kvokov/reading-synthesis
skills/reading-synthesis/SKILL.md
Rigorous thirteen-part synthesis of a text or talk: deep summary, insights, structure, critique, framework rebuild, and CEO-level takeaways. Triggers: reading synthesis, synthesize this, deep dive, rigorous analysis, deconstruct, book analysis, article analysis, essay breakdown, intellectual synthesis, multi-dimensional analysis, executive summary of ideas, framework extraction. Uses: Read (and related file tools) for attached sources; WebSearch or WebFetch when comparands are missing or context is thin. Outputs: single structured markdown message with fixed section headers per rules/output-sections.md.
$ install --global
skillsauthnpx skillsauth add kvokov/oh-my-ai reading-synthesisInstall 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 24, 2026, 2:52 AM29.3s3 files scanned
SKILL.md
- name:
- reading-synthesis
- description:
- Rigorous thirteen-part synthesis of a text or talk: deep summary, insights, structure, critique, framework rebuild, and CEO-level takeaways. Triggers: reading synthesis, synthesize this, deep dive, rigorous analysis, deconstruct, book analysis, article analysis, essay breakdown, intellectual synthesis, multi-dimensional analysis, executive summary of ideas, framework extraction. Uses: Read (and related file tools) for attached sources; WebSearch or WebFetch when comparands are missing or context is thin. Outputs: single structured markdown message with fixed section headers per rules/output-sections.md.
- version:
- 1.0.0
- tags:
- reading, synthesis, analysis, nonfiction, fiction, mental-models, critique, executive-summary
Reading synthesis
Turn a supplied title, excerpt, file, or full work into one cohesive, high-value analysis aimed at semi-technical readers who want depth without academic padding.
Non-negotiables
- Use the full rubric in output-sections: produce all thirteen sections with the exact headers and order defined there, unless the user explicitly limits scope in the same turn.
- Ingest the whole artifact when the user provides a path or attachment: read the complete source with file tools before analyzing. If only a fragment is given, analyze that fragment and state what is missing for full-work claims.
- Ban fluff and repetition: no throat-clearing, no duplicate sentences across sections, no vague praise. Every paragraph must earn its place.
- Keep section 8 near 300 words (280–320). Count mentally; tighten if over.
- Deliver exactly ten numbered actions in section 10; each must be specific and schedulable.
- Comparative section (5) requires 3–5 named works or thinkers in the same territory. If the user names none, run WebSearch (or WebFetch on solid results) to propose defensible comparands. Never imply you read books you did not access; if comparison is based on well-known summaries, label uncertainty.
- Label inference: in mindset and decision lenses, separate text-evidenced claims from reasonable inference from tone, structure, or context.
- Format: professional, direct tone; level-2 headers matching the rubric file; optional brief bullets inside sections where density helps.
Process
- Clarify the artifact — title, medium (essay, book chapter, talk transcript, etc.), and whether the user wants the full rubric or a subset. If they are silent, run the full rubric.
- Load content — from message or via Read/Glob as needed. Note length limits: if the source is huge, analyze the portion provided or offer to continue in a follow-up with explicit scope.
- Classify structure — fiction vs nonfiction (or hybrid); pick the appropriate structural template in section 6 of the rubric.
- Research comparands if needed for section 5 — short, targeted queries; prefer stable, citable names and works.
- Draft all thirteen sections in one pass — maintain consistent terminology; cross-reference themes instead of copying paragraphs.
- Self-check before send — headers match rubric; section 8 word band; section 10 has ten items; no empty critique; Socratic Q&A is ordered logically.
Integrated example (abbreviated shape)
User: “Here’s a blog post on compound interest and career capital [paste].”
You: Read the paste → section 6 uses nonfiction outline → section 5 compares to similar career-design writing (names 3–4 real essays/books via search if needed) → section 8 stays ~300 words with no repeat of section 1 → section 9 lists principles as a system → section 10 lists ten actions (e.g. “Schedule 90 minutes weekly for skill stack review”).
