بنقرة واحدة
onex-recap
Summarize the current Cursor session inline in chat.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Summarize the current Cursor session inline in chat.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use this skill when the user has a rough idea, wants to explore a feature, or says "let's brainstorm" or "help me design." The goal is to refine an idea into a validated design doc before any code is written.
Use this skill when ending a session and you want the next session to pick up where you left off. The goal is to capture enough context for seamless session continuity.
Use this skill when starting feature work that needs isolation from the current workspace, or when you need to work on multiple branches simultaneously. The goal is to create an isolated worktree with a verified clean baseline.
Use this skill when fixing a bug caused by invalid data reaching deep into execution. The goal is to add validation at every layer the data passes through, making the bug structurally impossible to reproduce.
Use this skill when documentation has drifted from the codebase, needs an inventory, or should be archived.
Autonomous implementation pipeline. Reads a plan file, reviews it adversarially,
| name | onex-recap |
| description | Summarize the current Cursor session inline in chat. |
| disable-model-invocation | true |
Summarize the current Cursor session inline in chat.
Read ~/.omnicursor/events.jsonl — filter lines where conversation_id matches
the value in ~/.omnicursor/sessions/current.json (field: conversation_id).
If the file is absent or the field is missing, use the most recent entries.
Read ~/.omnicursor/sessions/<conversation_id>.json for outcome and aggregated stats.
Run git log --oneline -5 and git diff --name-only HEAD for files in progress.
Respond with this structure, inline in chat (do not write to any file):
Outcome: success / failed / abandoned / unknown Files edited: [list paths, or "none"] Shell commands: N allowed, N warned, N denied Ruff findings: N total across session Prompts classified: N
2–3 sentence narrative of what was worked on this session.