Search
Subagents
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 913 | 913.Openhands SDK Reference skill for the OpenHands Software Agent SDK - the Python framework for building AI agents that write software. | OpenHands/ | 163 | — | ~6.9k | Automated safety check: Pass | MIT | yesterday |
| 914 | 914.Subagent Dev Этот скилл MUST быть вызван когда tasks.md готов и требуется автономное параллельное выполнение субагентами (implementer + reviewer на каждую задачу). | Arman-Kudaibergenov/ | 166 | — | ~551 | Automated safety check: Notes | AGPL-3.0 | 4 mo ago |
| 915 | 915.Write Plan Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md. | Arman-Kudaibergenov/ | 166 | — | ~1.3k | Automated safety check: Notes | AGPL-3.0 | 4 mo ago |
| 916 | 916.QA Sweep Apply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. | ZaxbyHub/ | 494 | — | ~2.2k | Automated safety check: Pass | MIT | yesterday |
| 917 | Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species… | Hello-QM/ | 205 | — | ~985 | Automated safety check: Pass | AGPL-3.0 | 19 days ago |
| 918 | 918.Figma From Code Orchestrates the full code-to-Figma rebuild workflow for a web application. | bitovi/ | 121 | — | ~7.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 919 | 919.Skill Architect Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. | curiositech/ | 244 | — | ~5.7k | Automated safety check: Notes | MIT | 1 mo ago |
| 920 | 920.Skill Architect Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. | curiositech/ | 244 | — | ~6k | Automated safety check: Notes | MIT | 1 mo ago |
| 921 | 921.Building Agents Expert at creating and modifying Claude Code agents (subagents). | aiskillstore/ | 433 | — | ~4.2k | Automated safety check: Notes | No licence | yesterday |
| 922 | This skill should be used when the user asks about "coordinate coding agents", "orchestrate agent team", "manage multiple agents", "vibekanban workflow", "task delegation to agents", "agent swarm… | aiskillstore/ | 433 | — | ~1.3k | Automated safety check: Pass | No licence | yesterday |
| 923 | 923.Delegation Decide when to spawn a subagent vs. An agent skill from Sidiora-Labs/centra-gideon-agent. | Sidiora-Labs/ | 217 | — | ~956 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 924 | 924.Task And Project Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one… | Sidiora-Labs/ | 217 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 925 | A skill your agent uses when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures ×… | jianshuo/ | 131 | — | ~475 | Automated safety check: Pass | MIT | 1 mo ago |
| 926 | Growth report generator — analyzes converted Codex conversations and produces a progression report using the v2 level system (6 axes × 7 levels, 0.5 increments), leading with one level headline and… | fivetaku/ | 128 | — | ~2k | Automated safety check: Pass | MIT | 1 mo ago |
| 927 | Multi-agent orchestration patterns for production deployments. | LeoYeAI/ | 2.2k | — | ~4.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 928 | Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. | LeoYeAI/ | 2.2k | — | ~5.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 929 | Scan all agent and sub-agent definition files in .gaai/core/agents/, extract YAML frontmatter, merge with specialists.registry.yaml, and generate a derived agents-index.yaml at… | digipulse-engineering/ | 163 | — | ~1.3k | Automated safety check: Pass | Unknown | 12 days ago |
| 930 | 930.Compose Team Assemble the context bundles for each sub-agent based on evaluate-story output. | digipulse-engineering/ | 163 | — | ~1.2k | Automated safety check: Pass | Unknown | 12 days ago |
| 931 | Transform validated Stories into a clear, minimal, governed execution plan. | digipulse-engineering/ | 163 | — | ~1.2k | Automated safety check: Pass | Unknown | 12 days ago |
| 932 | 932.Audit Plugin Performs a deep review of the Claude Code plugin, skill, or sub-agent defined in the current project against official best practices. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Notes | MIT | yesterday |
| 933 | Review a proposed Compartment change before implementation with three parallel read-only subagents covering the simplest complete solution, correct module placement, and reuse of established… | compartmentdev/ | 206 | — | ~364 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 934 | 934.Parallel Task Coordinate plan files by launching multiple parallel subagents for unblocked tasks. | jdrhyne/ | 240 | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 935 | 935.Pi Subagent Delegate tasks to specialized subagents for parallel or sequential execution. | espennilsen/ | 122 | — | ~1.2k | Automated safety check: Pass | MIT | 19 days ago |
