Skill Claude CodeCodex
Audit supervised fine-tuning datasets against the behavior and task they are meant to teach. Use when inspecting SFT JSONL, chat messages, instruction-response pairs, tool or agent trajectories, code corpora, synthetic examples, revised datasets, base-model evals, pass@k skill maps, train-validation-test splits…
Skill Claude CodeCodex
Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the user wants provocative attention-pull, category-defining language, or aggressive devil's-advocate defense without losing…
Skill Claude CodeCodex
Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling. Use when scoping agent work, deciding if a task is within reach, planning retries/parallelism, estimating wall-clock time for SWE/MLE/math tasks, or answering "can you do this" / "how long will this…
Skill Claude CodeCodex
Filter, compare, and rank papers, posts, captures, threads, bookmarks, product claims, or research ideas for high-entropy mechanistic insight and underpriced leverage. Use when the user asks for alpha, high entropy, the most intriguing or insightful items, sexy ideas, nerdsnipes, sapiosexual appeal, ideas worth…
Skill Claude CodeCodex
Trigger when: (1) the user asks for Manim, Manim Community, or ManimCE, (2) code contains from manim import , or (3) the task is to build a mathematical explainer animation. Opinionated Manim Community skill for concise math scenes. Focuses on scene structure, proof-style layout, visual language, text and formulas…
Skill Claude CodeCodex
Multi-specialist collaborative analysis — fans a topic out to parallel specialist subagents, cross-pollinates findings, and synthesizes across rounds.
Skill Claude CodeCodex
Canonical end-to-end workflow for turning a paper PDF or URL into grounded OCR artifacts and a teachable notes.md.
Skill Claude CodeCodex
High-accuracy OCR refinement workflow with self-scoring, Maj@K consensus voting, and targeted repair for page-faithful transcription.
Skill Claude CodeCodex
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
Skill Claude CodeCodex
Use for planning, researching, drafting, revising, or auditing technical write-ups, textbooks, papers, reports, READMEs, research notes, PR narratives, and public technical prose. Applies a full workflow, not only style rules: reader need, source audit, ontology, outline contracts, parallel research packets, serial…
Skill Claude CodeCodex
Use when planning, launching, tracking, or preserving experiments across projects, especially to separate deterministic operating rules from fuzzy experiment-defining variables that require clarification before costly or irreversible work, and to ensure any residual compatibility, migration, cleanup, or risk is…
Skill Claude CodeCodex
Issue-led atomic work logging. Use whenever the user says "worklog" or asks to run, apply, start, maintain, update, summarize, or close a worklog; also use for issue-led development, master or umbrella issue tracking, one-issue-per-bug/feature/change workflows, atomic issue-scoped commits, GitHub issue comment…
Skill Claude CodeCodex
Use when the user provides an X/Twitter status URL and needs the full thread, context beyond the first post, comparison, summary, intent analysis, title extraction, or reliable post text. Convert status links to Twitter Thread Reader URLs using the tweet id when X is blocked, incomplete, or thread context matters.