Borrowing it
Nothing to install: this file belongs to Lambenthan/empiricalwiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/research/SKILL.mdgit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lambenthan/empiricalwiki/research)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/research"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/research.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.06180 |
| Opus 5 | $0.00018 | $0.03090 |
| Sonnet 5 | $0.00007 | $0.01236 |
| Haiku 4.5 | $0.00004 | $0.00618 |
Grade A, and why
research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 549 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research
端到端研究编排器，将所有 skill 组合为完整的研究流程。 Stage 0 (Bootstrap) + 5 个 Stage + 2 个 Human Gate，覆盖从空 wiki 到论文提交的全流程。 零摩擦入口：wiki 为空时自动触发 Bootstrap（搜索 + auto-ingest 5 篇论文），无需手动 /init。 每个 Gate 和 Stage 保存进度到
wiki/outputs/pipeline-progress.md，支持跨 session 恢复。Stage 3 为非阻塞设计：实验部署后立即返回（
--auto模式自动设置 CronCreate 每 30 分钟监控）， 实验全部完成后自动进入 Stage 4。可随时用/exp-status查看进度。
--auto模式跳过人工确认（自动选 top-1 idea），--skip-paper只做研究不写论文。
Inputs
direction：研究方向描述或RESEARCH_BRIEF.md文件路径- 文本形式：一句话描述研究方向（如 "sparse LoRA for edge devices"）
- 文件形式：结构化的 RESEARCH_BRIEF.md（含 domain、constraints、target venues）
--auto（可选）：全自动模式，Gate 1 自动选 top-1 idea，Gate 2 自动继续，Stage 3b 自动 CronCreate--start-from <stage>（可选）：从指定 stage 恢复执行- 有效值：
stage1、stage2、stage3、stage3-collect、stage3-check、stage4、stage5 stage3-collect：跳过 deploy，直接进入 Stage 3c（收集已部署实验的结果）stage3-check：只检查实验状态（等同于/exp-status --pipeline {slug}），不继续执行- 需要
wiki/outputs/pipeline-progress.md存在
- 有效值：
--skip-paper（可选）：只做研究（Stage 1-4），不写论文（跳过 Stage 5），但仍执行 /exp-eval（Stage 4）--venue（可选）：目标会议（ICLR / NeurIPS / ICML / ACL / CVPR），传递给 /paper-plan
Outputs
- wiki 更新（通过子 skill 委托）：ideas/、experiments/、claims/、outputs/、graph/
- wiki/outputs/pipeline-progress.md — 流水线进度快照（用于恢复）
- wiki/outputs/PIPELINE_REPORT.md — 完整流水线报告
- paper/ 目录（若未 --skip-paper）— 可提交的论文
- wiki/log.md — 每个 stage 追加日志
Wiki Interaction
Reads
wiki/graph/context_brief.md— 全局上下文（传递给子 skills）wiki/graph/open_questions.md— 知识缺口（传递给 /ideate）wiki/ideas/*.md— Gate 1 选择、Stage 4 判决wiki/experiments/*.md— Stage 3-4 状态检查wiki/claims/*.md— Stage 4 判决、Stage 5 论文规划wiki/outputs/pipeline-progress.md— --start-from 恢复状态wiki/papers/*.md— Stage 5 论文写作上下文
Writes
wiki/outputs/pipeline-progress.md— 每个 Gate 保存进度（委托写入 wiki 实体的操作由子 skill 完成）wiki/outputs/PIPELINE_REPORT.md— 最终报告wiki/log.md— 追加日志- 其他 wiki 实体写入均通过子 skill 委托（不直接写入 ideas/experiments/claims/）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 549 lines · 36 tokens per session scan A 70c085f970ff
research is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 6,180 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review-paper
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via…
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
grant-proposal
Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist. Use…
preregister
Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when…
capture-environment
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…
data-management-plan
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…