empiricalwiki: Skill for Claude Code

.claude/skills/discover/SKILL.md

discover is a skill for Claude Code from Lambenthan/empiricalwiki. It costs 106 tokens per session (2,786 once invoked), scanned A, original, MIT.

A research-paper discovery tool that builds a ranked shortlist from a paper, a topic, or the current research wiki. It suggests candidates but does not add them to the wiki.

In plain words
What is it for?
Use it to find work similar to a paper, explore a topic, or continue reading from recently updated wiki pages.
Why use it?
It narrows a large research area to papers worth considering next while avoiding papers already recorded in the wiki.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is Lambenthan/empiricalwiki's own configuration. It tells Claude Code how to work on empiricalwiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything empiricalwiki configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/discover/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Lambenthan/empiricalwiki

Made for: Claude Code.

Wrote 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.

agentmods badge for discover

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/discover.svg)](https://agentmods.dev/skills/lambenthan/empiricalwiki/discover)
Your own site
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/discover"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.02786
Opus 5 $0.00053 $0.01393
Sonnet 5 $0.00021 $0.00557
Haiku 4.5 $0.00011 $0.00279

Measured 8d ago against content hash 465a44b67f93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

discover 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.

.claude/skills/discover/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/discover

从三种 seed 模式之一产出一份排好序的候选论文 shortlist,附带每条候选的 rationale,呈现给用户或调用方 skill。/discover 绝不自动 ingest —— 它只负责提出候选,实际动作由 /ingest 负责。

按需打开下列本地参考文件:

  • references/seed-modes.md —— 如何把用户的措辞映射到 anchor / topic / wiki 模式,以及三者的选择规则
  • references/ranking-signals.md —— tools/discover.py 的打分依据,以及为什么 discovery 不共享 /init 的 survey 偏好
  • references/wiki-dedup.md —— 候选如何被过滤掉已 ingest 的论文,以及 dedup 边界

Inputs

  • --anchor <id>(可重复):一或多个 anchor 论文 ID(优先 arXiv ID,也接受 S2 paperId)。驱动 anchor 模式 —— 主要使用场景,包括 /ingest 后的 "接下来该读什么"。
  • --negative <id>(可重复,可选):希望推开的论文 ID。只在配合 --anchor 时有意义。
  • --topic "<str>":topic / query 字符串。驱动 topic 模式 —— 相对 /init planner 更轻量的替代。
  • --from-wiki:自动从 wiki 最近修改过的论文页派生 seed。驱动 wiki 模式
  • --limit N(可选,默认 10):shortlist 最大长度。

--anchor--topic--from-wiki 三者必须恰好选一。

Outputs

  • .checkpoints/discover-{seed-slug}-{YYYY-MM-DD}.json —— 完整 shortlist payload,机器可读;seed slug 基于首个 anchor 或 topic 派生
  • 给用户的 markdown 摘要,包含每条候选的 rationale
  • wiki/log.md —— 通过 tools/research_wiki.py log 追加一行

/discover 除了 log.md 外不向 wiki/ 写入任何内容,也不触碰 raw/。是否把候选拉进 wiki 是调用方的决定(之后的 /ingest)。

Wiki Interaction

Reads

  • wiki/papers/*.md —— frontmatter 中的 arxiv(或旧版 arxiv_id),用于与已 ingest 的论文做 dedup
  • wiki/papers/*.md 修改时间 —— 用于 --from-wiki 模式下 anchor 选取

Writes

  • wiki/log.md —— 通过 tools/research_wiki.py log APPEND

Graph edges created

  • 无。图变更属于 /ingest,不属于 /discover

Workflow

前置条件:工作目录包含 wiki/raw/tools/。一次解析 Python 解释器路径并复用:

if [ -x .venv/bin/python ]; then
  PYTHON_BIN=.venv/bin/python
elif [ -x .venv/Scripts/python.exe ]; then
  PYTHON_BIN=.venv/Scripts/python.exe
else
  PYTHON_BIN=python3
fi
export PYTHON_BIN

Step 1: 选定 seed 模式

把用户请求映射到 from-anchorsfrom-topicfrom-wiki 之一。决策规则见 references/seed-modes.md,简版:

  • 用户指明了一或多篇具体论文,或者这是 /ingest --discover 的后续 → anchors
  • 用户给的是 topic / 方向 / 关键词 → topic
  • 用户问开放式 "接下来读什么",没有 anchor 也没有 topic → wiki

Read the full file on GitHub · 169 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 8d ago First seen · 169 lines · 106 tokens per session scan A 465a44b67f93

Subscribe to this mod's changes

discover is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 2,786 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

paper-workflow

A staged workflow for producing an evidence-based economics or social-science research paper, from choosing a topic through submission. It coordinates existing tools and analysis options, including Python, Stata, and R.

brycewang-stanford/Paper-WorkFlow · 262 tokens

chinese-documentation

A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.

jnMetaCode/superpowers-zh · 62 tokens

seven-pass-review

Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review…

pedrohcgs/claude-code-my-workflow · 70 tokens

slide-excellence

Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…

pedrohcgs/claude-code-my-workflow · 94 tokens

triage-inbox

Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…

pedrohcgs/claude-code-my-workflow · 132 tokens

scaffold-exercises

Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…

pedrohcgs/claude-code-my-workflow · 101 tokens