lyndonkl/skills/glossary-alignment-check
skills/glossary-alignment-check/SKILL.md
--- name: glossary-alignment-check description: For each technical term in a substacker draft's claims, checks shared-context/glossary.md for a writer-specific definition and compares to field-standard. Emits a note for terms where the two diverge (aligned / diverged-safe / diverged-risky). Feeds into classify-claim (which definition governs) and write-review-artifact's Glossary Alignment section. Use on every claim. Trigger keywords: glossary alignment, term definition, writer vs field, load-be
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/glossary-alignment-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 10:14 AM155.3s1 file scanned
SKILL.md
- name:
- glossary-alignment-check
- description:
- For each technical term in a substacker draft's claims, checks shared-context/glossary.md for a writer-specific definition and compares to field-standard. Emits a note for terms where the two diverge (aligned / diverged-safe / diverged-risky). Feeds into classify-claim (which definition governs) and write-review-artifact's Glossary Alignment section. Use on every claim. Trigger keywords: glossary alignment, term definition, writer vs field, load-bearing term.
Glossary Alignment Check
Workflow
Per claim:
- [ ] Step 1: Tokenize claim for candidate terms (named concepts, TLAs, math)
- [ ] Step 2: Grep shared-context/glossary.md for each term
- [ ] Step 3: If found, pull writer's definition
- [ ] Step 4: Compare to field-standard (prior knowledge + optional WebSearch)
- [ ] Step 5: Emit: aligned | diverged-safe | diverged-risky
Three outcomes
- aligned: writer's definition matches field-standard. No note.
- diverged-safe: definitions differ but the post's argument doesn't depend on the difference. Note but don't block.
- diverged-risky: definitions differ AND the post's argument hinges on which definition is in force. Tier-2 note for the writer.
Worked example
Term: "attention"
Writer's glossary: "the mechanism that lets tokens exchange information, including the residual bypass."
Field-standard: "the weighted sum softmax(QK^T/√d)V, excluding the residual."
Status: diverged-risky if post asserts "attention is O(n²)" — true under field definition, false-or-unclear under the writer's.
Output note: "Writer's glossary includes residual in 'attention'; field-standard excludes. Post's claim 'attention is O(n²) in memory' is true under field but misleading under writer's glossary. Consider disambiguating in-post or tightening the glossary."
Guardrails
- Never rewrite the glossary. Only flag.
- Never mark
alignedwithout actually checking the glossary file this run. - If glossary is missing or empty, emit
no-glossaryand treat field definition as governing. - When disagreement is strictly semantic (not functional), prefer
diverged-safeoverdiverged-risky— err toward non-blocking. - Diverged-risky notes appear in the Glossary Alignment section of the review artifact; don't bury in claim table.
Related Skills
lyndonkl/skills/advisory-edit
testing
VerifiedTrustedCommunity
--- 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
112SKILL.mdUpdated Jun 3, 2026
lyndonkl/strategist-voice
testing
VerifiedTrustedCommunity
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.
98SKILL.mdUpdated May 17, 2026
lyndonkl/markdown-to-pdf
testing
VerifiedTrustedCommunity
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.
98SKILL.mdUpdated May 17, 2026
lyndonkl/worked-example-walkthrough
testing
VerifiedTrustedCommunity
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.
94SKILL.mdUpdated May 10, 2026