Complete prep for all three scored components of the California Bar Exam: the five written ESSAYS (13 subjects — Business Associations, Civil Procedure, Community Property, Constitutional Law, Contracts, Criminal Law & Procedure, Evidence, Professional Responsibility, Real Property, Remedies, Torts, Trusts, Wills & Succession), the PERFORMANCE TEST, and the multiple-choice MBE (7 subjects). Trigger whenever someone is studying for the California bar (or the MBE) and says things like: "give me the rule for [issue]", "big issues in [subject]", "drill/quiz me on [topic]", "MBE questions on [subject]", "teach me [doctrine]", "build an attack outline", "grade my essay", "memorizable paragraph for [issue]", "performance test approach", or "make a study plan" — or names any tested essay/MBE subject in a study, memorization, drilling, or practice-question context. Also trigger when a student uploads a practice essay, PT, or question set to be graded or turned into rule blocks. When in doubt during bar prep, trigger.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
End-to-end prep for the written and multiple-choice halves of the California Bar Exam, weighted roughly 50/50: five one-hour essays (any of 13 subjects), one 90-minute Performance Test, and the 200-question MBE (7 subjects). This skill centralizes the black-letter rules, pre-written memorizable IRAC paragraphs, MBE practice, and exam-day strategy a student needs.
Core philosophy: memorize a bank of issue paragraphs in advance, then on exam day spot the issue and transcribe the paragraph, filling the application sentence with the facts in front of you; for the MBE, drill original questions until the rules and their traps are automatic. The banks make both fast.
| Component | What it is | Where the material lives |
|---|---|---|
| Essays | 5 essays drawn from 13 subjects | references/essays/ (attack outlines + IRAC rule blocks) + references/standard-paragraphs/ (memorizable paragraphs) |
| Performance Test | 1 closed-universe lawyering task (90 min) | references/pt/performance-test.md |
| MBE | 200 MCQs across 7 subjects | references/mbe/ (method + 7 subject files) |
Exam strategy for all components: references/exam/exam-day.md (timing, IRAC
discipline, issue-spotting, triage).
Business Associations · Civil Procedure · Community Property · Constitutional Law · Contracts · Criminal Law & Procedure · Evidence · Professional Responsibility · Real Property · Remedies · Torts · Trusts · Wills & Succession.
Each subject has two files: references/essays/<subject>.md (a condensed attack
outline plus full IRAC rule blocks) and
references/standard-paragraphs/<subject>.md (flowing memorize-and-transcribe
paragraphs with an Apply: frame for each issue). The standard-paragraphs file is
the most complete memorization set for a subject — it may include a few issues
not broken out in the attack-outline file — so prefer it when a student is memorizing,
and use the attack outline for issue-spotting structure.
For deeper calibration, the State Bar of California publicly releases past essay questions, Performance Tests, and selected answers on calbar.ca.gov — point students there for authentic practice material, and build issue maps from those released questions on the fly when grading or generating practice.
Civil Procedure · Constitutional Law · Contracts · Criminal Law & Procedure ·
Evidence · Real Property · Torts. See references/mbe/mbe-method.md first, then
the per-subject files for high-yield rules, distractor traps, and the all-important
MBE-vs-California splits.
Figure out which component (essay, PT, or MBE) and which mode the student wants from how they ask, then act. Students chain these constantly.
"Give me the rule for [X]" / "what are the big issues in [subject]." Open the relevant essay or MBE file and surface the matching attack-outline slice and IRAC rule block(s) or paragraph(s). If only a subject is named, lead with the major issues that anchor most questions, then offer the minor ones.
"Drill me", "quiz me on the rules", "teach me [doctrine]." Run active recall: prompt with an issue label → student states the rule → reveal the stored rule and diff what was missed. Track misses and re-test those first. One issue at a time; keep it brisk.
