Research AI agent skills

1,871 skills in the archive. Read a skill’s instructions or open its original repository.

• Citation Injector

  by @WILLOSCAR

  APPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without…

• Artifact Contract Auditor

  by @WILLOSCAR

  Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.

• Human Checkpoint

  by @WILLOSCAR

  Review and record one pending human checkpoint in a research Workspace; use when a HUMAN Unit is blocked on an `Approve C*` decision, and never treat silence or artifact existence as approval.

• Claim Matrix Rewriter

  by @WILLOSCAR

  Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl` rather than outline placeholders.

• Section Logic Polisher

  by @WILLOSCAR

  Logic coherence pass for per-H3 section files: enforce a clear paragraph-1 thesis and surface paragraph-island risks (connector stats are diagnostic, not a quota) before merging.

• Idea Signal Mapper

  by @WILLOSCAR

  Map paper notes + taxonomy into a signal table of tensions, missing pieces, and promising academic axes for brainstorm discussion. Writes `output/trace/IDEA_SIGNAL_TABLE.md`.

• Evidence Selfloop

  by @WILLOSCAR

  Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.

• Section Merger

  by @WILLOSCAR

  Deterministically merge the final fingerprinted section snapshot into `output/DRAFT.md`, preserving outline order and inserting transitions only when explicitly enabled.

• Opener Variator

  by @WILLOSCAR

  Rewrite subsection openers so they stop reading like a generated table-of-contents: remove \"overview/narration\" stems and reduce repeated opener cadences across H3s.

• Checkpoint Brief

  by @WILLOSCAR

  Project completed stage Artifacts into a concise human-review block in `DECISIONS.md`; use before a Workflow checkpoint, not for Workflow routing or approval.

• Prose Writer

  by @WILLOSCAR

  Write `output/DRAFT.md` (or `output/SNAPSHOT.md`) from an approved outline and evidence packs, using only verified citation keys from `citations/ref.bib`.

• Table Schema

  by @WILLOSCAR

  Define evidence-first table schemas for a survey: what each table must answer, row unit, columns, and which evidence-pack fields are required to fill it.

• Chapter Briefs

  by @WILLOSCAR

  Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.

• Pdf Text Extractor

  by @WILLOSCAR

  Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`.

• Paragraph Curator

  by @WILLOSCAR

  Deterministically compact final H3 bodies to the active delivery profile's paragraph budget without deleting prose or changing citation-block order.

• Pipeline Auditor

  by @WILLOSCAR

  Audit/regression checks for the evidence-first survey pipeline: citation health, per-section coverage, placeholder leakage, and template repetition.

• Post Merge Voice Gate

  by @WILLOSCAR

  Post-merge paper-voice gate: inspect the reader-facing draft for planner-talk and axis-label artifacts, then route fixes to the actual source.

• Snapshot Writer

  by @WILLOSCAR

  Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full survey.

• Outline Refiner

  by @WILLOSCAR

  Planner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`.

• Survey Seed Harvest

  by @WILLOSCAR

  Identify survey/review papers in a retrieved set and extract taxonomy seeds into `outline/taxonomy.yml` (topics/subtopics/terminology).

• Idea Direction Generator

  by @WILLOSCAR

  Generate a compact pool of discussion-worthy research directions from the signal table, writing `output/trace/IDEA_DIRECTION_POOL.md`.

• Evidence Binder

  by @WILLOSCAR

  Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.

• Latex Compile Qa

  by @WILLOSCAR

  Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.

• Schema Normalizer

  by @WILLOSCAR

  Normalize cross-skill JSONL interfaces (ids + titles + citation key formats) so downstream skills do not rely on best-effort joins.

• Draft Polisher

  by @WILLOSCAR

  Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.

• Source Tutorial Spec

  by @WILLOSCAR

  Use when a `source-tutorial` workspace has ingested sources and needs a grounded tutorial contract before structure planning.

• Agent Survey Corpus

  by @WILLOSCAR

  Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

• Argument Selfloop

  by @WILLOSCAR

  Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.

• Table Filler

  by @WILLOSCAR

  Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows).

• Claim Evidence Matrix

  by @WILLOSCAR

  Seed `outline/claim_evidence_matrix.md` from outline+notes; claim-matrix-rewriter rewrites it later from evidence packs.

• Concept Graph

  by @WILLOSCAR

  Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.

• Module Source Coverage

  by @WILLOSCAR

  Use when a tutorial module plan exists and the run needs an auditable module-to-source grounding file before prose.

• Citation Verifier

  by @WILLOSCAR

  Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.

• Idea Screener

  by @WILLOSCAR

  Screen the direction pool with a discussion-first scoring pass, writing `output/trace/IDEA_SCREENING_TABLE.md`.

• Global Reviewer

  by @WILLOSCAR

  Global consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.

• Module Planner

  by @WILLOSCAR

  Use when a tutorial concept DAG exists and the run needs an ordered teaching plan with objectives and outputs.

• Source Tutorial Writer

  by @WILLOSCAR

  Use when approved tutorial context packs exist and the run needs the final article-first tutorial deliverable.

