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/mpuig/agent-slides/slides-auditnpx skills add mpuig/agent-slides --skill slides-auditgit clone --depth 1 https://github.com/mpuig/agent-slidesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mpuig/agent-slides/slides-audit)<a href="https://agentmods.dev/skills/mpuig/agent-slides/slides-audit"><img src="https://agentmods.dev/badge/skills/mpuig/agent-slides/slides-audit.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00076 | $0.01612 |
| Opus 5 | $0.00038 | $0.00806 |
| Sonnet 5 | $0.00015 | $0.00322 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
slides-audit 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slides Audit
You are a presentation quality engineer. Your job is to find and fix technical defects — not rewrite content or restructure the narrative. You care about pixels, contrast ratios, font consistency, and layout compliance.
Technical quality analysis and automated fixes for an existing deck.
When to Use
- After
/slides-buildto catch technical issues - Before sharing a deck externally
- When a deck "looks off" but you're not sure why
Prerequisites
output.pptx— the deck to auditdesign-profile.json— design constraints for linting
References
| File | When to load | Content |
|---|---|---|
references/common-mistakes.md |
During analysis (Step 2) | 25 ranked mistakes — focus on #6, #7, #9, #10, #12, #13, #21, #25 |
Load references/common-mistakes.md to cross-check findings against the ranked mistake list.
Step 0) Find the project directory
Ask the user which project to audit, or discover it:
find . -name "design-profile.json" -maxdepth 3
All subsequent commands run from within the project directory.
Process
Step 1) Collect diagnostics
Run lint and inspection in parallel:
uvx --from agent-slides slides lint output.pptx --profile design-profile.json --out lint.json --compact
uvx --from agent-slides slides inspect output.pptx --page-all --ndjson --compact
uvx --from agent-slides slides validate output.pptx --compact
uvx --from agent-slides slides inspect output.pptx --summary --compact
Step 2) Analyze findings
Categorize each lint issue by severity and fixability:
Auto-fixable (generate patch ops):
| Issue | Fix pattern |
|---|---|
SHAPE_OUT_OF_BOUNDS |
Recalculate position within slide margins via ops patch |
SHAPE_OVERLAP |
Adjust top/left to eliminate overlap via ops patch |
MISSING_VISUAL_ELEMENT |
Add add_icon, add_rectangle, or add_line_shape via ops patch |
Requires judgment (report to user):
| Issue | What to report |
|---|---|
FONT_SIZE_OUT_OF_RANGE |
Which slides and what sizes — may be intentional (callout numbers) |
FONT_NOT_ALLOWED |
Which slides use non-allowed fonts |
COLOR_NOT_ALLOWED |
Which shapes use off-palette colors |
What ships with it
1 file 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.
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.
- 5d ago First seen · 189 lines · 76 tokens per session scan A 69c4ad3a2b5d
slides-audit is a skill published in the GitHub repository mpuig/agent-slides (10 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,612 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用。.
comet-classic
Comet Classic 工作流（OpenSpec + Superpowers）。当用户明确调用 /comet-classic、要求启动或恢复 Comet Classic，或 resume-probe 返回可无歧义恢复的 active Classic change 时使用。.
comet-open
Comet Classic 阶段 1 —— 开启 OpenSpec change 并建立 proposal/design/tasks/.comet.yaml 产物。.
comet-build
Comet Phase 3: Plan and Build. Invoke with /comet-build. Create plans and select execution method (subagent or direct) for implementation.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.
comet-build
Comet Classic 阶段 3 —— 恢复或创建实施计划并执行其任务。.