Claude skills and agent skills

DAIR-AutoResearchSkill

ask

DAIR-AutoResearch/AutoSci/.claude/skills/ask/SKILL.md

Ask the wiki a question, retrieve and synthesize relevant pages, optionally crystallize the answer back into the wiki

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

check

DAIR-AutoResearch/AutoSci/.claude/skills/check/SKILL.md

Scan the full wiki to detect health issues and produce a tiered fix-recommendation report (covers all entity types in runtime/schema/entities.yaml + graph consistency)

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

discover

DAIR-AutoResearch/AutoSci/.claude/skills/discover/SKILL.md

Build a ranked shortlist of candidate papers (anchor-driven, topic-driven, or derived from current wiki state) that the user — or an upstream skill — may decide to feed into `/ingest`. Use whenever the user asks "what should I read next", "find papers similar to this one", "recommend related work", "what's around this topic", or whenever `/ingest` is invoked with `--discover`. Does not ingest; only proposes.

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

edit

DAIR-AutoResearch/AutoSci/.claude/skills/edit/SKILL.md

Add or remove raw sources, or update wiki content, per user request

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

exp-design

DAIR-AutoResearch/AutoSci/.claude/skills/exp-design/SKILL.md

Idea-driven experiment design with iterative ablation — method candidate generation (direct / hybrid / cross-idea combination) → benchmark selection → iterative ablation (non-linear: ablation can trigger method simplification and re-planning) → sensitivity analysis → main experiment → optional generalization → deep analysis of intermediate quantities. Use when designing a full experiment suite for an idea after pilot evaluation.

DAIR-AutoResearchSkill

exp-eval

DAIR-AutoResearch/AutoSci/.claude/skills/exp-eval/SKILL.md

Experiment verdict gate — Review LLM independently judges results → 4 verdict paths → auto-update the linked idea's status / failure_reason and graph edges

DAIR-AutoResearchSkill

exp-pilot-eval

DAIR-AutoResearch/AutoSci/.claude/skills/exp-pilot-eval/SKILL.md

Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

DAIR-AutoResearchSkill

exp-pilot-run

DAIR-AutoResearch/AutoSci/.claude/skills/exp-pilot-run/SKILL.md

Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

DAIR-AutoResearchSkill

exp-run

DAIR-AutoResearch/AutoSci/.claude/skills/exp-run/SKILL.md

Full experiment execution pipeline — prepare code → deploy(Confirm with the user before operation and ask the applicant to conduct manual inspection) → monitor → collect results, supporting three run modes

DAIR-AutoResearchSkill

exp-status

DAIR-AutoResearch/AutoSci/.claude/skills/exp-status/SKILL.md

View the status of all running experiments; optionally auto-collect completed experiments and advance the pipeline

DAIR-AutoResearchSkill

ideate

DAIR-AutoResearch/AutoSci/.claude/skills/ideate/SKILL.md

Multi-phase research idea generation pipeline: landscape scan → dual-model brainstorm → filter & validation → write to wiki → pilot

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

novelty

DAIR-AutoResearch/AutoSci/.claude/skills/novelty/SKILL.md

Multi-source novelty verification — WebSearch + Semantic Scholar + wiki + Review LLM cross-verify — outputs novelty score and recommendations. Optionally writes the score back to an idea page with --write.

DAIR-AutoResearchSkill

paper-compile

DAIR-AutoResearch/AutoSci/.claude/skills/paper-compile/SKILL.md

LaTeX compile → PDF — latexmk compile + auto-fix + page count/anonymity/font/[UNCONFIRMED] checks + submission checklist

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

paper-draft

DAIR-AutoResearch/AutoSci/.claude/skills/paper-draft/SKILL.md

Draft a LaTeX paper from PAPER_PLAN — write each section from wiki sources + generate figures/tables + BibTeX verification + de-AI polish

DAIR-AutoResearchSkill

paper-plan

DAIR-AutoResearch/AutoSci/.claude/skills/paper-plan/SKILL.md

Compile a paper outline from the idea graph — evidence map → narrative structure → section plan + figure plan + citation plan, Review LLM review mandatory

Often used withdaily-arxiv·paper-illustration·exp-eval

DAIR-AutoResearchSkill

poster

DAIR-AutoResearch/AutoSci/.claude/skills/poster/SKILL.md

Generate an academic poster from a drafted paper — distill sections into a single-page HTML poster with figures and inter-section transitions

DAIR-AutoResearchSkill

prefill

DAIR-AutoResearch/AutoSci/.claude/skills/prefill/SKILL.md

Seed wiki/foundations/ with domain background knowledge so subsequent /ingest does not create duplicate concept pages for textbook material

DAIR-AutoResearchSkill

rebuttal

DAIR-AutoResearch/AutoSci/.claude/skills/rebuttal/SKILL.md

Parse review comments → atomize concerns (Rvx-Cy) → map to wiki ideas/methods → check evidence → Review LLM stress-test → generate rebuttal

Often used withdaily-arxiv·exp-eval·exp-run

DAIR-AutoResearchSkill

refine

DAIR-AutoResearch/AutoSci/.claude/skills/refine/SKILL.md

General-purpose multi-round iterative improvement — repeatedly calls /review on any research artifact, parses feedback, applies fixes, updates wiki, until the target score is reached

Often used withaddskill·daily-arxiv·astra-fullreview

DAIR-AutoResearchSkill

research

DAIR-AutoResearch/AutoSci/.claude/skills/research/SKILL.md

End-to-end research orchestrator — idea discovery → experiment design → execution → verdict → paper writing, with human gates and session-resumable state

Often used withdaily-arxiv·Problem-Solving Techniques·setup-ts-deep-modules