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

Gh Rendered Markdown

ASecurity

Use when Markdown must render: never hard-wrap issue-body paragraphs; fix GitHub code fences, fold logs into details, and pin source links to tags.

3 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agentsgobashgitapi

Works with

api

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 9/19/2026

$npx -y skills add tony/skills --skill gh-rendered-markdown --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gh Rendered Markdown?

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

Security grade badge for Gh Rendered Markdown
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tony-gh-rendered-markdown/badge)](https://www.skillsdirectory.com/skills/tony-gh-rendered-markdown)

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: gh-rendered-markdown
description: >-
  Use when Markdown must render: never hard-wrap issue-body paragraphs; fix
  GitHub code fences, fold logs into details, and pin source links to tags.
allowed-tools: ["Read", "Grep", "Glob", "Bash", "WebSearch", "WebFetch"]
metadata:
  source: "plugins/gh/skills/rendered-markdown/SKILL.md"
---

# Rendered markdown

Write the body so it renders, and link it so it still resolves in
three years.

Two references carry the rules, and they are the same ones
the `gh-create-issue` skill follows:

- `references/rendered-markdown.md` — wrapping,
  symbols, code fences, `<details>`, structure, and what to leave out.
- `references/source-links.md` — pinning,
  autolinking, cross-repo references, and the project link set.

## The test

Will a maintainer three years from now find this helpful? They will
not have the conversation, the open tab, or the branch. What survives
is the text and what it links to.

For a pull request that test also picks the subject: the branch's net
change, not the route it took.

## Core moves

- **Know which surface you are on.** GitHub renders a single newline
  as a line break in issue, pull request, and comment bodies, and as a
  space in a markdown file. So a comment body is never hard-wrapped,
  and a repository file follows the repository's own convention. Do
  not re-wrap a file to match a body.
- **Backtick every symbol** — functions, flags, paths, env vars,
  packages, types, verbatim errors. In the title too. Backticks are
  also how you stop `#123` or `@name` from linking.
- **Strip local paths and PII** before publishing: absolute home
  paths, hostnames, emails, tokens, internal URLs. Pasted logs are
  where they hide.
- **Fence liberally, one command per block**, no comments inside the
  fence, language tagged. A long command may wrap with `\`.
- **Fold long output into `<details>`** with a blank line after
  `</summary>` — without it the whole block renders as raw HTML.
- **Nested sections, not tables.** Rendered tables scroll sideways
  instead of reflowing and hide their right-hand columns.
- **Link at every opportunity, and pin what you link.** A release tag
  first, else a 7-character commit reachable from trunk, never
  `blob/main`. Name an open-source project once with its whole set:
  repository, homepage, docs, the changelog at that release, and its
  registry page.
- **Use the autolinks that already exist.** Bare `#123` and a bare
  7-character ref inside a GitHub body; `[REPO#123](url)` across
  repositories; a bare tracker key only when that repository actually
  resolves it.

## Calibrate to the project

Read `./AGENTS.md` and `./CLAUDE.md`. Where they define a house voice,
a slop rubric, or a wrap convention, that governs.

## Verify before publishing

Render the draft through GitHub's own renderer and read the output —
literal `**` means a `<details>` block lost its blank line, and a
`<br>` inside prose means the body is hard-wrapped.

```
gh api --method POST /markdown -f mode=gfm -f context=OWNER/REPO -f text="$(cat body.md)"
```

## Common mistakes

**Hard-wrapping an issue body at 72 columns.** Correct for a commit
message, correct for most repository files, wrong here — every newline
becomes a line break and the paragraph renders as ragged stubs.

**A `<details>` block with no blank line after `</summary>`.** The
fences, lists, and bold inside it all render as literal text. It is
the most common way a body ships broken.

**An alert inside `<details>` or a list item.** `> [!WARNING]`
degrades silently to a plain blockquote showing the marker.

**Linking `blob/main/…` with a line anchor.** It resolves forever and
points at different code every week.

**A table of contents linking to the body's own headings.** Issue-body
headings get no anchor ids; every one of those links is dead.

**@mentions as attribution.** They send mail. Name someone only when
you are asking them for something.

**Reformatting the repository to match.** This skill governs what you
are writing, not the files around it.


## Portability notes

- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.

Attribution

tonytony
View sourceSee grades on GitHubMore from tony →
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', ...

698431 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 →