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/conf-theme-clustering
testing
VerifiedTrustedCommunity
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-schedule-optimization
development
VerifiedTrustedCommunity
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-program-extraction
development
VerifiedTrustedCommunity
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-preference-elicitation
development
VerifiedTrustedCommunity
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.
127SKILL.mdUpdated Jun 28, 2026