ai-verification skills

jun0-ds/sonmat

Skill Claude CodeCodex

A repeatable work cycle that plans a task, defines the expected result, carries it out, checks the result, records useful findings, and repeats when needed.

jun0-ds/sonmat

Skill Claude CodeCodex

Devil's advocate for reasoning — discovery-led counter-arguments against interpretations, plans, and irreversible decisions. Locates the load-bearing assumption via CCT, then drives depth into the one axis where the claim is actually thin.

jun0-ds/sonmat

Skill Claude CodeCodex

Post-work persistence layer — observes completed work and writes what should outlive the session. Bridge notes, journal, progress, project rules discovered from user corrections, novel traps detected by guard, witness verdicts.

haidrrrry/loop-engineering-skills

Skill Claude CodeCodex

Make AI output measurably smarter using research-backed self-correction loops. Use this skill whenever the user asks to improve, refine, double-check, verify, or "make better" any AI-generated output — code, writing, plans, analysis, answers — or asks for "your best work", "high quality", "production ready", "make…

haidrrrry/loop-engineering-skills

Skill Claude CodeCodex

Give the agent episodic memory so it improves every cycle instead of repeating mistakes. Use this skill whenever working in a project that has a .loop/LESSONS.md file, whenever a task is being retried after a failure, whenever the user says "remember this", "don't make that mistake again", "learn from this", or "why…

haidrrrry/loop-engineering-skills

Skill Claude CodeCodex

Verify agent work against project gates before declaring it done. Use this skill whenever working in a project with a .loop/GATES.md file, whenever finishing any coding task inside a loop, whenever the user asks "is this actually done", "verify this", "check your work", or before emitting any VERDICT line. Also use it…

Deep-Process/deep-process

Skill Claude CodeCodex

Use when user has multiple analysis outputs (risk, feasibility, architecture, verification) and needs a combined decision. Triggers: "combine these analyses", "decision brief", "GO/NO-GO", "aggregate results", "what's the overall verdict".

Deep-Process/deep-process

Skill Claude CodeCodex

Use when user wants to find or create a business opportunity — whether discovering market gaps, inventing novel concepts, or both. Combines signal harvesting, gap detection, novel synthesis, and revenue architecture into one pipeline. Triggers: "find a niche", "what should I build", "business opportunity", "invent…

Deep-Process/deep-process

Skill Claude CodeCodex

Use when user asks to verify, fact-check, validate, or check correctness of code, documents, specs, claims, or LLM-generated artifacts. Triggers: "verify this", "is this correct", "check against spec", "find contradictions", "review this document". Do NOT use for code review (style/quality) — this is for…

Creed-Space/METTLE

Skill Claude CodeCodex

Use when a user wants to complete METTLE reverse-CAPTCHA challenges, obtain a signed result, or verify a METTLE credential.