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 skills add krillinai/growth-skills --skill meta-ads-auditgit clone --depth 1 https://github.com/krillinai/growth-skillsWrote 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/krillinai/growth-skills/meta-ads-audit)<a href="https://agentmods.dev/skills/krillinai/growth-skills/meta-ads-audit"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/meta-ads-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/krillinai/growth-skills/meta-ads-audit"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/meta-ads-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 42 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 5.1 | $0.00074 | $0.01905 |
| Opus 5 | $0.00037 | $0.00953 |
| Sonnet 5 | $0.00015 | $0.00381 |
| Haiku 4.5 | $0.00007 | $0.00191 |
Grade A, and why
meta-ads-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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ads Audit
Audit supplied Meta Ads evidence or evidence collected through the parent Skill's explicitly authorized connected-readonly mode without changing an account. Separate visible platform reporting from customer and business outcomes, and return bounded findings, missing evidence, and decision rules instead of invented benchmarks or account actions.
Read input-contract.md before requesting, normalizing, or validating data. For direct reads, apply the parent core-read-only-ad-platforms.md contract before this module. Read analysis-methods.md for account, delivery, creative, landing, measurement, economics, and planning methods. Apply evidence-and-boundaries.md to every claim and action. Use playbook-sources.md for the pinned Growth Playbook basis and time-sensitive Meta implementation references.
Select One Mode
| Mode | Use |
|---|---|
intake |
Build or validate the canonical input bundle and identify the smallest missing evidence that changes the decision |
full |
Audit structure, delivery, creative, landing continuity, measurement, customer quality, and business reconciliation |
creative |
Audit concepts, variants, coverage, execution, fatigue signals, creator evidence, and usage rights |
measurement |
Audit events, attribution, deduplication, reconciliation, new-customer definitions, economics, and incrementality evidence |
performance |
Investigate a reported change without treating the symptom, timing, or cause as verified |
connected-readonly |
Analyze a bounded evidence bundle collected under the parent Skill's authorized ads_read path |
out-of-scope |
Decline live account access or external action and provide a safe handoff or input plan |
Name one primary mode. A partial input is still useful when it supports that mode; mark unsupported sections unavailable instead of refusing the entire audit.
What ships with it
12 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/input-bundle/ads.template.csv 202 B
- assets/input-bundle/business-outcomes.template.csv 199 B
- assets/input-bundle/context.template.json 527 B
- assets/input-bundle/creatives.template.csv 271 B
- assets/input-bundle/daily-performance.template.csv 222 B
- assets/input-bundle/landing-pages.template.csv 224 B
- references/analysis-methods.md 7.6 KB
- references/evidence-and-boundaries.md 4.7 KB
- references/input-contract.md 6.1 KB
- references/playbook-sources.md 2.1 KB
- scripts/test_validate_input_bundle.py 5.5 KB runs code
- scripts/validate_input_bundle.py 12 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.
- 9d ago First seen · 98 lines · 74 tokens per session scan A a37be287b935
meta-ads-audit is a skill published in the GitHub repository krillinai/growth-skills (43 stars, last pushed 16d ago), licensed MIT. It adds 74 tokens to every session and 1,905 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…