

02 资源文件 5

03 SKILL.md 正文

SuperAGI Toolkits and Integrations

Use this sub-skill when the task is about SuperAGI tools, toolkits, marketplace or external tool downloads, toolkit configuration keys, or tool execution failures.

Read First

What This Sub-skill Covers

  • Built-in toolkits and tool classes under superagi/tools.
  • ToolBuilder, ToolExecutor, and toolkit config resolution.
  • tools.json lookup and marketplace/external tool registration.
  • Config-key handling and encrypted toolkit secrets.
  • Safety rules around install_tool_dependencies.sh and network downloads.

Safe Workflow

  1. If a user asks about a tool or toolkit by name, check the built-in inventory first before looking at the dynamic registry.
  2. If a tool is custom or marketplace-backed, distinguish between static source evidence and network-dependent installation behavior.
  3. For an execution failure, determine whether the issue is tool selection, argument validation, missing config, missing dependency, or an external API error.
  4. Avoid triggering marketplace downloads or apt/pip installers unless the downstream user explicitly wants that side effect.

Boundary Notes

  • Agent prompt generation and workflow looping belong to agents-workflows.
  • Public API routes for toolkit CRUD belong to api-service.
  • Resource/vector/provider setup that some tools consume belongs to models-resources-vector.
  • Host deployment and Docker entrypoints that invoke toolkit installers belong to deployment-configuration.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351