• Evidence Auditor

  by @WILLOSCAR

  Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.

• Source Manifest

  by @WILLOSCAR

  Build or validate the source manifest for the source-tutorial pipeline from user-provided URLs/files.

• Style Harmonizer

  by @WILLOSCAR

  De-slot and harmonize paper voice across `sections/*.md` without changing meaning or citation keys.

• Rubric Writer

  by @WILLOSCAR

  Use when `paper-review` has claims plus evidence gaps and needs the final referee-style report.

• Exercise Builder

  by @WILLOSCAR

  Use when a tutorial module plan exists but each module still needs a verifiable teaching loop.

• Bias Assessor

  by @WILLOSCAR

  Use when `evidence-review` has an extraction table and needs lightweight risk-of-bias fields.

• Extraction Form

  by @WILLOSCAR

  Use when `evidence-review` has screened includes and needs a schema-aligned extraction table.

• Synthesis Writer

  by @WILLOSCAR

  Use when `evidence-review` has completed extraction and needs a bounded narrative synthesis.

• Manuscript Ingest

  by @WILLOSCAR

  Use when `paper-review` needs a canonical manuscript text artifact before claim extraction.

• Source Ingest

  by @WILLOSCAR

  Fetch and normalize supported source-tutorial inputs into local, traceable text artifacts.

• Protocol Writer

  by @WILLOSCAR

  Use when `evidence-review` needs an operational protocol before screening and extraction.

• Screening Manager

  by @WILLOSCAR

  Use when an approved `evidence-review` protocol needs to be applied to a candidate pool.

• Novelty Matrix

  by @WILLOSCAR

  Use when `paper-review` needs overlap/delta positioning against provided related work.

• Beamer Scaffold

  by @WILLOSCAR

  Generate a Beamer slide deck from the final tutorial and approved module structure.

• Claims Extractor

  by @WILLOSCAR

  Use when a review workspace has manuscript text and needs a traceable claim ledger.

• Beamer Compile Qa

  by @WILLOSCAR

  Compile the Beamer tutorial deck and write a build report.

• Research Pipeline Runner

  by @WILLOSCAR

  Run a research Workflow end to end when the user requests a survey, brief, review, tutorial, or idea exploration; route an unbound goal, execute one eligible Unit at a time, and stop at checkpoints or diagnosed failures.

• Limitation Weaver

  by @WILLOSCAR

  Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \"Two limitations…\") across many H3s.

• Redundancy Pruner

  by @WILLOSCAR

  Remove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning.

• Subsection Polisher

  by @WILLOSCAR

  Polish a single H3 unit file under `sections/` into survey-grade prose (de-template + contrast/eval/limitation), without changing citation keys.

• Citation Anchoring

  by @WILLOSCAR

  Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.

• Outline Budgeter

  by @WILLOSCAR

  Merge/simplify an over-fragmented outline to hit a paper-like section budget (NO PROSE): target final ToC ~6–8 H2, fewer thicker H3.

• Terminology Normalizer

  by @WILLOSCAR

  Normalize terminology across a draft (canonical terms + synonym policy) without changing citations or meaning.

• Grad Paragraph

  by @WILLOSCAR

  Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).

• Keyword Expansion

  by @WILLOSCAR

  Expand and refine search keywords (synonyms, acronyms, exclusions) and update `queries.md`.

• Creative Research

  by @haowjy

  Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced…

• Zoom Out

  by @haowjy

  Use when orienting in an unfamiliar area — fans out exploration across structure, knowledge, and history, then synthesizes one orientation map.

• Qiaomu Markdown Proxy

  by @joeseesun

  Read, fetch, extract, parse, or convert a URL or link into clean Markdown. Use FIRST whenever a user asks to read source content from a webpage, especially WeChat/微信公众号 mp.weixin.qq.com, Feishu/Lark docs, X/Twitter, PDFs, arXiv…

• Autonomous Research

  by @federicodeponte

  An 18-agent pipeline that turns one topic line into a drafted research paper, literature review, or thesis chapter. Finds real sources at Crossref and OpenAlex, drafts each section against them, attacks its own draft for weak…

• Components.Write Docs

  by @coinbase

  Guidelines for creating or updating documentation for a CDS component on the docsite (apps/docs/). Use this skill after creating or making updates to a CDS React component to write high quality documentaiton in the CDS docsite.

• File Reader

  by @pilinux

  Precisely read source files or snippets and return concise, citation-backed facts needed for decisions or edits.

• Explain Code

  by @pilinux

  Produce concise, citation-backed explanations of module behavior, data flow, and important types/APIs.

• Adjust Abstraction Scope

  by @yogsoth-ai

  Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system boundary) until the representation has useful explanatory and experimental…

• Analyze Temporal Trajectory

  by @yogsoth-ai

  Analyze an ordered temporal trajectory, including persistence/narrowing/widening tests, regime changes, inflection points, and optional extrapolation with uncertainty. Entity type, window, and forecast mode are parameters.

• De Anthropocentric Research Engine

  by @yogsoth-ai

  DARE v4 is the product-level orchestrator for a research run. It turns a user request into a controlled sequence of North Star crystallization, executable specification, and phase-by-phase execution.

• Conceptual Blending

  by @yogsoth-ai

  Construct multiple input spaces, extract a shared generic space, selectively project structure into a blend, and simulate emergent properties that are not present in either source alone.

• Analyze Patent Citation Network

  by @yogsoth-ai

  Analyze patent citation/family relationships to identify central prior art, technological lineage, clusters, bridge patents, and citation anomalies.

• Appreciative Reframe

  by @yogsoth-ai

  Reframe a problem around functioning exceptions, existing strengths, positive deviance, and conditions under which desired behavior already occurs.

• Assess System Boundary

  by @yogsoth-ai

  Define and challenge the system boundary: what actors, processes, externalities, timescales, and value assumptions are included or excluded.

• Attach Evidence To Relation

  by @yogsoth-ai

  Attach supporting or contradicting evidence to a specific claim/relation with quality, directness, and independence metadata.

• Decompose Research Goal

  by @yogsoth-ai

  Turn a research direction into an AND/OR goal DAG with testable leaves, dependency structure, and feasibility annotations.

• Crystallize North Star

  by @yogsoth-ai

  Compress the goal structure and intentionality into a specific, ambitious, achievable one-sentence research North Star.

• Assess Question Quality

  by @yogsoth-ai

  Audit a research question for scope and FINER-style quality; return targeted repairs.

• Define Criteria

  by @yogsoth-ai

  Derive explicit evaluation criteria from the research objective and candidate set.

• Apply Question Framework

  by @yogsoth-ai

  Select and instantiate a research-question schema appropriate to study type.

• Decompose Ishikawa

  by @yogsoth-ai

  Build an Ishikawa-style causal decomposition across relevant cause families.

• Latex Paper En

  by @bahayonghang

  English LaTeX assistant for existing .tex journal or conference papers. Use for compile repair, venue formatting, bibliography/citation checks, section writing, logic, related work, tables, pseudocode, de-AI polish,…

• Paper Audit

  by @bahayonghang

  Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf. Use for peer-review critique, readiness/gate decisions, blocker triage, revision roadmaps, journal-style reports, re-audits, and under-claim /…

• Typst Paper

  by @bahayonghang

  Typst paper assistant for existing .typ manuscripts in English or Chinese. Use for compile/export diagnosis, venue formatting, BibTeX/Hayagriva checks, grammar, logic, abstract/title, tables, pseudocode, related work,…

• Cover Letter

  by @bahayonghang

  Submission cover-letter assistant for existing LaTeX manuscripts. Use to generate, optimize, align-check, preflight, and journal-fit-check cover letters against paper evidence, novelty claims, and target venue expectations. Also…

• Paper Writing Studio

  by @bahayonghang

  Use this academic writing skill to polish or translate academic writing with an explicit Nature, IEEE, Elsevier, or neutral profile. Selects a profile by explicit venue, journal allowlist, then unambiguous domain; reports…

• Bib Search Citation

  by @bahayonghang

  Search and cite from local BibTeX/BibLaTeX .bib libraries, including Zotero exports. Use to find, filter, preview, export, or generate LaTeX/Typst citation snippets by topic, author, year, venue, DOI, arXiv ID, keywords,…

• Outreach

  by @andrew-shwetzer

  Draft personalized outreach messages for LinkedIn connections, hiring managers, or recruiters. Creates targeted messages using a hook + proof + proposal structure. Under 300 characters for connection requests. Use when someone…

• Research

  by @andrew-shwetzer

  Research a company before applying or interviewing. Get an intelligence brief with culture, financials, recent news, team structure, key contacts, and smart interview questions. Use when someone says 'research this company',…

• Scan

  by @andrew-shwetzer

  Scan company career pages for job openings that match your profile. Uses web search with site-scoped queries to find listings on Greenhouse, Lever, Ashby, SmartRecruiters, and other ATS platforms. Use when someone says 'scan for…

• Kimi Webbridge

  by @mxyhi

  Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever…

• Exa Search

  by @mxyhi

  Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.

• Tavily Best Practices

  by @tavily-ai

  Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and…

• Tavily Search

  by @tavily-ai

  Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look…

• Tavily Map

  by @tavily-ai

  Discover and list all URLs on a website without extracting content, via the Tavily CLI. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where something is…

• Tavily Research

  by @tavily-ai

  Conduct comprehensive AI-powered research with citations via the Tavily CLI. Use this skill when the user wants deep research, a detailed report, a comparison, market analysis, literature review, or says "research",…

• Tavily Cli

  by @tavily-ai

  Set up, authenticate, update, troubleshoot, or choose between Tavily CLI web commands. Use when the user asks about the Tavily CLI, installing Tavily skills, first-time setup, authentication, keyless limits, CLI updates, or…

• Tavily Dynamic Search

  by @tavily-ai

  Programmatic Tavily search with context isolation. Use when web search or extraction will return large results that need filtering, deduplication, or multi-step triage before they enter the model context. Use tavily-search for…