skills/analogy-weight-check/SKILL.md
--- name: analogy-weight-check description: For every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reu
npx skillsauth add lyndonkl/claude skills/analogy-weight-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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).testing
--- name: advisory-edit description: A strict advisory-only editing discipline for a writer who dictates ("speaks out") essays and wants help WITHOUT having their voice changed. The editor directs structure, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply" / "make that change" / "rewrite this." Produces a line-referenced, suggestion-only critique where every item is marked the writer's call. Four passes: structural, l
testing
Provides the house style for analyst-grade strategist writing — third-person register with sparing first-person, no em dashes, no "not X, not Y, not Z" negation cascades, numbered footnote citations rather than inline source parentheticals, specific opinion-signaling phrases, and topic-forward paragraph structure modeled on voice patterns observed in Damodaran's Musings on Markets and Thompson's Stratechery. Use when consolidating working notes into a finished long-form strategist or analyst report that must read as written by a senior human analyst rather than an AI assistant.
testing
Renders a markdown report to a PDF using pandoc with xelatex (11pt serif body, 1-inch margins, numbered footnotes, formal heading hierarchy). Requires a one-time install of pandoc and a LaTeX engine on the user's machine — basictex on macOS or texlive-xetex on Linux. Does not attempt automatic install. Fails loudly with the exact install commands if pandoc or xelatex is missing on the user's PATH. Use when producing a finished strategist or analyst report PDF from a polished markdown source.
testing
Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.