Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown, capturing documentation, or monitoring competitor changes.
Monitors tracked preprints on arXiv, bioRxiv, and medRxiv for new versions, journal publication, peer review outcomes, and major revisions. Use when the user wants to be notified when a specific preprint is updated, published, or retracted, when tracking competitor papers, or when monitoring their own preprint's trajectory. Triggers on phrases like "watch this preprint", "track this arXiv paper", "has this been published yet", "any updates to", "monitor this preprint", "is this still a preprint", "what happened to", "version history".
Monitors incoming citations to the team's own papers and classifies them by type and context. Use when the user wants to know who has cited their work, track citation velocity, find papers that build on or challenge their results, generate a citation report for a grant renewal or review, or discover unexpected applications of their work. Triggers on phrases like "who cited our paper", "citation alert", "citation count", "has anyone cited X", "citation report", "who's building on our work", "citation velocity", "h-index".
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
Quick ephemeral sticky notes for project-wide capture before formal classification
Connects to a team's Zotero library to read, sync, and write paper collections, annotations, and notes. Use when the user wants to sync PaperClaw with their Zotero library, import an existing paper collection, pull annotations from Zotero, push summaries back to Zotero items, or export a collection to BibTeX. Triggers on phrases like "sync with Zotero", "import from Zotero", "our Zotero library", "pull from Zotero", "export to BibTeX", "Zotero collection".
Tracks specific scientific claims over time — who made them, who replicated or challenged them, and whether they still stand. Use when the user wants to verify a claim before building on it, check if a key result has been replicated, register a central claim from their own work, track whether cited results remain valid, or check if a paper has been retracted. Triggers on phrases like "has this been replicated", "does this claim still hold", "track this result", "verify this finding", "has X been retracted", "provenance of this claim", "register this claim".
A/B test evaluation, cohort retention analysis, funnel metrics, and experiment-driven product decisions. Use when analyzing experiments, measuring feature adoption, diagnosing conversion drop-offs, or evaluating statistical significance of product changes.
OKR trees, KPI dashboards, North Star Metric, leading/lagging indicators, and experiment design. Use when setting team goals, defining success metrics, building measurement frameworks, or designing A/B experiment guardrails.
Analyse text complexity across quantitative, qualitative, and reader-task dimensions with scaffolding recommendations. Use when selecting texts, assessing readability, or planning reading support.
Analyse existing written feedback for quality, specificity, actionability, and impact on student learning. Use when reviewing teacher or peer feedback to improve feedback practices.
End-to-end academic paper workflow: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), read with structured analysis (3-level strategy), and organize into literature maps or reports. Use when: finding papers, reading a paper, related work, literature survey, citation analysis, research trends, SOTA results, datasets, or literature reports. Do NOT use for writing a literature review section (use paper-writing), comparing research ideas (use idea-tournament), or planning paper structure (use paper-planning).
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust, promote limitations, attack novelty), reverse-outlining, and figure/table quality checks. Use when: user wants to self-review or self-check their own paper draft before submission, stress-test their claims, prepare for reviewer criticism, or mentions 'self-review', 'check my draft', 'is my paper ready'. Do NOT use for writing a peer review of someone else's paper, and do NOT use after receiving actual reviews (use paper-rebuttal instead).
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and experiment-craft (5-step diagnostic on failure). Use when: user has a planned experiment, needs to reproduce baselines, organize experiment workflow, or systematically validate a method. Do NOT use for debugging a specific experiment failure (use experiment-craft) or designing which experiments to run (use paper-planning).
Use this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs, hypotheses, failures, results, and next steps during active research. Apply it to underperforming methods, training that will not converge, regressions after a change, inconsistent results across datasets, aimless experimentation without progress, and questions like 'why doesn't this work?', 'no progress after many attempts', or 'how should I investigate this failure?'. Also use it for setting up practical experiment logging/record-keeping that supports debugging and iteration. Do not use it for designing a brand-new experiment pipeline or full experiment program (use experiment-pipeline), generating research ideas, fixing isolated coding/syntax errors, or writing retrospective summaries into research memory/notes/knowledge bases.
Feasibility analysis from first principles. Use when: evaluating solutions before tech-spec, comparing approaches, risk assessment. Not for: implementation (use feature-dev), architecture advice (use codex-architect). Output: quantitative comparison + recommendation.
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).
Reviews pull requests and code changes in this Ansible collection against project standards and the Ansible Collection Review Checklist. Use when asked to review a PR, patch, diff, or set of code changes. Do not use for GitHub Issues or general Q&A.
Student database processing tools. Includes grade calculation, duplicate name detection, recommendation letter filtering, and TOEFL score filtering.
This skill should be used when the user asks about "technical decision", "what to use", "A vs B", "comparison analysis", "library selection", "architecture decision", "which one to use", "tradeoffs", "tech selection", "implementation approach", or needs deep analysis for technical decisions. Provides systematic multi-source research and synthesized recommendations.
This skill should be used when the user asks to "find references", "참고할 만한 거", "similar implementation", "오픈소스 있나", "how others do this", "레퍼런스 찾아줘", or needs to find existing patterns (internal) and open-source examples (external) for implementing a feature.
