Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Wrap

ASecurity

End of session. Reflects wins, updates Command Center, moves done tasks, writes to session log and memory.

97 stars
0 votes
0 copies
0 views
Added 8/30/2026
ai-agents

Security Analysis

A100/100

Scanned 8/30/2026

Install to Claude Code

$npx -y skills add jdpolasky/ai-chief-of-staff --skill wrap --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Wrap?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Wrap
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jdpolasky-wrap/badge)](https://www.skillsdirectory.com/skills/jdpolasky-wrap)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: wrap
description: End of session. Reflects wins, updates Command Center, moves done tasks, writes to session log and memory.
user_invocable: true
---

End of session. Two phases.

---

## Phase 1 — Deterministic file work

Do these first, in order. Don't narrate them.

### 1. Bump the Command Center

Read `Command Center.md` from the vault (path is in `CLAUDE.md`). Find the line `**Last updated:** ...` near the top and replace the date with today's date (`YYYY-MM-DD`). Don't change anything else in the file unless the user has asked you to.

### 2. Move checked tasks to Done

In `To-Do.md`, scan the four quadrants (Do Now, Schedule, Defer, Later) for any tasks marked `- [x]`. Move each one into the `## Done` section at the bottom. Preserve the original wording. Add a date prefix in `YYYY-MM-DD` format if the task doesn't already carry one.

If no tasks were checked, skip this step silently.

### 3. Append a session log entry

Read `_system/last_session.md` to get the current session number from its frontmatter, then increment by 1 (the new value).

Append a block like this to `_system/Session Log.md`:

```
## Session N — YYYY-MM-DD

[Two to four sentences on what actually shipped this session. What changed in the world, not what was discussed.]

**Open threads:** [bullet list, or "none" if everything closed]
```

Use the new session number.

### 4. Overwrite hot context

Overwrite `_system/hot.md` with one paragraph (3-6 sentences) describing the current state at session close. This is deliberately low-fidelity. The next `/start` reads it to recover in-progress context quickly.

### 5. Overwrite last_session.md

Overwrite `_system/last_session.md`. Set the `date:` frontmatter to today and the `session:` frontmatter to the new session number. Body holds the recap paragraph and open-threads list. Same content as the Session Log entry, but as a standalone file the next `/start` reads first.

### 6. Append memory firings (if any fired)

If any memory file in `.claude/memory/` actually shaped a response during this session, append one line per firing to `_system/memory_firings.log`:

```
YYYY-MM-DD | session_N | filename.md | one-line note about how it fired
```

If no memories fired (rare), skip this step.

### 7. Audit counter

If the new session number is divisible by 7, flag at the end of the wrap output: "🔍 Audit due — run /audit when convenient."

---

## Phase 2 — Reflect and save

### Reflect wins

Name what was accomplished this session in a sentence or two. Don't let the user brush past progress. Use the moved-to-Done tasks as evidence if they exist.

### Save to memory

Update existing files in `.claude/memory/` rather than creating new ones. The four core files are `user_profile.md`, `preferences.md`, `projects.md`, and `session_context.md`. As the system grows, additional files follow the type-prefix convention (`user_*.md`, `feedback_*.md`, `project_*.md`, `reference_*.md`); see `docs/memory.md` for the full pattern.

For `session_context.md` specifically: prepend the new entry at the top with today's date. Then scan the file and remove any entries older than 7 days. Keep the file from growing unboundedly.

### Check Waiting For

Did anything get sent, handed off, or committed to this session? If so, propose adding a row to the Waiting For table in `To-Do.md`. Ask before adding.

### Suggest what to pick up next

One or two sentences. Frame as "queued up for next time," not "what you didn't finish."

Keep the whole Phase 2 section short. Prose, not bullet lists.

Attribution

jdpolaskyjdpolasky
View sourceMore from jdpolasky →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →