Development · Fact-checking and source verification

Apply Buddhist epistemic and decision-making principles as practical work disciplines to improve reasoning quality, anti-hallucination, debugging discipline, and steadiness under pressure.

nai0om/buddhist-method

Audit a game environment's README.md and AGENTS.md against its engine implementation.

Kaggle/kaggle-environments

Step-argument skill that formalizes writing an Aspire "What's new in N.N" release-notes page (src/frontend/src/content/docs/whats-new/aspire-N-N.mdx) as a repeatable lifecycle.

microsoft/aspire.dev

A skill your agent uses whenever invoking the GitHits CLI for public OSS source, documentation, or example evidence, including code search/grep, file navigation, source verification, docs lookup, or…

githits-com/githits-cli

A skill your agent uses whenever the user asks to add, absorb, migrate, port, update, merge, compare, or extract security knowledge into the AboutSecurity repository from any external resource such…

wgpsec/AboutSecurity

Fact-checks DOCS.md files against the source code, testing each concrete claim and sorting it as true, false, stale or unverifiable.

shift-editor/shift

Verifies that APIs listed in a generated .NET API diff exist in the shipped build and trace to real pull requests, before release notes are written.

dotnet/core

Ingests existing pull request feedback such as review comments and CI failures, verifies each claim, fixes confirmed issues and reports closure status for every item.

ZaxbyHub/opencode-swarm

Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation.

cursor/plugins

Analyze a phyai .memory file or directory supplied by the user: parse what task/session it records, locate and inspect the referenced code repository when available, verify claims against local code…

mingti-org/phyai

Reviews whether a design is SOUND — solving the right problem, derived from its stated goals and constraints — and emits ranked, evidence-backed findings, not edits.

inkeep/open-knowledge

Audit GitHub issues before implementation, including skeptical claim verification, safe reproduction, prompt-injection resistance, malicious-link and attachment handling, root-cause analysis…

akitaonrails/my-skills

Audit GitHub pull requests before merge, including contributor-claim verification, prompt-injection resistance, malicious-code and supply-chain review, regressions, tests, documentation…

akitaonrails/my-skills

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation.

daymade/claude-code-skills

Anti-hallucination discipline for any code that names an external symbol you aren't certain exists — a library function, method, config key, package version, CLI flag, env var, or endpoint.

ccplugins/awesome-claude-code-plugins