reasoning skills

Orchestra-Research/AI-Research-SKILLs

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

masamasa59/ai-agent-papers

Skill Claude CodeCodex

Write a monthly trend newsletter for this ai-agent-papers repo. Use when asked to create/update a monthly trend report, summarize a category's recent papers, or "make a newsletter". Encodes the house procedure: cover every coherent category with enough papers that month (no fixed number of issues; overlap between…

zhiliscope/baiyueguang-learning-skill

Skill Claude CodeCodex

Transform knowledge points into an investigable information network using the Baiyueguang Learning Method.

UditAkhourii/neuroarxiv

Skill Claude CodeCodex

Grounds a coding agent's architecture decisions in real arXiv prior art before it builds something new. Reads arXiv category-wise via real HTTP fetch, spawns parallel isolated reads across the papers found, scores/clusters them, then converges on ONE recommended path with citations, a first step, and known prior-art…

ahmadvh/octochains

Skill Claude CodeCodex

Determines whether a security incident involves personal data, triggers regulatory breach-notification obligations (e.g. GDPR Art. 33/34), and what notification timelines apply.

ahmadvh/octochains

Skill Claude CodeCodex

Analyzes authentication and authorization events for failed-login clustering, privilege-escalation chains, credential-stuffing patterns, and MFA-bypass indicators.

ahmadvh/octochains

Skill Claude CodeCodex

Detects anomalous behavior by authenticated users that may indicate insider threats through behavioral analysis of access patterns, privileged actions, and data movement.

lcqysl/GEMS

Skill Claude CodeCodex

This skill is designed to rewrite user prompts to align with the expert-level aesthetic standards. It transforms simple descriptions into multi-dimensional, professional-grade artistic instructions that maximize scores across all fine-grained aesthetic attributes.

lcqysl/GEMS

Skill Claude CodeCodex

This skill should be triggered when the user's request implies a need for imagination, artistic flair, conceptual depth, or unconventional visual storytelling.

lcqysl/GEMS

Skill Claude CodeCodex

This skill should be triggered when the user's request involves multiple objects, complex scene arrangements, or specific physical relationships between elements.

OmidZamani/dspy-skills

Skill Claude CodeCodex

Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.

Kastalien-Research/thoughtbox

Skill Claude CodeCodex

Guide for designing, implementing, and advising on MCP servers that use Code Mode — the pattern where an LLM writes and executes code to orchestrate API calls instead of calling individual tools one at a time. Use this skill whenever the user mentions Code Mode, MCP tool proliferation, context window bloat from MCP…

Kastalien-Research/thoughtbox

Skill Claude CodeCodex

Run an Agent-Native Architecture Audit using Thoughtbox Hub for multi-agent coordination. Spawns 3 auditor agents and 1 synthesizer that collaborate through structured channels, cross-reference findings, and build consensus on scores.

Kastalien-Research/thoughtbox

Skill Claude CodeCodex

Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that coordinate through shared workspaces, problems, proposals, and channels.

mrgoonie/fable-thinking

Skill Claude CodeCodex

Reasoning protocol distilled from Claude Fable 5. Makes any model reason like Fable — evidence-grounded claims, multi-hypothesis diagnosis, concrete simulation, adversarial self-review, calibrated outcome-first delivery. Its never-skipped Floor check catches simple-looking trick questions models answer confidently…

liortesta/ClawdAgent

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

chainlesschain/chainlesschain

Skill Claude CodeCodex

A two-stage workflow that plans changes first and edits code second, keeping reasoning separate from file modifications.

AP3X-Dev/AG3NT

Skill Claude CodeCodex

Structured multi-step reasoning tool for complex problem solving with branching, hypothesis testing, and evidence tracking.

cdeust/zetetic-team-subagents

Skill Claude CodeCodex

Synthesize multiple papers, benchmarks, interviews, reviews, or other sources into a defensible and qualified conclusion. Use for conflicting evidence, literature synthesis, claim auditing, argument mapping, qualitative coding, belief updates, or any request that must expose counter-evidence, uncertainty, and source…

cdeust/zetetic-team-subagents

Skill Claude CodeCodex

Draw the line where it costs least. Use for build-vs-buy calls, "where does this module/team/service boundary belong?", APIs and abstractions forcing users into implementation vocabulary, tools that should augment rather than automate, hardcoded decisions that belong at runtime, or information nobody can find.

cdeust/zetetic-team-subagents

Skill Claude CodeCodex

Audit the decision before it ships. Use for "are we sure about this?", high-stakes choices made on fast intuition, plans with no failure scenario, estimates that are suspiciously optimistic, metrics being gamed (Goodhart), unfalsifiable claims, negotiation prep, or strategies that break in extreme conditions.

Agents365-ai/scientific-thinking-general

Skill Claude CodeCodex

Use when interpreting research findings, evaluating scientific evidence, analyzing mechanisms, comparing competing hypotheses, designing experiments, or constructing scientific arguments.

PythonIaMath/PromptRail-Plugins

Skill Claude CodeCodex

Check whether the PromptRail Claude effort router is installed, configured, and healthy.

ihatesea69/HieuNghi-AI-Skills

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.