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/discover/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/discover)<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>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 | $0.00106 | $0.02786 |
| Opus 5 | $0.00053 | $0.01393 |
| Sonnet 5 | $0.00021 | $0.00557 |
| Haiku 4.5 | $0.00011 | $0.00279 |
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.
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/initplanner 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 dedupwiki/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 logAPPEND
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-anchors、from-topic 或 from-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
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.
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 · 169 lines · 106 tokens per session scan A 465a44b67f93
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.
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.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
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…
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…
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…
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"…