study
Skill0 starsChanged 4 months agoMITView on GitHub
Use when Gera asks to study, quiz himself, test his recall, make flashcards, build an active-recall deck, or "test me on X" from a wiki page or knowledge source. Also handles English vocab/phrasing drills. Turns any wiki page into a repeatable active-recall deck or an interactive chat quiz.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- halilural/imprimaturtheir own version, first seen Nov 8, 2026
- Sumit189/claude-codestheir own version, first seen Nov 1, 2026
- Slava-code/slava-stacktheir own version, first seen Oct 15, 2026
- gradigit/claude-skillstheir own version, first seen Oct 15, 2026
- JangInho/claude-skillstheir own version, first seen Oct 13, 2026
- pp6235024-bit/claude-skillstheir own version, first seen Oct 11, 2026
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- akashgit/remote-factory★ 74same name
- boston-harness-group/remote-factory★ 74same name
- mordor-forge/study-skill★ 46same name
- flc1125/skills★ 38same name
- alexiocassanifm/anthropic-certifications★ 36same name
- SugarMGP/study.skill★ 13same name
- WahyuS002/skills★ 5same name
- WindyITS/skills★ 5same name
- froster02/mini-Brain_skills★ 4same name
- matvej-melikhov/karpathy-llm-wiki★ 2same name
10 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 repository50 other files it gives its agents.
- aegisSkill
- agent-builderSkill
- agents-team-builderSkill
- ai-applySkill
- auditSkill
- bottleneckSkill
- buildSkill
- capability-radarSkill
- clay-leadsSkill
- cowatchSkill
- deepforkSkill
- design-blueprintSkill
- evalSkill
- fable-modeSkill
- financesSkill
- forgeSkill
- framework-builderSkill
- grill-meSkill
- hooks-builderSkill
- level-upSkill
- loops-builderSkill
- meeting-hudSkill
- multi-brainSkill
- nate-watchSkill
- onboardSkill
- plugin-builderSkill
- ponytailSkill
- presentSkill
- prompt-evalSkill
- radar-harvestSkill
- rag-forgeSkill
- rlsgateSkill
- rnd-loopSkill
- rndSkill
- roastSkill
- routines-builderSkill
- servy-routineSkill
- session-handoffSkill
- skill-builderSkill
- skill-harvestSkill
- sparkSkill
- storm-researchSkill
- talkSkill
- taste-skillSkill
- verify-loopSkill
- verify-specificsSkill
- wheel-of-lifeSkill
- workanaSkill
- workaround-builderSkill
- workflow-builderSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
Ground every card in the source: Don't invent facts the page doesn't support.
“Common” is measured: kept by at least 6 in 10 of the 16 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
What This Skill Does
Turns any wiki page or knowledge source into active-recall practice — a flashcard deck, an interactive chat quiz, or a self-quiz HTML artifact. Generalizes the one-off references/jumpstart-flashcards.md into a repeatable workflow. Serves quarter priorities #2 (keep learning) and #3 (improve English).
Active recall beats re-reading. The point is to make Gera retrieve the answer, not recognize it.
Context to Load
- The source: a named page in
references/, or — for a topic — readreferences/index.mdand pull the matching page(s). For "english", drive vocab/phrasing drills (optionally seeded from a page he names). references/jumpstart-flashcards.md— the format exemplar for a flashcard companion page.
Steps
- Resolve the source. Named page → read it. Topic → search
references/index.md, read the best match, confirm the pick in one line. "english" → English mode (below). - Pick the mode (ask in one line if not stated):
- (a) Flashcard deck — extract atomic Q→A pairs covering the page's key claims. One fact per card. Save as a wiki companion page
references/<slug>-flashcards.md(same shape as the jumpstart deck), register it inreferences/index.md, and append a line toreferences/log.md. - (b) Interactive quiz — ask one question at a time in chat, wait for Gera's answer, grade it (correct / close / off, with the right answer), track a running score, and re-ask missed ones at the end. ~8–12 questions unless he says otherwise.
- (c) Self-quiz artifact — render an HTML self-test to
artifacts/study/<today>-<slug>.html(questions with reveal-on-click answers), perreferences/html-as-llm-output.md. Use when he wants something to drill later, away from chat.
- (a) Flashcard deck — extract atomic Q→A pairs covering the page's key claims. One fact per card. Save as a wiki companion page
- English mode: pull useful vocabulary, idioms, and phrasing — ideally from real content he's working with (a wiki page, an email he's drafting). Drill meaning + usage, and flag any phrasing he got wrong with a natural correction. Keep it encouraging.
Output
- Flashcards:
references/<slug>-flashcards.md(wiki companion page) + index + log entry. - Interactive quiz: runs in chat, ends with a score + which cards to review.
- Self-quiz artifact:
artifacts/study/<today>-<slug>.html.
Notes / Guardrails
- Atomic cards — one fact per card. Don't bundle three claims into one question.
- Test recall, don't re-teach. Questions should force retrieval. Avoid yes/no and giveaway phrasing.
- Ground every card in the source. Don't invent facts the page doesn't support; if the page is thin, say so rather than padding.
- Flashcard decks are real wiki pages — follow the wiki protocol (index update + log line) when saving one. Interactive quizzes and artifacts don't touch the wiki.
- For English, be a warm coach, not a grammar police — correct naturally, keep his confidence up.
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.

