ワンクリックでManusで任意のスキルを実行

session-start

スター4

フォーク0

更新日2026年7月3日 17:41

Check memory for in-progress tasks and active TODOs at the start of each session. Use at the beginning of every new conversation.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

alexfayers

alexfayers/llm-prompts

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

session-start

At the start of every session, before responding to the user's first message, check memory for in-progress work using compact mode to minimise token usage:

read_graph(project="<repo-name>") to surface recent entities for the current workspace.
CRITICAL - do NOT skip this step or substitute read_graph results. Run both of these calls with compact=true:
- search_all_projects(query="task", status="in-progress", compact=true)
- search_all_projects(query="task", status="planned", compact=true) These are the only authoritative source for the task summary. read_graph only returns 10 recent entities from one project and will miss tasks in other scopes. compact=true omits observations to save tokens - you only need entity names and statuses for the summary.
Present the task summary grouped by project. Show in-progress tasks first, then planned. Include ALL results - do not truncate or summarise away tasks.
If nothing is in progress or planned anywhere, proceed normally without mentioning the check.
Run llm-prompts update --check to see if any tool sources have upstream updates available. If updates are found, mention them to the user.
Call the memory tools (read_graph, search_all_projects, search_nodes, etc.) directly - they are ordinary tools in your catalog. Do NOT run any tool-discovery step to "find" or "check availability of" memory first (e.g. list_mcp_resources, listing servers): that lists resources, not tools, and an empty result does not mean memory is unavailable. If and only if your harness hides tool schemas behind an explicit ToolSearch/deferred-tools step (Claude Code), pre-load them once with select:mcp__memory__add_observations,mcp__memory__read_graph,mcp__memory__search_nodes,mcp__memory__create_entities; otherwise there is nothing to pre-load - just call the tools.

このリポジトリの他の Skills

同じリポジトリ

git-usage

alexfayers/llm-prompts

Rules and style preferences for the usage of git. Use before you interact with git in any way.

2026-07-164

handoff

alexfayers/llm-prompts

Write a handoff document so a fresh session (or another agent) can resume multi-session work with full context. Use when the current session is ending mid-effort, context is running high, or the user asks to "hand off", "hand over", or prepare the next session/slice.

2026-07-124

session-end

alexfayers/llm-prompts

Checklist for wrapping up a session - persist memory, check TODOs, and ensure nothing is lost. Use before marking a task complete or ending a conversation.

2026-07-124

refine-plan

alexfayers/llm-prompts

Evaluate and refine a plan before implementation begins. Use once you think you are ready to present a plan or design to the user.

2026-06-164

retrospective

alexfayers/llm-prompts

Analyse recent session transcripts to extract learnings, discover pain points, and persist them into memory/skills/rules. Run manually when the retrospective counter is due (session-end reminds you at 5+).

2026-06-154

tidy-code

alexfayers/llm-prompts

Reduce the amount of code in a changeset or file - remove duplication, dead code, redundancy, and over-verbose constructs - while preserving behaviour. Use when asked to tidy, shrink, deduplicate, DRY up, or simplify code.

2026-06-124

name	session-start
description	Check memory for in-progress tasks and active TODOs at the start of each session. Use at the beginning of every new conversation.

session-start

At the start of every session, before responding to the user's first message, check memory for in-progress work using compact mode to minimise token usage:

read_graph(project="<repo-name>") to surface recent entities for the current workspace.
CRITICAL - do NOT skip this step or substitute read_graph results. Run both of these calls with compact=true:
- search_all_projects(query="task", status="in-progress", compact=true)
- search_all_projects(query="task", status="planned", compact=true) These are the only authoritative source for the task summary. read_graph only returns 10 recent entities from one project and will miss tasks in other scopes. compact=true omits observations to save tokens - you only need entity names and statuses for the summary.
Present the task summary grouped by project. Show in-progress tasks first, then planned. Include ALL results - do not truncate or summarise away tasks.
If nothing is in progress or planned anywhere, proceed normally without mentioning the check.
Run llm-prompts update --check to see if any tool sources have upstream updates available. If updates are found, mention them to the user.
Call the memory tools (read_graph, search_all_projects, search_nodes, etc.) directly - they are ordinary tools in your catalog. Do NOT run any tool-discovery step to "find" or "check availability of" memory first (e.g. list_mcp_resources, listing servers): that lists resources, not tools, and an empty result does not mean memory is unavailable. If and only if your harness hides tool schemas behind an explicit ToolSearch/deferred-tools step (Claude Code), pre-load them once with select:mcp__memory__add_observations,mcp__memory__read_graph,mcp__memory__search_nodes,mcp__memory__create_entities; otherwise there is nothing to pre-load - just call the tools.