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 unifapi-agent/agents --skill ai-visibility-fix-plangit clone --depth 1 https://github.com/unifapi-agent/agentsWrote 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/unifapi-agent/agents/ai-visibility-fix-plan)<a href="https://agentmods.dev/skills/unifapi-agent/agents/ai-visibility-fix-plan"><img src="https://agentmods.dev/badge/skills/unifapi-agent/agents/ai-visibility-fix-plan/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/unifapi-agent/agents/ai-visibility-fix-plan"><img src="https://agentmods.dev/badge/skills/unifapi-agent/agents/ai-visibility-fix-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 47 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00113 | $0.01428 |
| Opus 5 | $0.00056 | $0.00714 |
| Sonnet 5 | $0.00023 | $0.00286 |
| Haiku 4.5 | $0.00011 | $0.00143 |
Grade A, and why
ai-visibility-fix-plan 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Visibility Fix Plan
Turn AI visibility evidence into an execution-ready fix plan for generative engine optimization. The plan should say which prompt gaps to attack, why the current cited source wins, and whether the fix is Structure, Authority, or Presence.
This is an enhanced skill: it reads live public data through UnifAPI when needed, but it remains eyes, not hands. It does not edit pages, post on third-party sites, buy reviews, or manipulate mentions.
Use UnifAPI for live evidence
Start from ai-visibility-audit or ai-answer-gap output. Re-pull only what is stale or missing:
- Per-prompt answer and citations -
geo/serpwithtargetset to the brand domain. Confirm whether the brand is cited, merely named, or absent. - Demand weighting -
geo/keywords/search-volumeso the fix plan attacks prompts people actually ask. - Answer owners -
geo/mentions/top-domains,geo/mentions/top-pages, andgeo/mentions/cross-aggregated-metricsto identify the source or competitor winning the answer. - Organic cross-read -
seo/serpto identify quick wins where the brand ranks organically but is not cited in the AI answer. - Page structure read -
browser/markdownon the brand page and winning source to compare extractability: definition blocks, comparison tables, FAQ sections, cited stats, and clear headings.
Keep the run date, platform, market, prompt set, and billing metadata in the output.
Workflow
- Load the gap set. Prefer an existing audit or answer-gap table. If absent, run a small prompt set first; do not create a fix plan from vibes.
- Group misses by root cause.
- Structure - the brand has the answer, but it is not extractable.
- Authority - the winning source has stronger stats, quotes, citations, freshness, or topical depth.
- Presence - the answer is owned by third-party surfaces where the brand is missing: directories, review sites, listicles, Wikipedia-style pages, communities, or partner pages.
- Choose the build path.
- Update existing page when the brand ranks organically, is name-dropped, or has a near-equivalent page.
- Create net-new page when no credible page exists for a high-demand prompt.
- Earn third-party presence when the cited source is a list, review surface, community thread, or external authority page.
- Score the fix. Use AI search volume as the spine, then adjust for winnability, right-to-win, effort, and risk.
- Write acceptance checks. Each fix must say how to verify it after shipping: re-run
geo/serp, read the page withbrowser/markdown, validate schema, or check the third-party listing. - Separate content from distribution. On-site structure fixes, authority edits, and third-party presence work should not be lumped into one content task.
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.
- 9d ago First seen · 100 lines · 113 tokens per session scan A 4dc6c2c91bf7
ai-visibility-fix-plan is a skill published in the GitHub repository unifapi-agent/agents (559 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 1,428 once invoked, about $0.0006 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
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…
ai-visibility
Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not. Use this skill whenever someone asks about AI visibility, AEO, GEO, answer engine optimization, generative engine optimization, "AI SEO", brand mentions or share of voice in AI…
ansvisor-aeo-coach-standalone
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…
ansvisor-aeo-coach
Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
geo-report
Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions.