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

Readme Pass

ASecurity

Make a public repository README easier to understand and use. Apply when README structure or presentation is requested.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add badmuriss/my-llm-kit --skill readme-pass --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Readme Pass?

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

Security grade badge for Readme Pass
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/badmuriss-readme-pass/badge)](https://www.skillsdirectory.com/skills/badmuriss-readme-pass)

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

Download Zip
Files
SKILL.md
---
name: readme-pass
description: Make a public repository README easier to understand and use. Apply when README structure or presentation is requested.
---

# readme-pass

Make the README useful before making it pretty. Optimize for a distracted reader who wants to know what the project does, how to install it, and whether it fits their stack.

## Workflow

1. Read the repository instructions, README, installer files, and manifest. Do not document unsupported behavior.
2. Find existing brand assets before generating a banner. Check `assets/`, `public/`, `docs/`, logos, and brand files.
3. Cut before adding. Remove repeated claims, generic motivation, stale implementation detail, and sections that restate a table.
4. Put the sections in this order when the project supports them:
   - one-line value
   - agent-first install
   - core workflow or example
   - included capabilities
   - compatibility
   - advanced setup and safety
   - credits and license
5. Apply the `writing` skill. Preserve facts, commands, links, names, and licenses.
6. Add presentation only after the content is lean.
7. Verify commands, anchors, links, supported operating systems, and the changed diff.

## Attention budget

- Answer "what is this?" in one sentence.
- Keep paragraphs to one idea and usually one to three sentences.
- Prefer a short table for repeated mappings such as skill to purpose or host to support.
- Show the main workflow once. Link or move deep internals instead of explaining them twice.
- Put copyable prompts and commands before implementation details.
- Keep examples small enough to understand without scrolling back.
- Delete any sentence that only announces importance or repeats the heading.
- Do not preserve prose merely because it already exists.

## Agent-first install

When setup changes the user's machine, place a copyable agent-install prompt before manual commands. Tell the agent to:

- detect the operating system and select a documented installer;
- read repository instructions before mutation;
- preserve local changes and user-owned configuration;
- run the documented dry-run or preview first;
- continue only when no blocker remains;
- verify the installed capability and report backups, skips, failures, and unverified steps.

Use only commands and operating systems present in the repo. Keep manual commands below the prompt as a fallback.

## Presentation

Preserve existing branding. Add a banner, badges or navigation only when the
requested presentation work benefits from them. A text cleanup does not require
image generation. Use a plain heading when no visual identity is available.

## Writing rules

Use sentence-case headings, plain words, and concrete claims. Avoid em dashes, decorative triads, boldface spam, empty promises, and repeated feature lists.

## Delivery

- Stage files only when staging, committing or PR preparation is requested.
- Inspect the changed content for private information before an authorized publication.
- Report what was cut, what moved, what was added, and what remains unverified.

Attribution

badmurissbadmuriss
View sourceMore from badmuriss →
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 →