Learn: six-phase research workflow (deep research to publish-ready output)
Turn raw materials into a reliable mental model, reference notes or a publish-ready article — collect, digest, outline, fill, refine, self-review
- What
- Turn raw materials into a reliable mental model, reference notes or a publish-ready article — collect, digest, outline, fill, refine, self-review
- Cost
- Free
- Needs
- nothing — the skill is a research methodology; pairs with the waza plugin's /read and /write slash commands when installed (works standalone with reduced coverage)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @tw93's research operating system for agents: a six-phase workflow that turns raw materials into a reliable mental model, reference notes, or a publish-ready article. Phase 1 collects primary sources only (papers, official blogs, canonical repos); Phase 2 digests them into the mental model (cutting anything that fails its three key-claim tests); Phase 3 writes a source-backed outline; Phase 4 fills it in section by section; Phase 5 refines and strips AI patterns; Phase 6 self-reviews twice before the user publishes. Four modes adapt the depth: Deep Research, Quick Reference, Write to Learn, and Canonical Article (one article so thorough readers need nothing else). By @tw93, listed here with credit to its creator. Honest caveats: the trigger phrases in the frontmatter include Chinese (as well as English research terms); designed to pair with the waza plugin's `/read` and `/write` slash commands — without `/read` it warns once and falls back to native fetch with reduced coverage on paywalled, JS-heavy and Chinese-platform pages; publishing requires explicit user confirmation and stops at publish readiness; MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Learn is a free Muse skill that runs a six-phase research workflow, reference notes or a publish-ready article. Phase one collects primary sources only; phase two digests them into the mental model; phase three writes a source-backed outline; phase four fills it in section by section; and phase five refines and strips AI patterns.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 20b26d9Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: nothing — the skill is a research methodology; pairs with the waza plugin's /read and /write slash commands when installed (works standalone with reduced coverage) Install "Learn: six-phase research workflow" for me. Give my agent @tw93's learn workflow: a six-phase research method (1 collect primary sources, 2 digest into a mental model, 3 source-backed outline, 4 fill in section by section, 5 refine and strip AI patterns, 6 self-review twice) with four modes (Deep Research, Quick Reference, Write to Learn, Canonical Article). Never publish, upload or distribute anything without my explicit request. Repository: https://raw.githubusercontent.com/tw93/waza/20b26d9352413db5e000639c40199bf9f8ccde90/plugins/waza/skills/learn/SKILL.md Pinned version: install the code at commit 20b26d9352413db5e000639c40199bf9f8ccde90 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "learn". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing — it is a methodology; optionally install the waza plugin's /read and /write slash commands for full coverage). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 20b26d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.