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

Guides

ASecurity

Turn a repeated repository review into a reusable procedure

147 stars
0 votes
0 copies
0 views
Added 9/3/2026
ai-agentspython

Security Analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned 9/20/2026

$npx -y skills add prapaa-ai/agav --skill guides --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Guides?

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

Security grade badge for Guides
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/prapaa-ai-guides/badge)](https://www.skillsdirectory.com/skills/prapaa-ai-guides)

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

Download with Pro
Files
add-files-as-context.md
---
title: Author and Evolve a Skill
description: Turn a repeated repository review into a reusable procedure
guideLevel: advanced
order: 3
---

# Author and Evolve a Skill

Use a skill when you repeat the same procedure across several tasks.

## Scenario: review modules consistently

Create `.agav/skills/module-review/SKILL.md` in the hello-agav repository:

```markdown
---
name: module-review
description: Review a Python module against project conventions
version: 1.0.0
invocation: user
allowed-tools:
  - read_file
  - grep_search
  - find_files
---

# Module Review

1. Read the supplied module and identify its public functions.
2. Check for type annotations, docstrings, and error handling.
3. Find the corresponding test file in `tests/` and list untested paths.
4. Return a table with risk, evidence path, and recommendation.
5. Do not edit files.
```

Restart Agav, then run the skill manually:

```text
/module-review @counter.py
```

`invocation: user` keeps the workflow predictable: it runs only when you call it. The tool allowlist also keeps the review read-only.

## Improve it from real use

Inspect its configuration and usage:

```text
/skills info module-review
```

After several runs, change one instruction when you see a repeated problem — for example, add an edge-case check for malformed JSON if reviews keep missing it. Keep project skills in source control and review instruction changes like code.

## Expected result

Every module review follows the same checks and produces the same compact report format.

Next: [Compose Agents, Skills, and Tools](/guides/agent-skill-tool-combinations).

Attribution

prapaa-aiprapaa-ai
View sourceSee grades on GitHubMore from prapaa-ai →
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 →