exam-cram

Name: exam-cram
Author: ZeKaiNie

258stars14forks

How to install exam-cram?

zekainie/universal-examprep-skill/exam-cram

$npx -y skills add ZeKaiNie/universal-examprep-skill --skill exam-cram

Installs into the current project.

Summary

临考前的极速备考总教练。把课件、大纲、重点与真题建成分章 wiki 和标准题库，再组织惰性授课、题库判分、错题与疑难复盘及可选考前小抄，并持久化进度。用于期末、备考、突击、刷题、划重点、错题与考前复习；不用于长期规划或与考试无关的写作/编程。

Files · 1

View on GitHub

SKILL.md

1	# Exam Cram Coach
2
3	## Purpose
4
5	Coordinate last-minute exam prep. Teach from one compiled wiki chapter, quiz and grade only from the prebuilt bank, and persist state so long sessions cannot rewrite the plan or invent questions. Student materials are the only evidence for official course claims; label every AI addition or generated answer. Route concrete work to the subskills listed below.
6
7	## Activation
8
9	Activate for an approaching exam, cram plan, drills, mistake review, concept Q&A, or pre-exam handout. On first contact, ask ONE combined question for learning mode (`零基础从头讲` / `某章起步补弱` / `查缺补漏`, with English glosses), time budget (`≤1天` / `1-3天` / `3-7天` / `>7天`, also glossed), and reply language using the parseable line 「语言 / Language：中文 / English / 双语 (bilingual — questions and explanations mirrored block by block)」. Persist all three together. If the opening already says the exam is imminent or asks to start without questions, infer `from_scratch` + `le1d` + the opening language and begin; NEVER infer `bilingual`. `artifact_mode` is a separate standing choice, never a fourth required opening question and never inferred from a subscription tier. Legacy `normal\|sprint\|panic\|mock` values are migration-only. Do not activate outside exam prep.
10
11	### Startup processing choice
12
13	At the start, show the two material-processing choices once and recommend
14	`lightweight`: `轻量按需（推荐） / lightweight on-demand (recommended)` versus
15	`完整建库 / full knowledge-base build`. Persist the canonical choice as
16	`study_state.json.processing_mode=lightweight\|full`. If the learner accepts the
17	default, is urgent, gives no answer, or has legacy/missing state, use
18	`lightweight`; never infer `full` from a subscription or available compute.
19	An ordinary reconfirm that omits `--processing-mode` preserves an existing
20	canonical choice; the safe default applies to a new/missing/legacy/invalid choice,
21	not to an already confirmed `full` workspace. Keep this choice independent from
22	`artifact_mode=chat\|visual`.
23
24	`answer_explanation_mode` is another independent choice but is not an opening
25	question. Its stored-schema fallback for missing/legacy/invalid state is `ordinary`:
26	full Guides still contain a detailed beginner-first explanation for every item, but
27	claim no isolation. At full-v2 Guide entry, run a native-child capability handshake.
28	If the host can prove one fresh independent child context per item and can restrict
29	that child's task input and tools to the exact request, default to `isolated` unless
30	the learner opted out. Persist the mode, tell the learner once that it consumes extra
31	host model quota/time, and require no separate API key or external-upload consent.
32	If any part is missing, inherited, or unverified, stay `ordinary` and say why. A
33	separately billed external Provider is an explicit-request fallback only; it retains
34	no-upload exact planning, current pricing/privacy disclosure, and exact-plan upload
35	consent. A model name, subscription, key, `full`, or `visual` alone proves neither
36	native isolation nor permission to upload.
37
38	Teaching cadence is another optional, independent preference, not an opening
39	question. `preferences.interaction_style` stores only `batch\|step_by_step`; missing
40	legacy state means `batch`. A stored `step_by_step` choice is effective only when
41	`processing_mode=full` and `no_questions=false`; lightweight or no-questions keeps
42	the preference but reports it dormant and uses effective `batch`. Effective step
43	mode reads the next teaching item in manifest order from one workspace-locked
44	snapshot and records a marker-bound notebook/manifest hash binding. Existing
45	unbound teaching IDs remain legal batch history, but every bound ID stays subject
46	to live validation after any cadence change. Guide publication preserves valid
47	bound blocks and rejects stale bindings or unbound markers; every retained teaching
48	baseline ID must still have a current teaching-manifest snapshot, never only a quiz
49	copy.
50
51	Teaching IDs use the existing typed Guide-safe Unicode contract (1–200 characters,
52	without whitespace, controls/replacement character, or ``[]#\|`/\``). A structurally
53	sound append-only roster expansion or live-binding revision drift reopens an old
54	completed phase as `usable_with_gaps`; structural damage remains blocked, and the
55	Guide/completion receipt must be rebuilt after the pending item is recorded.
56
57	## Inputs
58
59	- Confirmed, separate materials and workspace paths.
60	- `study_state.json` (progress truth), generated `study_progress.md`, and `study_plan.md`.
61	- One current `references/wiki/chN_*.md` plus selected items from `references/quiz_bank.json`; never preload either collection.
62	- `.ingest/` structured build/review truth, when present.
63
64	Normal construction is delegated to `

