lyndonkl/skills/extract-thread-spine
skills/extract-thread-spine/SKILL.md
--- name: extract-thread-spine description: Extracts the 5-7 point argument backbone of a published substacker essay into a structured _spine.json working artifact that downstream platform-rewrite skills consume. Pulls verbatim sentences where possible (not paraphrases). Tags each point with evidence anchor (paper, anecdote, formula, analogy), essay section, and translatability score. Use at the start of a Distribution Translator run. Trigger keywords: spine, backbone, extract claims, thread spi
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/extract-thread-spineInstall 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, 10:12 AM187.5s1 file scanned
SKILL.md
- name:
- extract-thread-spine
- description:
- Extracts the 5-7 point argument backbone of a published substacker essay into a structured _spine.json working artifact that downstream platform-rewrite skills consume. Pulls verbatim sentences where possible (not paraphrases). Tags each point with evidence anchor (paper, anecdote, formula, analogy), essay section, and translatability score. Use at the start of a Distribution Translator run. Trigger keywords: spine, backbone, extract claims, thread spine, argument skeleton.
Extract Thread Spine
Workflow
For a published essay P:
- [ ] Step 1: Read P end-to-end
- [ ] Step 2: Identify thesis (usually opening confession + first pivot sentence)
- [ ] Step 3: Extract 5-7 load-bearing claims IN ORDER
- [ ] Step 4: Tag each claim: evidence_type (confession / claim / paper / analogy / formula / maxim), essay_section, translatability (1-5)
- [ ] Step 5: Extract closing_maxim verbatim
- [ ] Step 6: Extract 3 candidate hook sentences (from the essay itself, not paraphrases)
- [ ] Step 7: Write _spine.json
Output schema
{
"thesis": "{one sentence, verbatim or lightly-compressed from the essay}",
"claims": [
{"text": "verbatim from essay", "evidence_type": "confession|claim|paper|analogy|formula|maxim", "essay_section": "opener|pivot|body|closer", "translatability": 1-5}
],
"closing_maxim": "{verbatim from essay, usually bolded in the post}",
"best_hook_candidates": [
"{verbatim sentence 1}",
"{verbatim sentence 2}",
"{verbatim sentence 3}"
]
}
Translatability: 5 = works on any platform; 1 = needs the full essay's setup to make sense.
Worked example
Input (essay The Execution Gap, abridged):
I have been meaning to open a Kalshi account for months.
Not casually meaning to...
This is not a story about prediction markets. It is a story about the distance between learning about something and actually doing it.
[methodology, Brier arithmetic...]
I have not tried this. Not once.
Output _spine.json:
{
"thesis": "Learning about prediction markets is not the same as betting on them. The gap between knowing and doing is the real subject.",
"claims": [
{"text": "I have been meaning to open a Kalshi account for months.", "evidence_type": "confession", "essay_section": "opener", "translatability": 5},
{"text": "This is not a story about prediction markets. It is a story about the distance between learning about something and actually doing it.", "evidence_type": "claim", "essay_section": "pivot", "translatability": 5},
{"text": "Say you predict a team at 80% confidence. If they win, your Brier score is (0.80 - 1)^2 = 0.04. But if they lose, it's (0.80 - 0)^2 = 0.64. That's catastrophic.", "evidence_type": "formula", "essay_section": "body", "translatability": 3},
{"text": "I have not tried this. Not once.", "evidence_type": "maxim", "essay_section": "closer", "translatability": 5}
],
"closing_maxim": "I have not tried this. Not once.",
"best_hook_candidates": [
"I have been meaning to open a Kalshi account for months.",
"I am one of those people who substitutes learning for doing.",
"This is not a story about prediction markets. It is a story about the distance between learning about something and actually doing it."
]
}
Guardrails
- Pull verbatim sentences. Paraphrasing is the slop door — the writer's voice is in the exact phrasing.
- Never invent a claim not in the essay.
- Exactly 5–7 claims. Fewer under-represents; more overwhelms downstream rewrites.
- Preserve paper attributions intact at this stage. X skill decides per-tweet trade-offs later.
closing_maximis verbatim — it's what the writer will want bolded in the Substack Note.- Translatability is the writer's dial. Use it; don't inflate everything to 5.
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