28 tagged claim verification, measured the same way as everything else here.
Browse within: citations 18academic-writing 13citation-integrity 13vscode-extension 13zotero-plugin 13ai-skills 7agent-infrastructure 5agent-tools 5ai-search 5
Skill Claude CodeCodex
A human-led research workflow for investment decisions. It treats a trader’s market idea as a hypothesis, gathers evidence to test it, checks current prices, studies industries, records decisions, and leaves the final choice to the trader.
Skill Claude CodeCodex
A method for checking whether claims from posts, news, reports, or other AI systems are true. It breaks statements into smaller facts and checks them against original sources.
Skill Claude CodeCodex
OpenOrder — Order out of investment chaos. An AI-maintained investment research wiki that compounds your edge across every conversation. Triggers automatically on: (1) any stock ticker (US/HK/A-share/TW/JP) or company name; (2) industry/theme discussions (semiconductors, AI infra, photonics, HBM, energy, biotech…
wd041216-bit/zero-api-key-web-search
Skill Claude CodeCodex
Claude Code-compatible skill for source-backed web search, page reading, and evidence-aware claim checking. Use it when an answer depends on current facts, live sources, or explicit support/conflict handling. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.
wd041216-bit/zero-api-key-web-search
Skill Claude CodeCodex
Codex-compatible skill for source-backed web search, page reading, and evidence-aware claim checking. Use it to verify factual answers with live results and explicit source handling. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.
wd041216-bit/zero-api-key-web-search
Skill Claude CodeCodex
OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. No API keys required by default; optional providers can be enabled for stronger coverage. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.
Skill Claude CodeCodex
This skill should be used when about to state how many tests pass or fail - writing a commit message containing a count like "22 passed" or "15/17 passing", saying "all tests pass" or "the suite is green" or "tests are passing" in a summary, reporting a test result, or claiming work is verified. Use it before writing…
Skill Claude CodeCodex
Benchmark local LLMs (Ollama models such as qwen3:14b, hermes3:8b) as CiteVahti citation prescreening agents on a chosen topic, and build the publication-style prescreen report + a dedicated CiteVahti store from the run. Use this whenever the user wants to test how well small/local models rate claim-vs-source support…
Skill Claude CodeCodex
The secure front-door for building, developing, releasing, and updating CiteVahti. Use this whenever you are about to cut a release or bump the version; build, sign, or notarize the desktop app, the .mcpb extension, or the PyInstaller binary; set up or change automatic updates (tufup / code signing); add or change an…
Skill Claude CodeCodex
Use when checking manuscript claims against evidence, assessing whether a citation actually supports what it is cited for, adding audited references to Zotero, generating a citation-integrity report, or when a researcher mentions claims, citations, PubMed, Zotero, PRISMA, blinded rating, or peer review of evidence.
Skill Claude CodeCodex
Execute a multi-phase plan one phase at a time under a gated review loop, so the user never has to take the assistant's word that work was done correctly. Use when delivering any ordered build/change plan (e.g. a repositioning or refactor broken into phases), or when the user asks for "design review", "checks and…
Skill Claude CodeCodex
Verify a frontend/UI change in the Tru8 web app actually works and stays on-design before calling it done — for routing, nav, marketing pages, layout, and copy changes where correctness is largely visual and behavioural rather than unit-testable. Use after building a UI slice, or when asked to "verify the UI", "check…