learn

Name: learn
Author: tw93

6.6kstars384forks

How to install learn?

tw93/waza/learn

$npx -y skills add tw93/Waza --skill learn

Installs into the current project.

Summary

Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask in any language to research, study, deep-dive, compile sources, synthesize unfamiliar material, or turn a source bundle into a coh

Files · 1

View on GitHub

SKILL.md

1	# Learn: From Raw Materials to Published Output
2
3	Prefix your first line with 🥷 inline, not as its own paragraph.
4
5	Update check (non-blocking). Once per conversation, run `bash <skill-base-dir>/scripts/check-update.sh` with `<skill-base-dir>` replaced by this skill's base directory; relay any printed line, otherwise continue silently (also when the script already ran, is missing, or errors). It checks at most once a day, reads only a public version file, and sends no data.
6
7	Support the user's thinking; do not replace it.
8
9	## Outcome Contract
10
11	- Outcome: unfamiliar material becomes a reliable mental model, reference, article, or notes set the user can use.
12	- Done when: primary sources are collected or supplied, contradictions are handled explicitly, and the final structure teaches the topic without hiding uncertainty.
13	- Evidence: source URLs or files, fetched content, notes from digestion, outline decisions, and self-review against the requested output.
14	- Output: research notes, outline, publish-ready draft, or canonical reference, matching the chosen mode.
15
16	Boundary: single URL that only needs fetching belongs in `/read`. A single URL that needs summary or analysis can use `/read` as the fetch step, but the final answer should satisfy the user's requested summary or analysis. `/learn` is for multi-source research that produces a new structured output.
17
18	## Pre-check
19
20	Check whether `/read` and `/write` skills are installed (look for their SKILL.md in the skills directories). Warn if missing, do not block:
21	- `/read` missing -- Phase 1 fetch falls back to native `WebFetch` / `curl`; coverage on paywalled, JS-heavy, and Chinese-platform pages degrades.
22	- `/write` missing -- Phase 5 AI-pattern stripping falls back to manual scan. Phases 1-4 are unaffected.
23
24	## Choose Mode
25
26	Ask the user to confirm the mode, using the environment's native question or approval mechanism if it has one:
27
28	\| Mode \| Goal \| Entry \| Exit \|
29	\|------\|------\|-------\|------\|
30	\| Deep Research \| Understand a domain well enough to write about it \| Phase 1 \| Phase 6: publish-ready draft \|
31	\| Quick Reference \| Build a working mental model fast, no article planned \| Phase 2 \| Phase 2: notes only \|
32	\| Write to Learn \| Already have materials, force understanding through writing \| Phase 3 \| Phase 6: publish-ready draft \|
33	\| Canonical Article \| One article that covers a topic so thoroughly readers need nothing else \| Phase 1 \| Phase 6: single authoritative reference \|
34
35	If unsure, suggest Quick Reference.
36
37	## Canonical Article Mode
38
39	Activate when: "一篇就够", "一站式参考", "整理成长文", "目的是大家只需要看这篇就好了", or the user wants a single authoritative reference on a topic.
40
41	Goal: after reading the article, no one should need to search for anything else on this topic.
42
43	Additional requirements on top of standard Deep Research:
44	- Every major sub-topic must have its own section; nothing left as a footnote
45	- Include worked examples, not just principles
46	- Cover common mistakes and how to avoid them
47	- Add a "Further Reading" section with the 3-5 sources that go deepest; flag which ones are the best starting points
48	- Phase 6 self-review must confirm: "Could a reader implement/understand this from this article alone?"
49
50	## Phase 1: Collect
51
52	Gather primary sources only: papers that introduced key ideas, official lab/product blogs, posts from builders, canonical "build it from scratch" repositories. Not summaries. Not explainers.
53
54	Three ordered steps per source -- no shortcuts, no merging:
55
56	1. Discover -- use an installed search plugin (e.g., PipeLLM) to map the landscape, then deep-search the 2-3 most promising sub-topics. No plugin: use the environment's native web search. Output is a URL list; do not fetch content here.
57	2. Fetch -- every URL goes through `/read` when available. `/read` owns the proxy cascade, paywall detection, and platform routing (WeChat, Feishu, PDF, GitHub). Native fetch tools and raw `curl` silently fail on JS-heavy or paywalled sites and skip all of that. If `/read` is missing (Pre-check warned), fall back to native fetch and accept reduced coverage.
58	3. File -- tell `/read` the research project's source directory when one exists. If no directory was specified, let `/read` use a per-session temp directory and return the saved path. Move or index saved files into sub-topic directories after fetch returns. Move, don't refetch.
59
60	Target: 5-10 s