"Quiz me with MBE questions", "give me a timed set." Follow references/mbe/mbe-method.md:
generate original NCBE-style questions (never reproduce real exam questions),
reveal the best answer with a full explanation of why it's right and why each
distractor is wrong, and flag any MBE-vs-California divergence.
"Grade my essay/PT answer" or "mark my outline." For full answers: build the question's issue map (every issue a strong answer must raise, majors first) from the fact pattern and the subject's attack outline, then mark against it — issue spotting, IRAC integrity, rule accuracy, whether the answer got the hard structural move the question turns on, and missed CA divergences. Give an estimated 40–100 band (CalBar's essay scale) with the 2–3 highest-leverage fixes. For outlines (no time to write it out), mark spotting + sequencing + rule-cue accuracy only. Missed majors = the biggest leak (flag 🔴). Always state this is self-study calibration, not an official score.
"Build an attack outline / memorizable paragraphs for [topic]", "write me a practice
essay question", or a student uploads their own outline or question set. To author new
essay questions or model outlines: pick 4–7 issues from the subject's attack outline
(majors anchoring, one crossover), weave a fact pattern that raises each one, plant
ambiguities that cut both ways and at least one CA-divergence trigger, and label output
original practice question in CalBar style. For rule content,
produce new material in the existing file format (major issue first, then minor), in
original wording. Also handles study-plan requests — build a week-by-week plan across
the three components using references/exam/exam-day.md.
When the user brings released CalBar questions, selected answers, or their own scored essays into a session, use them freely within the session — build issue maps, anchor grading, diff the student's answer against what scored well. Do not reproduce vendor prose or graded student essays in outputs; distill them into original issue maps and analysis instead.
Throughout, 🔴 flags mark where California law departs from the majority/MBE rule — CEC vs FRE, CA community property, the CA Rules of Professional Conduct, pure comparative negligence, CA civil procedure, CA criminal statutes. On the essays the CA rule usually controls; on the MBE the majority/federal rule controls. The MBE subject files keep these two answers explicitly separate so students don't cross them up.
> ⚠️ VERIFY involve recently amended or unsettled law (e.g., CA
Rules of Professional Conduct, Evidence/Probate Code section numbers, felony-murder
reform, recent Supreme Court decisions). Confirm against current authority before
relying on them.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated. Does not decide real cases or claim that human judicial-recusal doctrine automatically applies.
中文简介正在准备中。当前显示原文说明。
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how the agent can be suspended, revoked, or escalated.
中文简介正在准备中。当前显示原文说明。
EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.
中文简介正在准备中。当前显示原文说明。
This skill builds a structured audit trail of an AI-assisted task: what the tool was asked to do, what materials it was given, what it produced, how the output was verified, and what was ultimately relied upon. It documents the workflow for supervision and later review without ruling on privilege or disclosure, so the record stays accurate rather than self-serving.
中文简介正在准备中。当前显示原文说明。
Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies required documentation and missing evidence, maps the use case to AI governance frameworks and applicable legal domains, and produces a preliminary or final governance review with scorecards, findings, owners, remediation actions, and follow-up questions.
中文简介正在准备中。当前显示原文说明。
Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable. Produces a multi-page website (default), a single-page interactive site, a Microsoft Word document, a PowerPoint deck, or a LaTeX/PDF. Use whenever a user has a stress-test result, ambiguity audit, or "where will this be litigated" scenarios and wants to publish, present, or share them. Triggers on "publish the audit," "make a report from this," "turn this into a website / deck / brief / Word doc," "make a Netlify site," "build slides of these ambiguities," "render the scenarios," "package this stress test," "produce a LaTeX version," and similar. Pairs with the ambiguity-stress-test skill (the underlying analysis) but works on any structured or semi-structured ambiguity analysis. Visual design is opinionated but the user can override colors, fonts, and brand label. Most formats need Python and a writable filesystem; single-file HTML works where the host has neither.
中文简介正在准备中。当前显示原文说明。