Anti-patterns
- Inventing quotations, studies, or comparands that cannot be traced to the source or to named public works.
- Replacing critique with tone policing or generic “some may disagree.”
- Turning the Socratic skeleton into a FAQ unrelated to the work’s through-line.
- Using the CEO section for a full recap of earlier sections instead of stakes, decisions, and behavior change.
Related Skills
kvokov/nestjs
tools
VerifiedTrustedCommunity
NestJS (Nest.js) production patterns for modules, controllers, providers, guards, interceptors, pipes, middleware, JWT, ValidationPipe, microservices, GraphQL, Bull queues, Prisma, and TypeORM. Triggers: NestJS, Nest.js, Nest module, dependency injection, class-validator DTO, exception filter, testing module, GraphQL resolver, Bull queue, microservice client. Uses: Read, Grep, Glob, Bash, WebSearch. Outputs: tier-ordered review checklists and/or concrete code edits with cited rule filenames. Do NOT use for: non-Nest backends (Express/Fastify only with no Nest integration), frontend-only frameworks, generating AGENTS.md, or toolchain setup unrelated to Nest.
4SKILL.mdUpdated May 1, 2026
kvokov/uiux
development
VerifiedTrustedCommunity
Professional UI/UX design skill for React, Next.js, Tailwind CSS, React Native, and Flutter. Use when the user asks to create or polish UI components (modals, forms, tables, charts, navbars, sidebars, cards), design landing pages, build dashboards or admin panels, set up SaaS or mobile app screens, review or fix layout and accessibility issues, configure dark mode or responsive breakpoints, or establish a design system with tokens and component specs. Capabilities include: creating design-system token files and MASTER.md artifacts, generating responsive Tailwind layouts, scaffolding page-level component hierarchies, reviewing and fixing UI accessibility (a11y, WCAG), implementing React Native safe-area screens, and configuring Flutter ThemeData. Outputs design-system files (MASTER, page overrides, tokens, component specs) plus stack-faithful code. Do NOT use for: pure backend-only work with no UI impact, or inventing branding assets you do not have rights to use.
3SKILL.mdUpdated Apr 23, 2026
kvokov/skill-maker
tools
VerifiedTrustedCommunity
Use this skill any time someone wants to create, scaffold, build, fix, improve, benchmark, or optimize a Tessl/Claude skill — even if they don't say 'tessl' explicitly. If the request involves making a new skill ('create a skill for X', 'build me a skill that does Y', 'scaffold a skill called Z'), fixing or completing an existing one (missing tile.json, broken repo integration, low eval scores, description not triggering), or running and iterating on evals, invoke this skill. The full workflow covers: structured interview → SKILL.md + tile.json + rules/ scaffolding → README/CI repo integration → tessl tile lint → optional Tessl CLI pipeline (skill review, scenario generate/download, eval run) → hand-authored evals or LLM-as-judge fallback → benchmark logging. Do NOT use for: editing application code, debugging, refactoring, writing general documentation, or creating presentations.
3SKILL.mdUpdated Apr 23, 2026
kvokov/llm-wiki
development
VerifiedTrustedCommunity
Compiles and maintains a persistent LLM-written markdown wiki between immutable raw sources and answers—the Karpathy LLM Knowledge Base pattern. The agent writes and maintains the wiki; the human curates sources and reads it. Knowledge compounds instead of being re-derived each query. Triggers: llm wiki, persistent wiki, personal knowledge base, wiki maintenance, ingest sources, compound knowledge, index.md, log.md, Obsidian wiki, cross-references, Karpathy wiki pattern, compile wiki, knowledge base. Uses: Read, Glob, Grep, file edits, optional WebSearch, AskUserQuestion when schema or goals are ambiguous. Outputs: updated wiki pages, index, append-only log, citations on query, filed answers, visual outputs. Do NOT use for: mutating raw sources, one-off chat answers with no wiki artifact, or replacing a user-defined wiki schema without reading it first.
3SKILL.mdUpdated Apr 23, 2026