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

Audit

ASecurity

Periodic integrity check. Reads memory, skills, vault state. Reports redundant rules, stale memories, broken links, drifted skills.

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 audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Audit?

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

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

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

Download Zip
Files
SKILL.md
---
name: audit
description: Periodic integrity check. Reads memory, skills, vault state. Reports redundant rules, stale memories, broken links, drifted skills.
user_invocable: true
---

Periodic integrity check. Run roughly every 7 sessions, or whenever the briefing surfaces an audit-due flag.

This is a read-mostly skill. Its job is to surface findings as a report. The user picks which fixes to make.

## Read

In parallel:

1. `.claude/memory/MEMORY.md` and every file it points at.
2. Every `SKILL.md` under `.claude/skills/`.
3. `Command Center.md` and `To-Do.md` from the vault.
4. `_system/memory_firings.log`.

## Checklist

Walk through these in order. For each, return findings with concrete file paths and line references where applicable.

### 1. Redundant or contradictory memory

Are any two memory files saying the same thing? Are any two saying contradictory things? List candidates for merging or reconciliation.

### 2. Stale memory

Read each memory file's `description` frontmatter against the actual contents. Does the description still describe what's in the file? Flag mismatches.

For project-type memories: do the projects still exist and look active? Closed-project memories should be moved or marked.

### 3. Index drift

Does `MEMORY.md` list every file in `.claude/memory/`? Is every file in the index actually present? Flag both directions of drift.

### 4. Broken links

Scan memory files and skills for wikilinks (`[[...]]`) and markdown links (`[...](...)`) pointing at vault files. Flag any whose target doesn't exist.

### 5. Skill drift

For each `SKILL.md`, does the skill's described behavior match what `CLAUDE.md`, the docs, and the vault templates actually support? A common drift: a skill references a file or pattern that has since been renamed or removed.

### 6. Decay analysis (gated)

Read `_system/memory_firings.log`. Count distinct session numbers. If under 10, **skip this section** with a short note: "Decay analysis is gated until the firings log holds 10 distinct sessions. Currently at N. Skipping."

If 10 or more, surface memory files that have not fired in the most recent 5 sessions. Don't recommend deletion. Surface for the user to review.

## Report format

Return findings as a numbered list grouped by checklist section. For each finding: what's wrong, where it lives, a one-line proposed fix. Don't make any of the fixes. The user picks.

End the report with a one-line state summary: total memory files, total skills, last audit-counter value, decay-analysis status (gated or live).

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 →