Long-term memory service for LLM agents. Provides persistent, structured memory (Cognitive Nexus) through three operations: Formation (encode conversations into memory), Recall (query memory with natural language), and Maintenance (consolidate and prune memory).
为任意组件或模块创建/更新 Serena memory 的工作流与格式规范。用于用户要求“源码级梳理并写入 Serena memory”的场景，例如“对 X 进行源码级梳理并写入 Y.md”，或者“分析 X 并生成Serena memory”。适用于组件类/接口名或模块名（如 OACModule_*），并要求输出包含概述/职责/涉及文件/架构/依赖/注意事项/调用方等章节。
Reflective Memory
Persistent memory and context for AI agents using Cognis by Lyzr. Use this skill when the user mentions "remember this", "what did I work on", "save this for later", "team knowledge", "project context", "recall", "memory", or needs long-term memory across sessions. Also use when the user asks about past decisions, preferences, or prior conversations. Supports personal memory (per-user), team memory (shared across repo contributors), semantic search, and automatic context assembly.
Persistent memory and context for AI agents using Cognis by Lyzr. Use this skill when the user mentions "remember this", "what did I work on", "save this for later", "team knowledge", "project context", "recall", "memory", or needs long-term memory across sessions. Also use when the user asks about past decisions, preferences, or prior conversations. Supports personal memory (per-user), team memory (shared across repo contributors), semantic search, and automatic context assembly.
Use when Codex users or Codex agents need to install, configure, validate, troubleshoot, or operate Mnemos through MCP, or when they mention Codex memory, AGENTS.md memory policy, Codex Automations, or Mnemos in Codex.
Structured memory system for AI workspaces. Indexes markdown memory files into SQLite FTS5 for fast, cited search. Extracts structured facts, maintains memory health, and provides an MCP server with live search + write-path for Claude Code integration. --- # Structured Memory Engine ## MCP Tools (v4) When running as an MCP server (`node lib/mcp-server.js`), exposes: - `sme_query` — Search memory. Supports `query`, `limit`, `since`, `type`, `minConfidence`, `includeStale`. - `sme_context` — Get relevant context for a message. Returns ranked, token-budgeted, formatted context for injection. Supports `message`, `maxTokens`. - `sme_remember` — Save a fact/decision/preference to today's memory log. Auto-indexed. - `sme_index` — Re-index workspace. Use `force: true` for full rebuild. - `sme_reflect` — Run maintenance: decay, reinforce, stale detection, contradictions, prune. Use `dryRun: true` to preview. - `sme_status` — Index statistics. ## CLI Commands ```bash # Index workspace memory files node lib/index.js index [--workspace PATH] [--force] [--include extra.md,other.md] # Search indexed memory node lib/index.js query "search terms" [--limit N] [--since 7d|2w|3m|2026-01-01] [--context N] [--type fact|confirmed|inferred|...] [--min-confidence 0.5] [--include-stale] # Show index status node lib/index.js status [--workspace PATH] # Memory maintenance node lib/index.js reflect [--workspace PATH] [--dry-run] node lib/index.js contradictions [--workspace PATH] [--unresolved] node lib/index.js archived [--workspace PATH] [--limit N] node lib/index.js restore <chunk-id> [--workspace PATH] ``` ## Configuration
Adaptive memory system that makes any LLM output better over time. Learns what works (strategies) and what fails (antibodies) from every scan. Injects winning patterns before generation, catches errors after. Hot/Cold tiered memory with multi-domain support.
Use when user wants to audit long-term memory for stale, incorrect, outdated, or duplicate entries, or correct memory entries based on new information
View and change hmem memory settings, hooks, sync, and checkpoint configuration. Use this skill whenever the user types /hmem-config, asks to change memory settings, adjust parameters, tune bulk-read behavior, configure auto-checkpoints, manage hmem-sync, or troubleshoot memory-related issues. Also trigger when the user asks things like "how often does auto-save fire", "why is my context so large", "change checkpoint to auto", "how many tokens does startup cost", or "set up sync". --- # hmem-config — View and Change Settings This skill guides you through reading, explaining, and updating hmem's configuration. The config controls how memory is stored, displayed, checkpointed, and synced across devices. ## Locate and read the config The config lives at `hmem.config.json` in the same directory as your .hmem file. Located at `~/.hmem/hmem.config.json` (in the same directory as your .hmem file). Read the file directly — don't ask the user where it is. If it doesn't exist, offer to create one (only non-default values need to be specified). The config uses a unified format with a `"memory"` block and an optional `"sync"` block: ```json { "memory": { ... }, "sync": { ... } } ``` ## Show current settings Present a table of current values vs. defaults. Only highlight values that differ from defaults — the user cares about what they've customized, not the full list. ### Core parameters | Parameter | Default | Purpose | |-----------|---------|---------| | `maxCharsPerLevel` | [200, 2500, 10000, 25000, 50000] | Character limits per tree level [L1–L5]. L1 is always loaded at startup, so keeping it short saves tokens across every session. L5 is raw data, rarely accessed. | | `maxDepth` | 5 | Tree depth (1–5). Most users need 5. Lower values save storage but lose granularity. | | `defaultReadLimit` | 100 | Max entries per bulk read. Lower = faster startup, higher = more complete overview. | | `maxTitleChars` | 50 | Auto-extracted title length. Only applies to entries without explic
Distill a graduated lab senior into an AI Skill. Import chats, meeting notes, photos, and screenshots to build Group Memory + Persona with continuous evolution. | 把毕业大师兄蒸馏成 AI Skill，导入聊天记录、组会纪要、照片和截图，生成 Group Memory + Persona，支持持续进化。
You MUST use this before any work to recall project memory, and after implementing to store decisions. Lossless-claude (lcm) provides persistent cross-session memory via CLI commands.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
