lyndonkl/skills/closer-critique
skills/closer-critique/SKILL.md
--- name: closer-critique description: Evaluates the final paragraph of a substacker draft for compression and closing form — bolded maxim, forward-looking question, or compressed mechanism statement. For series posts (frontmatter series: {slug}), verifies the running scoreboard (P&L, Brier, W-L) is present and updated. Use on every draft. Blocks publication of series posts missing the scoreboard. Trigger keywords: closer, closing, last paragraph, bolded maxim, scoreboard, CTA, wrap up, conclusi
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/closer-critiqueInstall 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, 10:10 AM168.2s1 file scanned
SKILL.md
- name:
- closer-critique
- description:
- Evaluates the final paragraph of a substacker draft for compression and closing form — bolded maxim, forward-looking question, or compressed mechanism statement. For series posts (frontmatter series: {slug}), verifies the running scoreboard (P&L, Brier, W-L) is present and updated. Use on every draft. Blocks publication of series posts missing the scoreboard. Trigger keywords: closer, closing, last paragraph, bolded maxim, scoreboard, CTA, wrap up, conclusion.
Closer Critique
Table of Contents
- Closing archetypes
- Scoreboard check (series posts)
- Workflow
- Worked example
- Guardrails
Related skills: Called by Editor in the structural pass. For series posts, enforces scoreboard non-negotiability (ties to style-guide.md's scoreboard template and each section-profile's operational rules).
Closing archetypes
| Archetype | Example | Verdict | |---|---|---| | Bolded maxim | "You don't have an AI problem. You have an eval problem." | PASS | | Forward-looking question / statement | "Game 6 is tomorrow. The scoreboard will move." | PASS | | Compressed mechanism | "The AI is not the bottleneck. The context you architect around it is." | PASS | | Gratitude beat | "I'm grateful for it." (after a reader-correction post) | PASS | | Scoreboard + restrained disclaimer | Running-tally block + one-paragraph financial disclaimer | PASS (and REQUIRED for series) | | "In summary…" or "To conclude…" | prompt residue | FLAG tier-2 | | Custom CTA | "If this resonated, subscribe!" | FLAG tier-1 | | No close / dangling | Post ends mid-thought | FLAG tier-1 |
Scoreboard check (series posts)
If draft frontmatter has series: {slug}, the closer MUST include a scoreboard block per style-guide.md:
Running tally: P&L $NNN.NN, Brier 0.NN, W-L N-N
This week: +$N.NN or -$N.NN on {bet}.
Placed above the bolded maxim (if one exists).
Missing scoreboard = automatic tier-1 blocker. No-go on series posts until fixed.
Workflow
Evaluate closer:
- [ ] Step 1: Extract last paragraph (and bolded maxim if separate)
- [ ] Step 2: Classify archetype
- [ ] Step 3: If series, check scoreboard presence + format
- [ ] Step 4: Emit verdict + flags
Worked example
Series post closer (Kalshi Log) — missing scoreboard:
This concludes my Fed-meeting experiment. Thanks for reading.
The decision is not the news. The explanation is.
Flags:
- (Tier-1) Scoreboard missing. Series is
kalshi-log. Prior post ended with P&L +$127, Brier 0.18, W-L 4-3. This post must update. - (Tier-2) "Thanks for reading" — CTA residue. Cut.
Rewrite (scoreboard insertion above the maxim):
Running tally: P&L $134.50, Brier 0.19, W-L 5-3
This week: +$7.50 on the Fed decision not moving.
**The decision is not the news. The explanation is.**
Non-series post closer (good):
After training for two weeks, the model held. I do not know whether it would hold on a different dataset.
The context you architect around it is.
Classification: compressed mechanism + bolded maxim. PASS.
Guardrails
- Series posts without scoreboard = automatic tier-1. Non-negotiable.
- Scoreboard format follows
style-guide.mdexactly. Deviations (missing W-L, missing Brier) are tier-1. - Custom CTA ("subscribe if this resonated!") = tier-1. Substack's platform boilerplate is fine.
- Dangling close ("... and that's what I think about attention") = tier-1.
- Don't flag bolded maxims that are a full paragraph of prose — bolded-for-emphasis within a paragraph is different from a one-sentence maxim close. Accept both forms.
- The closer can be a scoreboard-only (no maxim) on series posts — acceptable if the scoreboard IS the close.
Quick reference
- Input: last paragraph + draft frontmatter.
- Output: classification + verdict + scoreboard-check result for series posts.
- Blocks: series posts without scoreboard, custom CTAs, dangling closes.
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