Search
Agent Workflows · SQLite · For developers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing. | shareAI-lab/ | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | 12 days ago |
| 2 | Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals. | dotnet/ | 23k | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 3 | Walks through adding a new persisted memory kind to EverOS: choose storage among Markdown, SQLite and LanceDB, pick a Markdown strategy, then wire schemas, repos and writers. | EverMind-AI/ | 13k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Migrate docs from bd (beads) to br (beadsrust). An agent skill from Dicklesworthstone/beads_rust. | Dicklesworthstone/ | 1.1k | — | ~2.2k | Automated safety check: Pass | Unknown | yesterday |
| 5 | Read and write the shared long-term memory store. An agent skill from tigerless-labs/agent-memory. | tigerless-labs/ | 3.4k | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 6 | A skill your agent uses when adding, changing, or reviewing an LLM/MCP tool in Trilium (the defineTools definitions under packages/trilium-core/src/services/llm/tools/ —… | TriliumNext/ | 38k | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | today |
| 7 | Coordinate parallel coding agents with Foremerge's local Git-compatible CLI and MCP server. | naw103/ | 538 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 8 | Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs. | professorpalmer/ | 467 | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 9 | Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network. | Ikalus1988/ | 526 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | 10.Audit Flow Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. | zebbern/ | 4.7k | — | ~4.2k | Automated safety check: Pass | MIT | today |
| 11 | Give a Python agent (such as Hermes Agent by Nous Research) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client… | liliang-cn/ | 274 | — | ~1.7k | Automated safety check: Pass | MIT | 2 days ago |
| 12 | 12.Clawmem ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring… | yoloshii/ | 210 | — | ~7.5k | Automated safety check: Pass | MIT | 5 days ago |
| 13 | 13.Memora A skill your agent uses when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful. | agentic-box/ | 733 | — | ~813 | Automated safety check: Pass | MIT | 12 days ago |
| 14 | Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs. | mnemosyne-oss/ | 3.4k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 15 | Explains how cognee stores session memory by session_id and bridges it into the permanent graph with improve(), including the stages, results and settings. | topoteretes/ | 32k | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | today |
| 16 | 16.Orchestrator A skill your agent uses when somebody asks for an orchestrator, a lead agent, a coordinator, or somebody to "keep an eye on" the agents working on a project — and when asking about who is minding a… | SirAllap/ | 330 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 17 | 17.Paxm Use paxm as Codex's active and passive memory layer. An agent skill from pax-beehive/paxm. | pax-beehive/ | 422 | — | ~574 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 18 | 18.Obelisk Search and query past Claude Code, Codex, Kimi Code, Kiro, and Pi session history. | tommy0103/ | 571 | — | ~6.5k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 19 | Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package. | liliang-cn/ | 274 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 20 | 20.Kb Workflow Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. | willynikes2/ | 183 | — | ~1.1k | Automated safety check: Pass | MIT | 5 days ago |
| 21 | Read-only lookup of local OpenCode history, including sessions, messages, plans, prompt history and prior decisions, queried through sqlite3 only when earlier context would help. | carson2222/ | 113 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 3 mo ago |
| 22 | 22.Memorywhale Query and write durable debugging memory recorded by MemoryWhale. | wuisabel-gif/ | 154 | — | ~765 | Automated safety check: Pass | MIT | 3 days ago |
| 23 | 23.Marm Init Guided MARM MCP setup. An agent skill from Lyellr88/marm-memory. | Lyellr88/ | 419 | — | ~7.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 24 | Manage Codex's native global memory (~/.codex/memories) with three sub-procedures - trim (audit + dedupe + three-layer cleanup), compress (rewrite verbose memories into concise form), and add-global… | Yu-Xiao-Sheng/ | 101 | — | ~453 | Automated safety check: Pass | MIT | 1 mo ago |
