Каталог навыков агентов

Use when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts ign...

Creates structured context summaries for continuing work across AI sessions. Use when ending a session to enable seamles...

Compresses the current session state into a handoff document for seamless continuation in the next session. Captures pro...

Produces structured markdown session continuation documents for multi-session workflows. Captures active work streams, d...

Use this checklist at the end of a working session before context is lost.

Use this skill proactively when wrapping up a session to prepare the repo for the next agent. Read this before finalizin...

Save and restore cross-session state for coding work. Use when ending a session, switching tasks, or resuming work later...

Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching cont...

Use when concluding or pausing work so the next Claude Code session can continue reliably without hidden context.

Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resu...

WHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity...

세션 대화를 요약하여 의사결정 근거 중심의 히스토리 파일로 저장하는 스킬. "세션 정리해줘", "오늘은 여기까지", "마무리", "끝", "세션 히스토리 저장", "핸드오프 노트 작성해줘", "작업 내역 정리", "...

Restores full context when user says "hi-ai" or starts a new conversation. Searches project files, loads memory indexes,...

Cross-session learning system that extracts insights from session transcripts and injects relevant past learnings at ses...

List all past development sessions with summaries and timestamps

Load saved session context from a previous session. Lists available sessions and restores TODOs, context, and pending wo...

Load previous session state

Logs development sessions in real-time to track decisions and issues.

Search and analyze your own session logs (older/parent conversations) using jq.

Context preservation, tiered summarization, resumability

Manage Claude Code sessions with naming, checkpointing, and resume strategies.

Apply when initializing, saving, resuming, or closing a work session

Manage work sessions with creation, loading, syncing, and archiving capabilities.

Manage named Claude Code sessions for CircleTel workflows. Use when starting feature work, resuming previous sessions, o...

Manage current Claude Code session metadata — set project, tags, and summary on session.md via Obsidian CLI. Use this sk...

自动触发的会话生命周期管理 - INHERIT (继承知识) + DEPOSIT (沉淀精华)

Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - ev...

Migrate session logs from markdown to JSON format. Use when PRs contain markdown session logs that need conversion to th...

Persist and restore agent sessions across conversations with state snapshots

Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into c...

Use when a past or running agent session went wrong and the operator wants to know why (repeated work, ignored plan, a s...

Query previous pi sessions to retrieve context, decisions, code changes, or other information. Use when you need to look...

Seamlessly recover from session interruptions, crashes, or context switches without losing progress.

Capture session learnings and propose targeted improvements to docs, skills, or core agent instructions. Evidence-based...

Convert a Claude Code session JSONL file into an animated GIF replay showing the conversation as typed terminal output.

Use when resuming work on existing project - lists registered projects, reads project_state.md, summarizes current state...

Resume context from previous session

Resume from last checkpoint — show progress, cluster state, next actions

Resume previous work from archived session with full context restoration

Save current session progress, TODOs, and context to a local file before ending a session. Enables picking up later with...

Save current session state for resumption

Load relevant memories at session start for context continuity. IMPORTANT: Use this AUTOMATICALLY at the START of every...

Use this skill when initializing a session for any project repo. Autonomously analyzes git state, VCS issues, SSOT files...

Resumes work from a previous session using handoff notes, checkpoints, or compact state. Use at the beginning of a new s...

Execute work session initialization routine at conversation start. Identifies new skills, researches improvements for ex...

Manages session state transitions per SESSION_ORCHESTRATION.md. Internal use only. Do NOT load for: user session managem...

Persistently stores conversation state, decisions, and progress to allow seamless resume across sessions.

Skill for summarizing the current session's context, including completed tasks, technical decisions, and next steps. Use...

Consolidate a Claude Code session JSONL log into a summary-only meeting record under meetings/ (decisions, rejected alte...

Session management, conversation history, and checkpoints

Session and incident records: session logs (Freebuff dumps, orchestrator debug), postmortems, error memory (recurring er...

Build or update the teaching curriculum for a learning sub-project from its source materials. Use whenever the user want...

SetFit few-shot learning for efficient intent classification with minimal data

Use this skill when switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set...

Add keyless GBrain memory to an existing agent, or connect a hosted brain while preserving identity and configuration

Connect this agent to a running Guaardvark (self-hosted AI studio) and check what it can do right now. Use first when th...

Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow

Set up @vitest-agent/plugin in the current project

Configure or reconfigure aigent-OS identity, priorities, authority, projects, people, and decision logic

Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker,...

Guide for setup Serena MCP server for semantic code retrieval and editing capabilities

Performs unsupervised clustering on single-cell RNA-seq data using Seurat. This process finds nearest neighbors, compute...

Performs coarse clustering on ALL cells (including T cells, B cells, and non-T/B cells) before cell type selection. This...

Generates comprehensive cluster statistics and visualizations for Seurat objects, including dimension reduction plots, g...

Map query single-cell datasets to high-quality reference atlases using Seurat's reference mapping workflow. Performs lab...

Load, prepare, and apply quality control (QC) to single-cell RNA-seq data using Seurat. Performs data loading, QC filter...

Performs fine-grained re-clustering on specific subsets of cells (e.g., individual clusters, cell types, or custom subse...

Help users discover and select the right Salesforce skill for their task. Lists all available Salesforce development ski...

Supervised Fine-Tuning with SFTTrainer and Unsloth. Covers dataset preparation, chat template formatting, training confi...

Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.

Prüfung des Rentenanspruchs nach SGB VI – Altersrenten §§ 35–38 (Regelaltersrente, langjährig / besonders langjährig Ver...

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrai...

Comprehensive GLSL shader techniques for stunning visual effects — ray marching, SDF modeling, fluid simulation, procedu...

AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use whe...

Version: 1.1.0 | Author: Shadows Company | License: MIT

A shallow skill at the first level under skills/.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining mac...

Interpretabilidade e explicabilidade de modelos usando SHAP (SHapley Additive exPlanations). Use essa skill ao explicar...

Model interpretability using SHAP values and feature importance analysis

SHAP-based model explainability skill for feature attribution, summary plots, and interaction analysis.

Model interpretability via SHAP (Shapley values from game theory). Covers explainer choice (Tree, Deep, Linear, Kernel,...

Demonstrate that synthetic CoT traces with incorrect final answers outperform human-written correct solutions for superv...

DO NOT use directly: this skill is infrastructure for other imbue skills. This skill provides shared patterns consumed b...

Shared AgentOps skill contracts.

Context window auto-reset procedures for Ralph agents. Use when context fills up during long tasks.

Context window auto-reset procedures for Ralph agents. Use when context approaches 70% capacity during long tasks. Use p...

Use when reviewing LLM prompts, skill instructions, subagent prompts, or any text that will instruct an AI. Triggers: "r...

Context window hygiene for long-running LLM agents. Decision rules for when and how to compress, mask, switch, or delega...

Shelve the current session — create a bookmark so you can find and resume it later with /unshelve.

Autonomous pipeline monitor using sense-think-act loop. Watches snakemake/nextflow jobs, detects errors, applies fixes f...

Gate a PR's merge without human review, and merge it when the gate passes. Use when landing a PR during autonomous work,...

Prime context for a task — calls context_continue + context_retrieve to find relevant files before starting work. Minimi...

Package completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifa...

史铁生生死哲思思维——轮椅上的哲思、苦难中的超越、地坛的沉思、生死之问。 触发词：「史铁生视角」「像史铁生那样写」「我与地坛」「死是一件不必急于求成的事」。 擅长：生死哲思、苦难超越、内省散文、地坛意象、轮椅上的思考。

Local-first brain for OpenClaw. Offline, learns with use.