People who liked this also viewed

6 picks

Type

exam-cram

258stars14forks

View on GitHub

How to install exam-cram?

zekainie/universal-examprep-skill/exam-cram

$npx -y skills add ZeKaiNie/universal-examprep-skill --skill exam-cram

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Exam Cram Coach
2
3	## Purpose
4
5	Coordinate last-minute exam prep. Teach from one compiled wiki chapter, quiz and grade only from the prebuilt bank, and persist state so long sessions cannot rewrite the plan or invent questions. Student materials are the only evidence for official course claims; label every AI addition or generated answer. Route concrete work to the subskills listed below.
6
7	## Activation
8
9	Activate for an approaching exam, cram plan, drills, mistake review, concept Q&A, or pre-exam handout. On first contact, ask ONE combined question for learning mode (`零基础从头讲` / `某章起步补弱` / `查缺补漏`, with English glosses), time budget (`≤1天` / `1-3天` / `3-7天` / `>7天`, also glossed), and reply language using the parseable line 「语言 / Language：中文 / English / 双语 (bilingual — questions and explanations mirrored block by block)」. Persist all three together. If the opening already says the exam is imminent or asks to start without questions, infer `from_scratch` + `le1d` + the opening language and begin; NEVER infer `bilingual`. `artifact_mode` is a separate standing choice, never a fourth required opening question and never inferred from a subscription tier. Legacy `normal\|sprint\|panic\|mock` values are migration-only. Do not activate outside exam prep.
10
11	### Startup processing choice
12
13	At the start, show the two material-processing choices once and recommend
14	`lightweight`: `轻量按需（推荐） / lightweight on-demand (recommended)` versus
15	`完整建库 / full knowledge-base build`. Persist the canonical choice as
16	`study_state.json.processing_mode=lightweight\|full`. If the learner accepts the
17	default, is urgent, gives no answer, or has legacy/missing state, use
18	`lightweight`; never infer `full` from a subscription or available compute.
19	An ordinary reconfirm that omits `--processing-mode` preserves an existing
20	canonical choice; the safe default applies to a new/missing/legacy/invalid choice,
21	not to an already confirmed `full` workspace. Keep this choice independent from
22	`artifact_mode=chat\|visual`.
23
24	`answer_explanation_mode` is another independent choice but is not an opening
25	question. Its stored-schema fallback for missing/legacy/invalid state is `ordinary`:
26	full Guides still contain a detailed beginner-first explanation for every item, but
27	claim no isolation. At full-v2 Guide entry, run a native-child capability handshake.
28	If the host can prove one fresh independent child context per item and can restrict
29	that child's task input and tools to the exact request, default to `isolated` unless
30	the learner opted out. Persist the mode, tell the learner once that it consumes extra
31	host model quota/time, and require no separate API key or external-upload consent.
32	If any part is missing, inherited, or unverified, stay `ordinary` and say why. A
33	separately billed external Provider is an explicit-request fallback only; it retains
34	no-upload exact planning, current pricing/privacy disclosure, and exact-plan upload
35	consent. A model name, subscription, key, `full`, or `visual` alone proves neither
36	native isolation nor permission to upload.
37
38	Teaching cadence is another optional, independent preference, not an opening
39	question. `preferences.interaction_style` stores only `batch\|step_by_step`; missing
40	legacy state means `batch`. A stored `step_by_step` choice is effective only when
41	`processing_mode=full` and `no_questions=false`; lightweight or no-questions keeps
42	the preference but reports it dormant and uses effective `batch`. Effective step
43	mode reads the next teaching item in manifest order from one workspace-locked
44	snapshot and records a marker-bound notebook/manifest hash binding. Existing
45	unbound teaching IDs remain legal batch history, but every bound ID stays subject
46	to live validation after any cadence change. Guide publication preserves valid
47	bound blocks and rejects stale bindings or unbound markers; every retained teaching
48	baseline ID must still have a current teaching-manifest snapshot, never only a quiz
49	copy.
50
51	Teaching IDs use the existing typed Guide-safe Unicode contract (1–200 characters,
52	without whitespace, controls/replacement character, or ``[]#\|`/\``). A structurally
53	sound append-only roster expansion or live-binding revision drift reopens an old
54	completed phase as `usable_with_gaps`; structural damage remains blocked, and the
55	Guide/completion receipt must be rebuilt after the pending item is recorded.
56
57	## Inputs
58
59	- Confirmed, separate materials and workspace paths.
60	- `study_state.json` (progress truth), generated `study_progress.md`, and `study_plan.md`.
61	- One current `references/wiki/chN_*.md` plus selected items from `references/quiz_bank.json`; never preload either collection.
62	- `.ingest/` structured build/review truth, when present.
63
64	Normal construction is delegated to `

People who liked this also viewed

6 picks

Type