Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Improve

ASecurity

Use after a session reveals a reusable self-improvement pattern.

4 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agents

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add mverab/slashstack-skills --skill improve --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Improve?

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

Security grade badge for Improve
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mverab-improve/badge)](https://www.skillsdirectory.com/skills/mverab-improve)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: improve
description: Use after a session reveals a reusable self-improvement pattern.
---

# Improve

## Purpose

Capture reusable self-improvement patterns that shape future agent work
without overwriting existing learning.

## When to Use

Use after a session reveals a reusable self-improvement pattern.

## Workflow

1. Identify a pattern: a repeated mistake, useful tactic, repo convention, or
   verification habit likely to matter again.
2. Read `.agents/memory/patterns.json` before writing. Preserve every existing
   pattern unless the update is an intentional merge.
3. Add a concise pattern with: name, trigger (when to use), action (what to do),
   evidence (why it matters), confidence (0-1), and sources (files or sessions).
4. Keep entries repository-specific and durable. Do not store secrets, transient
   task status, commit hashes, or one-off TODOs.
5. Reuse relevant patterns during preflight, implementation, audit, and ship.

## Pattern Store Contract

- Schema version is `1`. Top-level fields: `version` (number) and `patterns` (array).
- Each pattern must have: `name`, `trigger`, `action`, `evidence`,
  `confidence` (number 0-1), `sources` (array of strings), `createdAt` (ISO string).
- Deduplication is by `id`. If `id` is missing, it is generated from `name` in kebab-case.
- Merging keeps the higher confidence, combines and deduplicates `sources`, and keeps
  the older `createdAt`.
- Invalid stores fail loudly: read and update operations throw rather than silently
  recovering or overwriting user data.

## Output

Updated `.agents/memory/patterns.json` with the new pattern merged in.

Attribution

mverabmverab
View sourceSee grades on GitHubMore from mverab →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →