lyndonkl/skills/claim-extractor
skills/claim-extractor/SKILL.md
--- name: claim-extractor description: Extracts atomic technical claims from a substacker essay draft, converting flowing intuition-first prose into a numbered list where each item is a statement that could in principle be verified or falsified. Skips non-technical sections (personal anecdote, motivation, call-to-action). Use when the Technical Reviewer starts a per-draft review. Trigger keywords: extract claims, atomic claims, technical claim list, fact-check prep. --- # Claim Extractor ## Wo
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/claim-extractorInstall 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, 10:09 AM133.7s1 file scanned
SKILL.md
- name:
- claim-extractor
- description:
- Extracts atomic technical claims from a substacker essay draft, converting flowing intuition-first prose into a numbered list where each item is a statement that could in principle be verified or falsified. Skips non-technical sections (personal anecdote, motivation, call-to-action). Use when the Technical Reviewer starts a per-draft review. Trigger keywords: extract claims, atomic claims, technical claim list, fact-check prep.
Claim Extractor
Workflow
Per draft:
- [ ] Step 1: Segment draft by heading / section
- [ ] Step 2: Within each section, split by sentence
- [ ] Step 3: Flag sentences containing technical claims:
- Math symbols / formulas
- Named systems, components, algorithms
- Quantitative assertions
- Universal quantifiers ("always", "never", "all models")
- Named papers / results
- [ ] Step 4: Coalesce adjacent claim sentences that argue the same thing into one claim
- [ ] Step 5: Output numbered list: {id, excerpt (≤200 chars), location}
Non-claim content (skip)
- Personal anecdotes without technical assertion
- Motivation / framing
- Calls to action
- Closing maxims (unless they assert a technical fact)
Worked example
Draft paragraph:
Attention is O(n²). This is why context windows are expensive. Each token looks at every other token, and the matrix is n-by-n.
Extraction:
- "Attention is O(n²) in compute and memory in a naive implementation." [§2 ¶1]
- "Context windows are expensive because of attention's complexity." [§2 ¶1]
- "Each token attends to every other token via an n-by-n matrix." [§2 ¶1]
Guardrails
- Never paraphrase aggressively. Preserve the writer's hedges.
- Excerpts ≤200 chars verbatim.
- Coalesce adjacent claims only if they argue the same thing.
- Respect
[contrarian]annotations — still extract the claim, but flag it forclassify-claimto treat specially. - Don't extract claims from code blocks or quoted text.
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