Skip to content

sergekostenchuk/seo-llm-skill-cluster / skills/llm-citation-monitor

llm-citation-monitor

Verified

Plan and record evidence-backed LLM and AI-search citation checks across approved assistant/search surfaces with timestamped queries, locales, modes, cited URLs, snippets, screenshots or transcripts, and caveats. Use this skill when the user asks whether ChatGPT, Perplexity, Claude, Gemini, Copilot, or another assistant cites a target site, but do not claim citation without direct evidence.

references/citation-evidence-policy.md

View on GitHub
# Citation Evidence Policy

## Required Fields Per Observation

| Field | Required |
| --- | --- |
| Surface | yes |
| Model/product/version if visible | yes, if visible |
| Date and time | yes |
| Locale/language | yes |
| Account state | anonymous, logged-in, paid, API, unknown |
| Query text | yes |
| Target URL cited | yes/no |
| Cited URL list | yes, if citations appear |
| Answer snippet or summary | yes |
| Screenshot/transcript path | optional but recommended |
| Caveats | yes |

## Query Matrix Types

- brand query;
- topic query;
- problem query;
- comparison query;
- how-to query;
- citation-check query;
- competitor query.

## What Can Be Claimed

Allowed:

- "Observed citation on this surface for this query at this time."
- "Not observed in this run."
- "Competitor domain was cited in this run."

Not allowed:

- "Assistant always cites the site."
- "Assistant never cites the site."
- "The site ranks in LLMs."
- "This caused traffic growth" without analytics evidence.

## Caveats To Record

- personalization;
- account state;
- locale;
- model/product changes;
- freshness;
- citation UI variability;
- cached answers;
- limited query sample size.

## Privacy

- Remove account email, profile info, private chats, private files, and private prompts from stored artifacts.
- Do not store API keys or cookies.
- Ask before preserving private screenshots or transcripts.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall