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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Brag

ASecurity

Create a short launch video, poster and share copy from a project or website when the user asks to brag about it or make a product demo video.

12 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentspythongit

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add Nmor/the-claude-council --skill brag --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Brag?

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

Security grade badge for Brag
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nmor-brag/badge)](https://www.skillsdirectory.com/skills/nmor-brag)

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

Files
SKILL.md
---
name: brag
description: Create a short launch video, poster and share copy from a project or website when the user asks to brag about it or make a product demo video.
---

# BRAG for Council

> Size budget: 4 KB.

Adapted from [latent-spaces/brag](https://github.com/latent-spaces/brag).
Use this skill for a requested video, not automatically after coding or a release.
Work in the main session with the user's model; do not launch a Council review team.

## Choose the route

- Default: read [the lean workflow](references/slim.md). It works with the available
  rendering tools and does not require Hyperframes or a specific model.
- `--full` or `--voice`: read the lean creative guidance, then
  [the Hyperframes route](references/hyperframes.md). Voice is explicitly opt-in.
- Keep tone, format, duration, `--no-music`, `--no-sfx` and title direction from the
  request. Default: about 20 seconds, landscape 1920×1080, 30 fps, no narration.

Resolve scripts relative to this skill directory, including when accessed through
Codex's Council catalog. Run `python3 <skill-dir>/scripts/brag.py doctor` first;
add `--full` for the Hyperframes route. It checks local tools without installing or
calling a model. Report missing dependencies, install them within the user's scope,
and verify again. Read only relevant project files or the requested website.

## One plan, honest content

Reuse the project's existing implementation plan for progress and handoffs. Record
creative scene timing in `brag-output/storyboard.md`; it is a media artifact, not
another implementation plan. Never create `brag-plan.md` or run a plan scaffold.
Use a timestamped output folder when prior output exists; keep intermediates in `work/`.

Use the real product, its visual identity and verifiable claims. Do not expose secrets,
private customer data or unpublished material in a public demo. Use synthetic demo data
where needed. Upstream music files are not bundled: generate original audio or use
assets the user has rights to use. Keep attribution with the deliverables when needed.

A request to create the video authorizes local rendering; no extra preview approval
is needed. Creating share copy does not authorize posting, uploading or messaging.
Do not send project material to an external generation service without authorization.

## Deliver and verify

Deliver `brag.mp4`, `brag.jpg`, `share-copy.txt` and `storyboard.md`. Inspect settled
frames and transitions, listen to the mix, and check readability and actual product
behavior. Bake the chosen poster into frame zero without extending the duration.

Run `python3 <skill-dir>/scripts/brag.py verify --output <output-dir> --duration 20
--format landscape` with the actual target duration and format. Use `--audio required`
when music, SFX or voice were requested, or `--audio none` for intentional silence.
The verifier checks artifacts and media properties; it does not judge visual quality,
prove the poster is frame zero, or establish the truth of marketing claims.
Report the files, checks and any limitation concisely. Keep progress in the existing plan.

See [provenance and license](UPSTREAM.md) and [Council installation](../../docs/BRAG.md).

## Standards cited

Use [W3C WCAG 2.2, SC 1.4.3 Contrast (Minimum)](https://www.w3.org/TR/WCAG22/#contrast-minimum)
when checking readable foreground/background text in scene frames. Apply the project's
accessibility requirements to narration/captions and motion as relevant.

Attribution

NmorNmor
View sourceMore from Nmor →
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".

1074701 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', ...

695601 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.

691 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 →