aeon-paper-pick
Surface the one AI / ML paper to read today from Hugging Face Papers, with the central claim, why it's worth an hour, where it might be wrong, and a time-budgeted read order. Filters out pure benchmark-chasing and incremental scaling reports. Use as a daily morning brief input for AI-savvy operators. Triggers: "one paper to read today", "best AI paper today", "what's the must-read paper", "HF Papers top pick".
What this skill does
# aeon-paper-pick One paper per day. Not a digest — one pick, with a short brief that lets the reader decide whether to invest the next hour. ## How the pick works 1. Fetch last 24h of HF Papers (`https://huggingface.co/papers`). 2. Drop pure benchmark-chasing (new SOTA on existing leaderboard, no method change), incremental scaling reports, and position papers without empirical claims. 3. Score survivors on novelty of method/framing, falsifiability of central claim, reproducibility signal (code + weights + data), and cross-discipline applicability. 4. Pick the highest scoring. Tie-break: sharper falsifiable claim. ## Brief format ``` [Paper title] Authors: A, B, C (Lab) arXiv: 2505.xxxxx Central claim: [one sentence, plain English] Why it's worth an hour: - [method shift, not benchmark bump — they replace X with Y] - [claim is falsifiable: ablation in §4 isolates X vs not-X cleanly] - [code + weights released, reproducible at home] Where it might be wrong: - [training distribution is narrow — open question whether the effect transfers] - [comparison baseline is older than expected] Read order: 1. §3 (method) — 8 min 2. §4 (ablations) — 12 min 3. §6 (limitations) — 5 min Optional: §5 (extended experiments) ``` ## Empty days If 0 papers survive the filter: ``` No surviving picks today. 14 papers filtered out: 6 benchmark-chasing, 5 incremental scaling, 3 position papers. Worth scrolling yourself: huggingface.co/papers ``` Honesty over manufactured picks. ## Rules - One pick, not three. Three picks is a digest, and digests become wallpaper. - "Where it might be wrong" is mandatory. - Read order time-budgeted. Save the reader from skimming the whole PDF. - Cite actual sections so the reader can verify the brief.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.