ask
Skill9 starsChanged 5 months agoMITView on GitHub
Answer a question from the knowledge base — retrieve relevant notes, synthesize a cited answer, and flag gaps (optionally searching the web for what's missing)
76 other projects use a version of this.
Adopted by
Most recently taken up by
- finolabs/finolabs-vibecodetheir own version, first seen Nov 16, 2026
- mad01/thismoontheir own version, first seen Nov 15, 2026
- AndyMelnykov/obsidian-claudetheir own version, first seen Nov 15, 2026
- finolabs/vibecodetheir own version, first seen Nov 15, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 9, 2026
- jskswamy/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
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.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
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.
Also in 4 projects that use this
phanghonghaoSkillposter
HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.
Also in 4 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions76 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 76
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- acunniffe/git-ai★ 3ksame name
- git-ai-project/git-ai★ 3ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
66 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- .claude/AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- alphaxivSkill
- autoexploreSkill
- collateSkill
- curriculumSkill
- editSkill
- goalSkill
- notionSkill
- obsidianSkill
- retrieveSkill
- tutorSkill
- webSkill
- zoteroSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 62 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
If $ARGUMENTS is empty, ask the user for their question, then continue.
- Very specific: line 20
Retrieve: Use the /retrieve skill to gather the notes relevant to the question across the whole base: get BM25 seeds, then expand by …
- Distinctive: line 43
Flag gaps: If the base doesn't fully answer the question, say so plainly and name what's missing — e.g.
“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Answer $ARGUMENTS using the local knowledge base. Retrieve the relevant notes, synthesize an answer grounded in them with inline citations, and be explicit when the base doesn't have enough to answer.
If $ARGUMENTS is empty, ask the user for their question, then continue.
Layout
Knowledge-base I/O is at the repo root, across sources/ (objective paper text),
notes/ (personal notes), papers/ (paper pages), and concepts/ (concept pages).
Steps
Retrieve. Use the
/retrieveskill to gather the notes relevant to the question across the whole base: get BM25 seeds, then expand by following relevant wikilinks.sh .claude/src/pyrun .claude/src/retrieve_cli.py --retrieve "$ARGUMENTS" sh .claude/src/pyrun .claude/src/retrieve_cli.py --resolve "<linked topic>" ...Readeach relevant file.- Synthesize an answer. Answer the question directly and concisely in your own
words, grounded only in the retrieved files. Cite each claim inline with a
relative link to the file it came from, e.g.
ReAct grounds reasoning in tool observations, cutting hallucination ([ReAct](papers/react.md)). Distinguish objective findings (sources/,papers/) from the user's own notes (notes/) where it matters. Where the answer is mathematical, give the relevant equations/derivations rather than vague prose (the Page conventions in.claude/AGENTS.mdcover this). Format note: answers print to the terminal, which does not render LaTeX, so use plain readable notation (e.g.sqrt(d_k)) in the reply; only switch to LaTeX ($ ... $/$$ ... $$) if the user asks to save the answer into a page. - Flag gaps. If the base doesn't fully answer the question, say so plainly and
name what's missing — e.g. "no source in the base covers X". If it would help,
use
WebSearch/WebFetchto identify what the missing material is (a paper, a method, a result) and suggest the user ingest it via/paper. Clearly mark any web-derived information as not from the knowledge base and do not present it as a cited base answer.
Wrap up
End with a short Sources list (the base files you cited) and, separately, any
gaps found — so the user can fill them with /paper or /concept.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