People who liked this also viewed

6 picks

Type

learn

6.6kstars384forks

View on GitHub

How to install learn?

tw93/waza/learn

$npx -y skills add tw93/Waza --skill learn

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Learn: From Raw Materials to Published Output
2
3	Prefix your first line with 🥷 inline, not as its own paragraph.
4
5	Update check (non-blocking). Once per conversation, run `bash <skill-base-dir>/scripts/check-update.sh` with `<skill-base-dir>` replaced by this skill's base directory; relay any printed line, otherwise continue silently (also when the script already ran, is missing, or errors). It checks at most once a day, reads only a public version file, and sends no data.
6
7	Support the user's thinking; do not replace it.
8
9	## Outcome Contract
10
11	- Outcome: unfamiliar material becomes a reliable mental model, reference, article, or notes set the user can use.
12	- Done when: primary sources are collected or supplied, contradictions are handled explicitly, and the final structure teaches the topic without hiding uncertainty.
13	- Evidence: source URLs or files, fetched content, notes from digestion, outline decisions, and self-review against the requested output.
14	- Output: research notes, outline, publish-ready draft, or canonical reference, matching the chosen mode.
15
16	Boundary: single URL that only needs fetching belongs in `/read`. A single URL that needs summary or analysis can use `/read` as the fetch step, but the final answer should satisfy the user's requested summary or analysis. `/learn` is for multi-source research that produces a new structured output.
17
18	## Pre-check
19
20	Check whether `/read` and `/write` skills are installed (look for their SKILL.md in the skills directories). Warn if missing, do not block:
21	- `/read` missing -- Phase 1 fetch falls back to native `WebFetch` / `curl`; coverage on paywalled, JS-heavy, and Chinese-platform pages degrades.
22	- `/write` missing -- Phase 5 AI-pattern stripping falls back to manual scan. Phases 1-4 are unaffected.
23
24	## Choose Mode
25
26	Ask the user to confirm the mode, using the environment's native question or approval mechanism if it has one:
27
28	\| Mode \| Goal \| Entry \| Exit \|
29	\|------\|------\|-------\|------\|
30	\| Deep Research \| Understand a domain well enough to write about it \| Phase 1 \| Phase 6: publish-ready draft \|
31	\| Quick Reference \| Build a working mental model fast, no article planned \| Phase 2 \| Phase 2: notes only \|
32	\| Write to Learn \| Already have materials, force understanding through writing \| Phase 3 \| Phase 6: publish-ready draft \|
33	\| Canonical Article \| One article that covers a topic so thoroughly readers need nothing else \| Phase 1 \| Phase 6: single authoritative reference \|
34
35	If unsure, suggest Quick Reference.
36
37	## Canonical Article Mode
38
39	Activate when: "一篇就够", "一站式参考", "整理成长文", "目的是大家只需要看这篇就好了", or the user wants a single authoritative reference on a topic.
40
41	Goal: after reading the article, no one should need to search for anything else on this topic.
42
43	Additional requirements on top of standard Deep Research:
44	- Every major sub-topic must have its own section; nothing left as a footnote
45	- Include worked examples, not just principles
46	- Cover common mistakes and how to avoid them
47	- Add a "Further Reading" section with the 3-5 sources that go deepest; flag which ones are the best starting points
48	- Phase 6 self-review must confirm: "Could a reader implement/understand this from this article alone?"
49
50	## Phase 1: Collect
51
52	Gather primary sources only: papers that introduced key ideas, official lab/product blogs, posts from builders, canonical "build it from scratch" repositories. Not summaries. Not explainers.
53
54	Three ordered steps per source -- no shortcuts, no merging:
55
56	1. Discover -- use an installed search plugin (e.g., PipeLLM) to map the landscape, then deep-search the 2-3 most promising sub-topics. No plugin: use the environment's native web search. Output is a URL list; do not fetch content here.
57	2. Fetch -- every URL goes through `/read` when available. `/read` owns the proxy cascade, paywall detection, and platform routing (WeChat, Feishu, PDF, GitHub). Native fetch tools and raw `curl` silently fail on JS-heavy or paywalled sites and skip all of that. If `/read` is missing (Pre-check warned), fall back to native fetch and accept reduced coverage.
58	3. File -- tell `/read` the research project's source directory when one exists. If no directory was specified, let `/read` use a per-session temp directory and return the saved path. Move or index saved files into sub-topic directories after fetch returns. Move, don't refetch.
59
60	Target: 5-10 s

People who liked this also viewed

6 picks

Type