Formula Derivation Package
Turn scattered research equations into an honest, coherent derivation package — or a blocker report
- What
- Turn scattered research equations into an honest, coherent derivation package — or a blocker report
- Cost
- Free
- Needs
- research notes to work from — a problem, a goal and your current formulas or draft; an agent able to read/write/edit files in the working directory
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — structures research formula derivation into exactly one output: a coherent derivation package for the original target, a reframed package with corrected object/assumptions/scope, or a blocker report explaining why the current notes cannot yet support a coherent derivation. It extracts and normalizes the target phenomenon, the intended role of the derivation (exact identity, proposition, approximation, mechanism interpretation), explicit assumptions, notation and definitions — and if anything is ambiguous, it states its exact interpretation before deriving anything. Honesty over polish is the design principle: no fake polished theorem stories. By @wanshuiyin, listed here with credit to its creator. Honest caveats: output quality depends entirely on your input notes — feed it your problem, goal and current formulas; it may legitimately return a blocker report instead of a derivation, and that is the feature, not a failure; it reads and writes files in the working directory. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Formula Derivation Package is a free Muse skill that turns scattered research equations into an honest, coherent derivation package, or a blocker report. It produces exactly one output: a coherent package for the original target, a reframed package with corrected object, assumptions and scope, or a blocker report explaining why the current notes cannot yet support a coherent derivation.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 26b95cfStep 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: research notes to work from — a problem, a goal and your current formulas or draft; an agent able to read/write/edit files in the working directory Install "Formula Derivation Package" for me. Give my agent the formula-derivation methodology — input extraction and normalization, ambiguity declared up front, exactly one of three outputs (coherent package, reframed package, blocker report) Repository: https://raw.githubusercontent.com/wanshuiyin/auto-claude-code-research-in-sleep/26b95cfa0d8747078e9e43b42e20952709e561b8/skills/formula-derivation/SKILL.md Pinned version: install the code at commit 26b95cfa0d8747078e9e43b42e20952709e561b8 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 for the wanshuiyin-auto-claude-code-research-in-sleep-formula-derivation skill from the repository into a temporary folder 2. Safety check: review the SKILL.md 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 into the agent's skills directory, in a folder named "wanshuiyin-auto-claude-code-research-in-sleep-formula-derivation". 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. point my agent at my notes directory with the problem, goal and current formulas). 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
- 26b95cf · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- 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.