بنقرة واحدة
session-summarizer
Use when user runs /summarize command to capture session knowledge
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use when user runs /summarize command to capture session knowledge
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 when initializing or maintaining agent-friendly repo context, setting up AGENTS.md or CLAUDE.md, adding local rules, defining verification commands, or checking whether context files are stale.
Use when the user asks to run workflow:ship, ship a branch, publish a feature branch, open and merge a PR, or push/PR/merge/cleanup completed work.
Use when the user asks to run workflow:commit, create a commit, make a git commit, stage changes, write a commit message, or prepare local changes for shipping.
Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for Opus 4.7 (with adaptive thinking) inside the chat app — claude.ai, the Mac app, the iOS app — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for the chat app. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan to send into the chat app and clearly wants a reusable, well-structured prompt rather than a direct answer. The output is always a single, copy-pasteable prompt in a code block that the user sends as-is — never a template with placeholders. Always ends with the exact line "Think before answering (maximum reasoning)".
Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.
Pre-discovery intent exploration for genuinely vague ideas. Use when the user pitches an idea where the real user-need, problem framing, or core assumptions are unclear — before /kiro-discovery. Delegates to the intent-explorer skill, which produces .kiro/specs/<slug>/intent-spec.md. The output is auto-detected by /kiro-discovery and downstream spec skills, so the user does not need to pass intent context as an argument. Skip this skill entirely when the user already has a clear problem statement.
| name | session-summarizer |
| description | Use when user runs /summarize command to capture session knowledge |
Every session generates knowledge: decisions made, patterns that worked, problems encountered, questions that arose. Session summaries capture this for future compound learning.
Core principle: Document sessions to build knowledge that compounds across time.
User runs /summarize command to create a session summary.
Create summaries to capture:
You MUST integrate all three sources:
Session logs: ~/.claude/projects/[project-path]/[session-id]/session-memory/summary.md
Git history: git log --oneline -n 20 and git diff since session start
Conversation context: Your memory of the session
Using session logs:
# Find current session log
ls -la ~/.claude/projects/$(pwd | sed 's/\/Users\/[^/]*\/Projects\///g')/*/session-memory/summary.md | tail -1
# Read it
cat [path-from-above]
# Session Summary - [Date]
## Context
[One-line: what was the goal/problem]
## Victories
- [What worked, solutions found]
- [Patterns that were effective]
## Failures
- [What didn't work, why]
- [Dead ends, wrong assumptions]
## Root Causes
- [For each failure above: What in your system prompt or tooling made you make this mistake?]
- [Analyze prompt assumptions, tool limitations, missing context that led to errors]
- [Example: "Assumed Write tool would create parent directories - tooling doesn't support this"]
- [Example: "System prompt emphasized speed over verification - led to skipping file reads"]
## Tough Questions
- [Questions that came up, answered or not]
- [Ambiguities encountered]
## Improvements
- [What could be better next time]
- [Patterns to codify, failures to document]
## Git Activity
- [Commit count, key changes]
- [Files modified, tests added]
## Next Session
- [Unfinished items, follow-ups needed]
/summarize command~/.claude/projects/.../summary.mdFor each failure or mistake documented:
Examples:
Purpose: Understand what gaps in prompts or tooling cause errors, enabling systemic improvements.
User: /summarize
You: "I'll create a session summary capturing what we accomplished and learned today."
[Read session logs, check git, write summary with root cause analysis...]
You: "Here's the summary:
Fixed authentication bug in React app where tokens weren't persisting across page refreshes.
Would you like me to save this anywhere specific, or is the session log sufficient?"