lyndonkl/skills/flag-boundary-break
skills/flag-boundary-break/SKILL.md
--- name: flag-boundary-break description: For each simplified-boundary claim, drafts a one-paragraph suggestion for how to acknowledge the boundary inside the post — usually a single sentence or "but" clause — so the break becomes a teaching moment rather than hidden fragility. Runs for exactly the claims classified as simplified-boundary. Skip for all other classifications. Use after cross-reference-claim. Trigger keywords: boundary break, fold break into post, feature not flaw, simplified-bou
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/flag-boundary-breakInstall 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, 10:13 AM145.5s1 file scanned
SKILL.md
- name:
- flag-boundary-break
- description:
- For each simplified-boundary claim, drafts a one-paragraph suggestion for how to acknowledge the boundary inside the post — usually a single sentence or "but" clause — so the break becomes a teaching moment rather than hidden fragility. Runs for exactly the claims classified as simplified-boundary. Skip for all other classifications. Use after cross-reference-claim. Trigger keywords: boundary break, fold break into post, feature not flaw, simplified-boundary.
Flag Boundary Break
Workflow
Per simplified-boundary claim:
- [ ] Step 1: Identify the intuition the writer was using (analogy, metaphor, concrete picture)
- [ ] Step 2: Identify precisely where the intuition breaks using primary source
- [ ] Step 3: Draft a one-sentence suggestion that names the break as a feature
- [ ] Step 4: Optionally suggest a follow-up post if break is too rich for a sentence
- [ ] Step 5: Return {intuition, break_point, fold_suggestion, optional_follow_up}
Worked example
Claim: "Attention is O(n²) in memory."
Classification: simplified-boundary.
Primary source: Dao et al. 2022 — FlashAttention, arXiv:2205.14135. "FlashAttention uses O(N) memory rather than the O(N²) of standard attention."
Fold suggestion:
"The O(n²) figure is the naive memory cost — modern production attention (FlashAttention, Dao et al. 2022) is actually O(n) in HBM by never materializing the full attention matrix. The quadratic view is still the right intuition for 'why context windows are expensive' circa 2020, but the actual frontier now is 'attention is memory-bandwidth-bound,' which is a richer story — probably a follow-up post."
Optional follow-up: "FlashAttention as memory-bandwidth reframe."
Guardrails
- Fold suggestion is a nudge, not a rewrite. Never propose more than one sentence of insertion.
- Never fold-suggest for
wrongclaims — those get fixed, not folded. - Always name the break specifically. "The analogy breaks at scale" is vague; "the drawer metaphor implies physical contiguity but the cache is logically indexed" is specific.
- Optional follow-up is optional. Offer when the break is rich enough for its own post.
- Writer's voice preserved — fold suggestions read like the writer could say them.
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