| 25 | Covers the read-side tools of the remindb MCP server, a SQLite-backed agent memory, for orienting, searching, resyncing and tracing relations. | radimsem/ | 129 | — | ~2.7k | Automated safety check: Pass | MIT | 2 mo ago |
| 26 | 26.Explore Graph-driven project understanding using code-review-graph (CRG). | xwtro0tk1t-cloud/ | 265 | — | ~1.6k | Automated safety check: Pass | No licence | 5 mo ago |
| 27 | 27.Retinue Coordinate work through a local Retinue workspace using its MCP tools. | jklthinking/ | 117 | — | ~279 | Automated safety check: Pass | MIT | 2 days ago |
| 28 | Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history. | wuisabel-gif/ | 154 | — | ~459 | Automated safety check: Pass | MIT | 3 days ago |
| 29 | Persist agent state across runs, shape what the LLM sees per turn, and cap history to fit a context window. | ag2ai/ | 252 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 30 | 30.Pad Talk to your project. An agent skill from PerpetualSoftware/pad. | PerpetualSoftware/ | 188 | — | ~10k | Automated safety check: Notes | Apache-2.0 | today |
| 31 | 31.Memmesh CLI MemMesh CLI + local MCP server — the zero-infra, no-API-key path to the same engine as the hosted SDK. | ThinkfleetAI/ | 420 | — | ~855 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 32 | MemoryWhale debugging; compiler failures; terminal diagnostics. | wuisabel-gif/ | 154 | — | ~370 | Automated safety check: Pass | MIT | 3 days ago |
| 33 | Queries MiMoCode's raw trajectory SQLite database for cross-session analysis such as repeated errors, tool-call patterns and verifying what was actually run. | XiaomiMiMo/ | 14k | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 34 | 34.Brainstorm 当需要探索方案、头脑风暴、创意思维时自动使用此 Skill. An agent skill from bkywksj/knowledge-base. | bkywksj/ | 330 | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 35 | Exports an OpenCode session from its local database into a single self-contained HTML page styled like the official share view, with folding and editing controls. | nigo81/ | 133 | — | ~1.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 36 | SkillOpt-flavored offline training loop for any SKILL.md. An agent skill from rohitg00/pro-workflow. | rohitg00/ | 2.9k | — | ~1.3k | Automated safety check: Pass | No licence | 11 days ago |
| 37 | 37.Review 代码变更完成后触发。审查变更是否引入跨模块破坏、存储兼容性问题、部署差异问题。 | riowang88/ | 177 | — | ~650 | Automated safety check: Pass | No licence | 3 mo ago |
| 38 | A skill your agent uses when starting, scaffolding, or organizing a FrontMCP project. | agentfront/ | 146 | — | ~5.8k | Automated safety check: Pass | Apache-2.0 | today |
| 39 | 39.Remember Front door for long-term memory backed by a remindb MCP server. | radimsem/ | 129 | — | ~728 | Automated safety check: Pass | MIT | 2 mo ago |
| 40 | Coordinate with WrongStack agents through the project-scoped Mailbox MCP server. | WrongStack/ | 371 | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 41 | 41.Memory NetClaw's native persistent memory (spec 033) — structured facts with temporal validity, semantic search across past sessions, decision logging, and entity relationships, backed by SQLite + ChromaDB… | automateyournetwork/ | 676 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 42 | 42.Pp Authentik Agent-native admin CLI for authentik identity provider with offline SQLite cache and an MCP server for Claude Desktop. | mvanhorn/ | 2.1k | — | ~23k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 43 | 43.Pp Motogp The first CLI and MCP server for MotoGP — human-friendly commands, offline SQLite history, and analyses no single endpoint provides. | mvanhorn/ | 2.1k | — | ~7.1k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 44 | 44.Pp V0 Generate and iterate on web apps with v0 from the terminal: create chats from prompts, stream agent output, sync history to a local SQLite mirror, and track credit spend across models. | mvanhorn/ | 2.1k | — | ~7.5k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 45 | A skill your agent uses when controlling AutoCAD 2026 with Tianzheng HVAC T30 through the autocadtianzheng MCP server, including connecting the THvac30V1 profile, reading or creating DWG engineering… | hashgraph-online/ | 1.3k | — | ~762 | Automated safety check: Pass | Apache-2.0 | today |
| 46 | Create the app skeleton: Express API, SQLite through node:sqlite, a Vue screen, and the test harness, following the layout the later checks rely on. | receptron/ | 237 | — | ~647 | Automated safety check: Pass | MIT | today |
| 47 | Manage autonomous AI research agents with SQLite-based state tracking. | sundial-org/ | 663 | — | ~1k | Automated safety check: Pass | No licence | 7 mo ago |