plugins/cc-meta/skills/summarizing-session-end/SKILL.md
Auto-generates a session summary on SessionEnd. Writes structured notes to ~/.claude/session-summaries/ for use by bigpicture synthesis.
npx skillsauth add qte77/claude-code-plugins summarizing-session-endInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generates a structured session summary when triggered by the SessionEnd hook. Reuses the compacting-context template to produce consistent, synthesis-ready notes.
Add to .claude/settings.json:
{
"hooks": {
"SessionEnd": [
{
"type": "prompt",
"prompt": "/summarizing-session-end"
}
]
}
}
Gather context -- Review the conversation for what was accomplished, which files were touched, and any unresolved issues.
Generate session ID -- Use the current date and a short identifier (first 8 chars of session UUID if available, or timestamp).
Write summary -- Create ~/.claude/session-summaries/YYYY-MM-DD-<id>.md
using the output template below. Create the directory if it does not exist.
Keep it brief -- The summary must be under 50 lines. This is a summary, not a transcript.
Write to ~/.claude/session-summaries/YYYY-MM-DD-<id>.md:
# Session Summary -- YYYY-MM-DD
## Trajectory
<!-- Phase reached: research / planning / implementation / review -->
<!-- One-line description of the session arc -->
## Key Files
<!-- Files touched with one-line purpose each -->
## Completed
<!-- Done items, one bullet per item -->
## Blockers
<!-- Blocking issues discovered (empty section if none) -->
## Findings
<!-- Key discoveries, decisions made, learnings -->
development
Verify an external or AI-generated security report against the actual codebase before acting on it. Use when handed a scanner PDF, automated teardown, audit report, or bug-bounty submission — classifies every finding CONFIRMED / OVERSTATED / FALSE-POSITIVE / FABRICATED and salvages the real work items.
development
Audits a site's SEO and AI-search (GEO) readiness — meta tags, Open Graph/Twitter, JSON-LD, robots/llms conventions — and generates fixes. Use when reviewing search visibility, social previews, structured data, or LLM/AI-crawler discoverability.
documentation
Generate or update README.md files across three scopes — repo (with project-type detection), account (GitHub user profile), and org (organization profile). Use when creating, updating, or aligning a README to org conventions.
development
Audit README.md files against best practices for repos, accounts, or orgs. Detects missing sections, stale links, inconsistent formatting, and convention violations. Use when reviewing README quality across one or many repos.