Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/citedy/adclaw/html-presentation-decknpx skills add citedy/adclaw --skill html-presentation-deckgit clone --depth 1 https://github.com/citedy/adclawWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00101 | $0.02240 |
| Opus 5 | $0.00051 | $0.01120 |
| Sonnet 5 | $0.00020 | $0.00448 |
| Haiku 4.5 | $0.00010 | $0.00224 |
Grade A, and why
html-presentation-deck scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- html-presentation-deck — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Presentation Deck
Create polished, browser-native presentation decks as standalone HTML files. The output is a web presentation, not a PowerPoint file.
Skill directory (<skill-dir>)
<skill-dir> is always the folder that contains this SKILL.md. Install method chooses where that folder lives — do not mix paths across installs.
@citedy/skills (Claude Code / Codex CLI)
npx @citedy/skills install copies into the user project (where you run the command), not into the npm cache:
| Target | Skill folder | Slash command |
|---|---|---|
| Codex | <project>/.codex/skills/html-presentation-deck |
<project>/.codex/commands/html-deck.md |
| Claude | <project>/.claude/skills/html-presentation-deck |
<project>/.claude/commands/html-deck.md |
If both exist, prefer the namespace that matches where /html-deck was invoked (see commands/html-deck.md in the npm package).
AdClaw agent (built-in skill)
AdClaw does not install skills under .codex/skills or .claude/skills. It resolves skills from the working directory (default ~/.adclaw, overridable with ADCLAW_WORKING_DIR):
| Context | <skill-dir> |
|---|---|
| Runtime (normal use) | $ADCLAW_WORKING_DIR/active_skills/html-presentation-deck |
| User customized copy | $ADCLAW_WORKING_DIR/customized_skills/html-presentation-deck (wins over active when present) |
| AdClaw repo development | src/adclaw/agents/skills/html-presentation-deck (built-in source; synced into active_skills on init) |
When AdClaw loads this skill, use the resolved directory from the agent — not a .codex path.
Both in one machine
AdClaw and @citedy/skills keep separate copies. Updating one does not update the other. Pick the <skill-dir> that matches the tool you are using for this deck.
Validators (any install)
Run from the deck project root (where deck/index.html lives):
python3 <skill-dir>/scripts/validate_html_deck.py deck/index.html
python3 <skill-dir>/scripts/validate_deck_quality.py deck/index.html
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/screenshot-backgrounds/clean-grid/blue-anchor.webp 47 KB
- assets/screenshot-backgrounds/clean-grid/lemon-signal.webp 34 KB
- assets/screenshot-backgrounds/clean-grid/lime-circuit.webp 44 KB
- assets/screenshot-backgrounds/clean-grid/orange-marker.webp 99 KB
- assets/screenshot-backgrounds/editorial/forest-ledger.webp 417 KB
- assets/screenshot-backgrounds/editorial/indigo-porcelain.webp 296 KB
- assets/screenshot-backgrounds/editorial/ink-paper.webp 314 KB
- assets/screenshot-backgrounds/editorial/sand-gallery.webp 249 KB
- assets/screenshot-backgrounds/editorial/warm-archive.webp 430 KB
- assets/template-clean-grid.html 9.2 KB
- assets/template-editorial.html 8.7 KB
- assets/template-product-grid.html 17 KB
- README.md 2.5 KB
- references/checklist.md 2.1 KB
- references/components-product-grid.md 5.1 KB
- references/image-prompts.md 2.9 KB
- references/layout-lock.md 4.3 KB
- references/layouts-clean-grid.md 2.4 KB
- references/layouts-editorial.md 1.9 KB
- references/layouts-product-grid.md 11 KB
- references/screenshot-framing.md 3.1 KB
- references/themes.md 2.3 KB
- references/typography.md 4.4 KB
- scripts/.gitignore 19 B
- scripts/validate_deck_quality.py 13 KB runs code
- scripts/validate_html_deck.py 28 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 204 lines · 101 tokens per session scan A 41e776e7f40b
html-presentation-deck is a skill published in the GitHub repository citedy/adclaw (35 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,240 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
update-setup
One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 设置更新, 初始化更新.
image-generation
Generate images and iteratively edit saved image artifacts.
cron
Schedule reminders and recurring tasks.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).