From thinking-frameworks-skills
Verifies each analogy in a substacker draft carries mechanical weight (explains vs. decorates) and checks analogy-catalog.md for novelty and domain fit.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:analogy-weight-checkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- [Mechanical-weight test](#mechanical-weight-test)
Related skills: Called by Editor in structural pass (since analogy decisions affect paragraph structure). Reads shared-context/analogy-catalog.md for novelty.
The test: if you remove the analogy, does the explanation still work?
A decorative analogy is not a tier-1 issue by itself — writers may legitimately use decorative language occasionally. But:
For each analogy in the draft:
- [ ] Step 1: Identify the analogy (source + target)
- [ ] Step 2: Mechanical-weight test — simulate removing it; does the explanation degrade?
- [ ] Step 3: Check analogy-catalog.md for reuse
- [ ] Step 4: Check source domain against voice-profile priority (biology > organizational > sports; not physics/military)
- [ ] Step 5: Emit verdict per analogy: carries-weight | decorative | reused-from-catalog | wrong-domain
Draft excerpt:
A KV cache is like a library's card catalog — it lets you find things. Under the hood, it stores key and value projections for each past token, so when a new token arrives, attention can index back without recomputing.
Attention is also like a room full of people trying to hear each other.
Analogies:
"KV cache like a library card catalog"
"Attention is also like a room full of people trying to hear each other"
Overall: 2 decorative analogies in one excerpt. Cluster signal — flag as tier-2, note pattern.
update-analogy-catalog).npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsCross-references proposed analogies against a shared catalog to flag reuse, classifying each as new, reused, or adjacent. Prevents stale analogies before presenting framings.
Scan Every drafts for editorial-review failures: clarity gaps, argument problems, mechanics red flags, and AI tells. Reports line-level diagnoses and suggested fixes.
Lints and critiques prose in markdown, HTML, or plain text using classical style guides. Audits for AI tells, polishes voice, tightens clarity, and captures writing style into a project profile.