lyndonkl/skills/check-analogy-novelty
skills/check-analogy-novelty/SKILL.md
--- name: check-analogy-novelty description: Cross-references each proposed analogy in a 5-framing set against substacker shared-context/analogy-catalog.md to flag reuse. Classifies each analogy as new, reused-from-catalog (and which entry), or adjacent-to-catalog (close to an existing entry but not identical). Prevents the writer from recycling "imagine a library" for the twentieth time. Use after generate-analogy-set and before presenting framings to the writer. Trigger keywords: novelty, cata
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/check-analogy-noveltyInstall 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, 10:08 AM122.9s1 file scanned
SKILL.md
- name:
- check-analogy-novelty
- description:
- Cross-references each proposed analogy in a 5-framing set against substacker shared-context/analogy-catalog.md to flag reuse. Classifies each analogy as new, reused-from-catalog (and which entry), or adjacent-to-catalog (close to an existing entry but not identical). Prevents the writer from recycling "imagine a library" for the twentieth time. Use after generate-analogy-set and before presenting framings to the writer. Trigger keywords: novelty, catalog, analogy reuse, already used, imagine a library.
Check Analogy Novelty
Table of Contents
- Workflow
- Match tiers
- Worked example
- Guardrails
Related skills: Called by the Intuition Builder after generate-analogy-set and before presenting framings. Reads shared-context/analogy-catalog.md. Does NOT write to the catalog — that's update-analogy-catalog's job, fired on publish.
Workflow
For each of the 5 framings:
- [ ] Step 1: Extract the analogy's source domain (e.g., "library card catalog")
- [ ] Step 2: Extract the analogy's target concept (e.g., "KV cache")
- [ ] Step 3: Grep analogy-catalog.md for exact or near-exact source × target match
- [ ] Step 4: Classify: new | reused-from-catalog | adjacent-to-catalog
- [ ] Step 5: For reused/adjacent, cite the catalog entry with its post
Match tiers
- New: neither the source nor a close variant of it appears in the catalog for this target concept.
- Reused-from-catalog: exact source × target match — writer already used this analogy in a published post. Flag strongly; either justify reuse or swap.
- Adjacent-to-catalog: source matches a nearby analogy in the catalog (e.g., "drawer" vs. "card catalog") or target is in the catalog but source differs. Flag softly — writer should see the adjacency.
"Close variant" = same source domain (library, immune system, bucket brigade) even if different specific instance.
Worked example
Proposed framings for KV cache:
- Everyday: "a library's card catalog with a fixed drawer count"
- Physical metaphor: "a ring buffer with index"
- Contrarian: "the cache is not the table — it's the index into what's been already paid for"
- Historical: "before caches, every lookup was recomputation"
- Counterfactual: "remove the cache and decode becomes quadratic"
Catalog check:
- Entry in catalog: "Agents as departments reading each other's memos but never sitting in on each other's meetings" — source: institutional. Target: multi-agent. Not related to KV cache.
- Entry: "Bucket brigade" — source: bucket brigade. Target: sequential multi-agent. Not related.
- No entry for
library→ KV cache, orring buffer, orindex.
Output:
- Everyday: new
- Physical metaphor: new
- Contrarian: new
- Historical: new
- Counterfactual: new
But: if the catalog had an entry "Library index → tokenizer vocabulary", framing 1's adjacency would trigger: "adjacent-to-catalog — library appears once for a different target". Flag softly.
Guardrails
- Read-only. Never writes to the catalog.
- Match on both source domain and target concept. Same source for different target is an adjacency, not a reuse.
- Flag adjacencies, don't auto-reject — the writer decides if reuse is intentional (a recurring analogy can be a feature).
- Cite the catalog entry + post when flagging. "Reused from catalog" without pointing to the entry is useless.
- Don't expand near-matches to other analogy directions (biology vs. organizational are different domains, never flag across).
- If the catalog is empty (early-stage publication), all framings are
newby definition. Note this once in the output.
Quick reference
- Input: list of 5 framings + analogy-catalog.md.
- Output: per-framing classification
{new | reused-from-catalog | adjacent-to-catalog}with citation. - Side effect: none. Read-only.
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