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

Write For Learners

ASecurity

The house style for every reader-facing document in this repo — the spec sections, docs/learn, README, status. Readers are students and junior developers. Covers the fixed section shape (In plain words, Why it matters, example, The rules, Common mistake), sentence rules, the single running example, and what to cut. Load before writing or editing prose under specs/dsor/, docs/, or README.md.

6 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgobackendsecurity

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add panaversity/dsor --skill write-for-learners --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Write For Learners?

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

Security grade badge for Write For Learners
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/panaversity-write-for-learners/badge)](https://www.skillsdirectory.com/skills/panaversity-write-for-learners)

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

Download Zip
Files
SKILL.md
---
name: write-for-learners
description: The house style for every reader-facing document in this repo — the spec sections, docs/learn, README, status. Readers are students and junior developers. Covers the fixed section shape (In plain words, Why it matters, example, The rules, Common mistake), sentence rules, the single running example, and what to cut. Load before writing or editing prose under specs/dsor/, docs/, or README.md.
metadata:
  version: "1.0.0"
---

# Writing for learners

The reader is a student or a junior developer. They are intelligent and they have not
built a security-sensitive backend before. English is often their second language.
Writing that only an expert can follow is a defect (AGENTS.md → decision 7).

## The section shape

Every numbered spec section has these parts, in this order. Leave a part out when it
would be empty. Never reorder them.

1. **In plain words.** What this section is about, with no jargon. If a term is
   unavoidable, define it in the same sentence. Two to five sentences.
2. **Why it matters.** The real failure this section prevents, told as a short story
   from the running example. Skip it if there is no concrete failure to tell.
3. The example (YAML, a diagram, a table).
4. **The rules.** The requirement lines. A first-time reader is told they may skip
   these, so nothing they need to understand may appear *only* here.
5. **Common mistake.** What a beginner actually does wrong, stated as the wrong thing,
   then the fix. Only when there is a specific, common one.

## Sentence rules

- Short sentences. One idea each. Prefer a full stop to a dash or a semicolon.
- Say the plain thing. "DSoR looks the vendor up itself", not "state is sourced
  authoritatively".
- Define before use. The prerequisite table in `docs/learn/start-here.md` is the list
  of terms a reader may be assumed to know after reading it. Anything else gets
  defined where it first appears.
- An analogy must fit the rule exactly where it is used, and is dropped the moment it
  stops fitting. The established ones: new clerk (the whole idea), permission slip
  (delegation), booking the last hotel room (atomic reservation), order-tracking page
  (proposal), pilot's checklist (pipeline), a lock that stays locked when the power
  fails (fail closed). Reuse these before inventing another.
- Name the failure concretely: who, which invoice, how much, what went wrong.
- No filler, no hype, no "simply" or "just". If a step were simple, the reader would
  not need the document.

## One running example

`org_456` · `user_123` (AP supervisor) · `accounts-payable-fte` · `del_100` ·
`cfo_100` · `VENDOR-44` · `INV-1008` · `PAY-901` · 31,400.00 USD · threshold
25,000 USD · limits 50,000 per transaction and 200,000 per day. Every example uses
these names and numbers. A new scenario is a new step in this story, not a new cast.

## What to cut

- A paragraph that repeats what **In plain words** already said.
- Commentary about earlier versions. That belongs in `research/history.md`.
- A present-tense sentence about something `docs/status.md` does not list as built.

## Check before you finish

Read the section as a student who has read only `docs/learn/start-here.md`. Is every
term defined? Could they say, in one sentence, what goes wrong without this section?
Then run `pnpm guard`: it catches dead links and unknown requirement ids.

Attribution

panaversitypanaversity
View sourceMore from panaversity →
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 →