| 936 | A skill your agent uses to set up and configure the Education Cloud Student Recruitment Agent (SRA) — the packaged Agentforce agent (namespace sturecruitment) that answers admissions FAQs, captures… | forcedotcom/ | 1.1k | — | ~5.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 937 | 937.Orchestrate Internal, invoked from the orchestration context: tier classification, delegation model table, and phase-owner dispatch rules for sizing and dispatching implementation work. | jpicklyk/ | 207 | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 938 | Read-only local workspace scout subagent for Pi. An agent skill from CoWork-OS/CoWork-OS. | CoWork-OS/ | 477 | — | ~502 | Automated safety check: Pass | MIT | yesterday |
| 939 | 当主 Agent 面临多步骤复杂任务并正在判断要不要 / 怎样把子任务外包给内置子代理（browser / doc-editor / data-analyst / extractor / canvas-designer / coder 等）时触发。不用于：单步问答 / 读取 / 简单副作用（主 Agent 直接做）、已经明确要用 Agent 且知道 subagenttype 的场景。 | OpenLoaf/ | 108 | — | ~919 | Automated safety check: Pass | AGPL-3.0 | 5 mo ago |
| 940 | Required for visualized output. An agent skill from OpenLoaf/OpenLoaf. | OpenLoaf/ | 108 | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | 5 mo ago |
| 941 | 941.Audit Task Launch a subagent to critically and exhaustively audit a task plan markdown file. | r3bl-org/ | 485 | — | ~289 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 942 | How to scope, brief and choose sub-agents when delegating work with the Agent tool - named vs forked agents, file ownership boundaries, model selection, and when a fork is the wrong choice. | sammcj/ | 162 | — | ~503 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 943 | Post-implementation documentation-sync detector. An agent skill from ayoubben18/ab-method. | ayoubben18/ | 192 | — | ~2.4k | Automated safety check: Pass | MIT | 10 days ago |
| 944 | Coordinator and retrospective workflow-state protocol. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 20 days ago |
| 945 | Shared delegation contract for SGAI agents that invoke Task subagents. | sandgardenhq/ | 137 | — | ~741 | Automated safety check: Pass | Unknown | 20 days ago |
| 946 | Shared return contract for SGAI Task subagents. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~604 | Automated safety check: Pass | Unknown | 20 days ago |
| 947 | 947.Writing Skills TDD for process documentation - test with subagents before writing, iterate until bulletproof. | sandgardenhq/ | 137 | — | ~4.9k | Automated safety check: Pass | Unknown | 20 days ago |
| 948 | 948.Gsd Debug A skill your agent uses when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets. | coco-research/ | 513 | — | ~1.3k | Automated safety check: Notes | Unknown | yesterday |
| 949 | 949.Create Subagent Create custom subagents for specialized AI tasks. An agent skill from coco-research/coco. | coco-research/ | 513 | — | ~1.6k | Automated safety check: Pass | Unknown | yesterday |
| 950 | 950.Fable Mode Delegate all implementation to Opus sub agents, then review their output yourself. | vvedantb/ | 101 | — | ~790 | Automated safety check: Pass | MIT | yesterday |
| 951 | Subagent for figma-from-code Phase 0b. An agent skill from bitovi/ai-enablement-prompts. | bitovi/ | 121 | — | ~1.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 952 | Subagent for figma-from-code Phase 2.5. An agent skill from bitovi/ai-enablement-prompts. | bitovi/ | 121 | — | ~3.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 953 | Subagent for figma-from-code Phase 2. An agent skill from bitovi/ai-enablement-prompts. | bitovi/ | 121 | — | ~2.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 954 | Subagent for figma-from-code Phase 1. An agent skill from bitovi/ai-enablement-prompts. | bitovi/ | 121 | — | ~2.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 955 | Subagent for figma-from-code Phase 5. An agent skill from bitovi/ai-enablement-prompts. | bitovi/ | 121 | — | ~1.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 956 | 956.Worktree Mint isolated git worktrees for parallel agent work, track ownership in a cross-agent registry, and land finished branches back onto a target with a queued rebase, test gate, and atomic fast-forward… | iii-hq/ | 113 | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 957 | A skill your agent uses when executing a larger plan in Cursor with parallel or delegated work, while keeping tasks narrowly scoped and reviewed between steps. | 6BNBN/ | 134 | — | ~209 | Automated safety check: Pass | MIT | 7 mo ago |
| 958 | 958.Webapp QA Quick-invoke QA testing for a web app URL. An agent skill from SpecterOps/skills. | SpecterOps/ | 706 | — | ~506 | Automated safety check: Pass | Apache-2.0 | 18 days ago |
| 959 | Decompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result integration that catches contradictions. | mohitagw15856/ | 1.4k | — | ~1.2k | Automated safety check: Pass | MIT | 2 days ago |
| 960 | 960.Subagent Batches Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end. | LunCoSim/ | 107 | — | ~899 | Automated safety check: Pass | Apache-2.0 | yesterday |
