Skills & prompts

ai-loop

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

ChatGPT Claude Codex CLI Cohere Cursor DeepSeek Gemini GitHub Copilot GLM Grok Kimi Llama MiniMax Mistral OpenAI opencode Skill Screened 49999
LLM Mart 25 views

deterministic-design

Render the UI and prove it's balanced + usable: a deterministic layout audit (centroid / optical-center / pixel-oracle balance via explicit math + annotated screenshot) plus a vision-judged Nielsen usability audit by a separate fresh-eyes judge. The measurement layer taste-only d

ChatGPT Claude Codex CLI Cohere Cursor DeepSeek Gemini GitHub Copilot GLM Grok Kimi Llama MiniMax Mistral OpenAI opencode Skill Screened 49999
LLM Mart 22 views

neckbeard

Use when asked to fix, build, refactor, review, verify, or release software and the work is non-trivial — including delivering a change request through planning, gates, implementation, review, verified PR, and authorized release; continuing work started elsewhere with no packet v

Claude Skill Screened 182
LLM Mart 21 views

dont-lie-to-me

Use when the user explicitly wants evidence-disciplined answers that separate observed facts, sourced claims, user reports, inference, unknowns, and contradictions before making strong factual or completion claims.

Claude Skill Screened 127
LLM Mart 14 views

hermes-change-review

Use when a branch, pull request, Kanban task, or implementation must be reviewed separately for intent fidelity, repository quality, and verification evidence before completion or merge is accepted.

Claude Skill Screened 127
LLM Mart 11 views

verification-before-completion

在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言

Claude Cursor opencode Skill Screened 8572
LLM Mart 10 views

fact-checking

Use when verifying claims. Covers tracing a claim to its origin, evaluating sources, detecting laundered statistics, and reporting a verdict with the evidence rather than an assertion. Trigger on "is this true", "where does this statistic come from", "fact check this article". Do

Claude Skill Screened 34
LLM Mart 1 views

deep-research

Use when researching a question that requires multiple sources. Covers question decomposition, source evaluation, tracking what is known versus assumed, and producing a synthesis with honest confidence levels. Trigger on "research this for me", "what does the evidence actually sa

Claude Skill Screened 34
LLM Mart 1 views

apify-verified-email-finder

Builds a list of verified business emails from Google Maps, Google SERPs, or a user-supplied URL list. Verification happens inside the same Apify run — no third-party verifier needed. Use when user asks to find verified emails, build a leads list, scrape emails from Maps or SERP,

Claude Skill Screened 295
LLM Mart 1 views

verification

Cross-DCC verification toolset - deterministic capture review views, in-band image statistics, scene-vs-spec validation, and reference-vs-render comparison sheets. Pure Python, read-only, DCC-agnostic. Use to close the quality loop without shipping pixels to a model: flag white/n

Claude Skill Screened 74

MCP servers

Turn a written policy into rules a program can check, and get the same answer every time.

6 views

Articles

Byte-identical or bust

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

LLM Mart · Sep 20, 2026 12 views

AI content SEO: how to publish pages that earn their place

AI made publishing cheap, which is exactly the problem. What separates a page worth ranking from a competent summary of the first ten results.

LLM Mart · Aug 21, 2026 20 views

Prompt testing: build a lightweight eval set

A prompt that works once isn't a quality system. Five cases, an observable rubric, and a regression set will tell you whether a change helped.

LLM Mart · Aug 21, 2026 22 views

What counts as proof

"Verify your work" isn't an instruction. It's a mood. Here's the version that's an instruction. Verify with a different mechanism than the one that made the claim.

LLM Mart · Aug 19, 2026 31 views

How to Research with AI Without Losing the Source Trail

Use AI to speed research without losing trust. Learn to find primary sources, verify claims, preserve uncertainty, and keep an auditable source trail.

LLM Mart · Aug 14, 2026 32 views