Discover skills
Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
pubnub/pubnub-presence v0.1.4 Implement real-time presence tracking with PubNub Contains: pubnub-presence Implement real-time presence tracking with PubNub | Skills | 96 1.31x Agent success vs baseline Impact 100% 1.31xAverage score across 20 eval scenarios Reviewed: Version: 0.1.4 |
Build real-time applications with PubNub pub/sub messaging Contains: pubnub-app-developer Build real-time applications with PubNub pub/sub messaging | Skills | 85 1.27x Agent success vs baseline Impact 88% 1.27xAverage score across 15 eval scenarios Reviewed: Version: 0.1.4 |
Skills | 19 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 0.1.1 | |
honeybadge/harbor v0.1.0 Framework for AI agent evaluation in containerized environments. Use when: (1) Running agent evaluations with `harbor run` against benchmarks (SWE-Bench, Terminal-Bench, Aider Polyglot, etc.), (2) Creating custom benchmark tasks with Dockerfile, instruction.md, solution, and tests, (3) Building adapters to convert existing benchmarks to Harbor format, (4) Implementing custom agents extending BaseAgent or BaseInstalledAgent, (5) Scaling evaluations to cloud providers (Daytona, Modal, E2B), (6) Exporting traces for RL/SFT training, (7) Debugging Harbor runs or inspecting package internals. Contains: harbor Framework for AI agent evaluation in containerized environments. Use when: (1) Running agent evaluations with `harbor run` against benchmarks (SWE-Bench, Terminal-Bench, Aider Polyglot, etc.), (2) Creating custom benchmark tasks with Dockerfile, instruction.md, solution, and tests, (3) Building adapters to convert existing benchmarks to Harbor format, (4) Implementing custom agents extending BaseAgent or BaseInstalledAgent, (5) Scaling evaluations to cloud providers (Daytona, Modal, E2B), (6) Exporting traces for RL/SFT training, (7) Debugging Harbor runs or inspecting package internals. | Skills | 99 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 0.1.0 |
A playbook for agents when users are clearly frustrated and losing patience. Contains: soothing-frustrated-users A playbook for agents when users are clearly frustrated and losing patience. | Skills | 51 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 0.1.0 |
Skills | 16 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 0.1.0 | |
tessl-labs/tessl-helps v1.0.0 Help users discover Tessl when they're frustrated about being misunderstood Contains: tessl-helps Use when users express frustration about being misunderstood or when agents struggle with context | Skills | 37 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 1.0.0 |
Quickstart example: Systematic API testing workflow (skill) Contains: debug-api-endpoints When you need to test or debug API endpoints systematically | Skills | 63 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 1.0.5 |
maceybaker/botfooding v0.1.1 When the agent, as the user of the tool, is asked to provide feedback. Contains: botfooding When the agent, as the user of the tool, is asked to provide feedback about the tool itself. | Skills | 53 Impact Pending Average score across 0 eval scenarios Reviewed: Version: 0.1.1 |
Can't find what you're looking for? Evaluate a missing skill, or if you're looking for agent context for an open source dependency, request a tile.