Каталог навыков агентов

Lightweight session initialization. Reads latest manifests and handoffs to resume context. Loads only what the current t...

Create protocol-compliant JSON session logs with verification-based enforcement. Autonomous operation with auto-incremen...

Internal sub-skill for session startup checks, Plans.md status, git state, and harness-mem resume pack. Invoked by sessi...

Analyze past Claude Code sessions to extract patterns, metrics, and recommendations.

This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intellig...

Answer "how are people using <site>", "what are visitors doing on <page>", "why is nobody downloading/copying/signing up...

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debuggi...

Validate that builtin servers and external MCP managers maintain proper session isolation. Use when auditing session iso...

Use at session start for context warm-up and during work to capture decisions

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

Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a tracea...

Extract and persist learnings from the current session. This skill should be used when the user wants Claude to analyze...

分析当前会话并持久化学习到三层存储（项目 CLAUDE.md、用户 CLAUDE.md、Memory MCP）

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

Organize sessions by prompt: find, rename, archive, prune.

The session bookends, codified — one skill that makes every repo start, run, and end sessions the same way.

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

Summarize the current conversation session and append results to the weekly agent-log. Use when user says "log this", "s...

Summarize the current session's files changed, tests run, commits, and decisions as handoff or standup notes.

Claude Code Stop 이벤트마다 마지막 user/assistant 교환을 세션당 1개 markdown 파일에 기계적으로 append하는 훅을 설치하거나 제거하는 스킬. LLM 호출 없이 jq 추출만 하므로...

Human-readable markdown session logs for characters and adventures.

Dig a user's original text out of their own archives when they ask for it — dated memory notes first, then session logs,...

Fix session protocol validation failures in GitHub Actions. Use when a PR fails with "Session protocol validation failed...

Log work sessions with timestamps, decisions, agent handoffs, issues, and outcomes. Use when a session log needs to be c...

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

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

Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extract...

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Cre...

Start or end a work session for any context (teams or other contexts). Use when starting work, ending a session, or when...

Context preservation, tiered summarization, resumability

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

セッション管理（Session Management）機能の開発・修正を行う際に使用。OPSession, ClientSession, SSO, RP-Initiated Logout, Back-Channel Logout実装時に役立...

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

Managing session docs, updating documentation throughout SDLC, archiving sessions. Use when starting/ending sessions or...

Use when PERFORMING session actions: checking token usage, preparing handoffs, or ending sessions early. Do NOT load for...

Implements secure session management with JWT tokens, Redis storage, refresh flows, and proper cookie configuration. Use...

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

Expert skill for implementing session management in SSG (Static Site Generation) and SSR (Server-Side Rendering) context...

Manage Claude Code sessions for the current branch. Use this skill when:- User asks "what's next?" or "where was I?"- Us...

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...

Read and reuse AI coding session context across Claude Code, Codex, Antigravity/agent hooks, Cursor adapters, and compat...

Write what the session produces into your vault AS IT HAPPENS, not at the end: a decision taken, a tool, scheduled task,...

Stores verified cross-session facts, decisions, preferences, and open questions without secrets, speculation, or monitor...

Maintains a structured running-notes document during long work sessions. Use when the user says "session notes", "update...

Per-user persistent session state management via session-manager.py

Session start bootstrap. Use this skill at the beginning of EVERY new session, before answering anything else. Purpose:...

Manages the entire session lifecycle: from context loading (PRD, Tech Stack) at startup, to maintaining project memory d...

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

Intelligent model routing for Claude Code sessions. Recommends optimal model (Opus/Sonnet/Haiku) and effort level based...

別の稼働中セッションについて相談したいときに使う。対象セッションを選んで相談したいことを伝えると、その履歴を読んで外から客観視し、簡単に答える。相談の結果、対象セッションへ送ることになったら人間の裁可を経て SendMessage で送る。...

Conversational guide for using tools/session-retro/observe.mjs to capture friction, wins, corrections, decisions, gaps,...

PROPOSE-ONLY session review — turn what actually happened this session into dated, evidence-backed skill improvement pro...

Start a session with context from previous work. Triggers on /open, 'what were we working on', 'where did we leave off',...

Construct temporary, session-specific memory palaces for complex projectsand conversations.Triggers: session context, pr...

Persist and restore agent sessions across conversations with state snapshots

Three-layer memory persistence system for continuous context across sessions. Use when you need to maintain state, recov...

Resume work from a prior handoff, tickets, and repository evidence without redoing completed steps.

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...

Audit what PRs this session produced. Ask: "What work did I do this session that isn't in a PR yet, or isn't merged?" Fo...

Prepares a session by organizing scattered information. Use when user says they have information to organize, want to pr...

Orchestrate end-to-end processing of D&D session videos from upload through knowledge extraction. Use when the user want...

Profile and debug Hermes sessions from their JSONL transcripts. Find a session and its subagents, build a queryable even...

Session management protocol. Use for saving and loading session state.

Use when running a work-item (WI) or thread session in this template repo — how to read the plan, execute only the scope...

Follow the end-of-session git checklist before handing off.

Check investigation session QA skip eligibility per ADR-034. Validates if staged files qualify for investigation-only ex...

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

Prepares branch for PR and merge. Cleans up, tests, validates commits, and generates PR/merge titles and descriptions.

全范围召回 - 从 Project CLAUDE.md、User CLAUDE.md 和 Memory MCP 查询历史知识

Rebuild working context from recent sessions, tickets, and live repository state.

Find and correctly interpret past conversation sessions using session_search and the state.db SQLite database. Covers ti...

Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the sessio...

This skill should be used when the user asks to "record session", "log interactions", "track session activity", "audit C...

Detect and recover previous planning sessions, reconstructing lost context from persistent planning files.

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

Troubleshoot Claude Code session issues. Use when encountering "No conversations found" errors, missing sessions, or ses...

Seamless continuation across sessions and IDEs — on session start, read .toh/memory/ and greet the user with where the l...

Automatically bridge long technical sessions to keep context window small and costs low. Extracts key technical decision...

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

This skill should be used when the user asks to 'reflect on this session', 'save insights to memory', 'capture what we l...

Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff...

Rename the current chat tab or any saved session with a descriptive name

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

Analyze claude-trace JSONL files for session health, patterns, and actionable insights. Use when debugging session issue...

Generate a session report with token usage estimates, work summary, and outcomes

Use when writing a NIGHT-LOG.md diary entry, a docs/REPORT-*.md session report, or a closing summary of work for Cristia...

Generate a comprehensive session report with per-model token usage (input, output, cache_read, cache_write including com...

Generate an Obsidian session report at the end of a coding session. Summarizes commits, tests, decisions, blockers, and...

Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) fr...