{"id":"9bf63cb3-92ee-4a31-98ae-56f98b3c0936","slug":"glebis-claude-skills","kind":"skill","name":"claude-skills","summary":"Collection of Claude Code skills for enhanced AI workflows","owner":"glebis","repoUrl":"https://github.com/glebis/claude-skills","license":"MIT","licenseTier":"permissive","trust":"community","stars":392,"match":null,"fewStars":false,"format":"skill","createdAt":"2025-10-25T14:58:50.000Z","addedAt":"2026-10-14T05:02:32.381Z","logoUrl":"https://avatars.githubusercontent.com/u/437776?u=f093bf340a56d1ba7ab13ee9446e8a48be5cd8ef&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools"],"tags":[],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-14T22:20:27.936Z","sample":false,"url":"https://conduits.dev/tools/glebis-claude-skills","language":"JavaScript","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Claude Skills\n\n~100 skills for [Claude Code](https://claude.com/claude-code) — meeting pipelines, research, image generation, TDD, publishing, personal analytics, and Claude Code ops. Each skill is a self-contained folder with a `SKILL.md`; Claude triggers them from natural language.\n\nBy [Gleb Kalinin](https://glebkalinin.com/) — Berlin-based technologist, AI educator, solopreneur, artist. Join the [Claude Code Lab](https://claude.salient.community/).\n\n## Install\n\n```bash\n# Plugin marketplace (recommended)\nclaude plugin marketplace add glebis/claude-skills\nclaude plugin install tdd@glebis-skills\n\n# skills CLI\nnpx skills add glebis/claude-skills --skill tdd\n\n# Manual\ngit clone https://github.com/glebis/claude-skills.git\ncp -r claude-skills/<skill-name> ~/.claude/skills/\n```\n\nPer-skill setup (API keys, Python/Node deps) is documented in each skill's `SKILL.md`. See [BUNDLES.md](./BUNDLES.md) for curated groupings.\n\n## Contents\n\n[Recent additions](#recent-additions) · [Meetings & transcripts](#meetings--transcripts) · [Research & knowledge](#research--knowledge) · [Writing, design & publishing](#writing-design--publishing) · [Images, audio & media](#images-audio--media) · [Communication](#communication) · [Development & release](#development--release) · [Thinking & decisions](#thinking--decisions) · [Personal analytics](#personal-analytics) · [Claude Code ops](#claude-code-ops) · [Lab, consulting & business](#lab-consulting--business)\n\n## Recent additions\n\n| Added | Skill | What it does |\n| --- | --- | --- |\n| 2026-07 | [font-features](./font-features/) | Inspect and apply OpenType features — ligatures, stylistic sets, alternates |\n| 2026-07 | [typography](./typography/) | Deterministic smart quotes, dashes, non-breaking spaces (RU/EN/DE/FR) |\n| 2026-07 | [pre-session-portrait](./pre-session-portrait/) | 7-lens JTBD client portrait before a paid consulting hour |\n| 2026-07 | [automation-advisor](./automation-advisor/) | Quantified ROI + break-even analysis for \"should I automate this?\" |\n| 2026-07 | [cull-release](./cull-release/) | Six-skill release orchestration suite (check, prepare, publish, verify, recover) |\n| 2026-07 | [elimination-research](./elimination-research/) | Numeric, source-auditable shortlist comparisons for products and vendors |\n| 2026-07 | [nielsen-heuristics](https://github.com/glebis/humane-agentic-design) | Formal heuristic evaluation against Nielsen's 10 usability heuristics — **moved to the humane plugin** |\n| 2026-07 | [i18n-studio](./i18n-studio/) | Edit, translate, and review Astro-style i18n string corpora |\n| 2026-07 | [the-goal](./the-goal/) | Theory-of-Constraints diagnostic for deciding what to automate |\n| 2026-06 | [design-tokens](https://github.com/glebis/humane-agentic-design) | DTCG 2025.10 token sets — validate, resolve, export to CSS — **moved to the humane plugin** |\n| 2026-06 | [app-release](./app-release/) | iOS/watchOS release pipeline to TestFlight and the App Store |\n| 2026-06 | [local-models](./local-models/) | Offline llama.cpp inference reusing models Ollama already downloaded |\n| 2026-06 | [feature-factory](./feature-factory/) | Solo-dev feature pipeline: goal-first, TDD, deterministic verification |\n\n## Meetings & transcripts\n\n| Skill | What it does |\n| --- | --- |\n| [fathom](./fathom/) | Fetch Fathom meetings, transcripts, summaries, action items; download video |\n| [granola](./granola/) | Granola cache/API → transcripts and Obsidian export, with 15-min auto-sync |\n| [zoom](./zoom/) | Create/manage Zoom meetings, access cloud recordings and transcripts |\n| [meeting-prep](./meeting-prep/) | Pull Cal.com bookings, research participants, audit past sessions, write prep notes |\n| [meeting-processor](./meeting-processor/) | Auto-detect meeting type and extract type-specific structured summaries |\n| [transcript-analyzer](./transcript-analyzer/) | Decisions, action items, opinions, terminology via Cerebras llama-3.3-70b |\n| [coaching-session-summarizer](./coaching-session-summarizer/) | Summarize coaching/therapy transcripts after a Fathom/Granola sync |\n| [session-anonymizer](./session-anonymizer/) | Three-layer PII anonymization (Natasha NER + privacy filter + local LLM) |\n| [youtube-transcript](./youtube-transcript/) | Transcript + metadata → Obsidian markdown, no video download |\n| [thinking-patterns](./thinking-patterns/) | Longitudinal cognitive analysis across months of transcripts (12 dimensions, multi-agent) |\n\n## Research & knowledge\n\n| Skill | What it does |\n| --- | --- |\n| [deep-research](./deep-research/) | OpenAI Deep Research API with prompt enhancement and sourced markdown reports |\n| [firecrawl-research](./firecrawl-research/) | Scrape and enrich notes with web sources; scientific writing with citations |\n| [elimination-research](./elimination-research/) | Deterministic scoring, ownership costs, and audit trail for shortlists |\n| [doctorg](./doctorg/) | Evidence-based health research, GRADE-style ratings, Apple Health context |\n| [qmd-search](./qmd-search/) | Local semantic + keyword search over an Obsidian vault; cross-lingual (EN↔RU) |\n| [learning-vault](./learning-vault/) | Learning profile for portable study vaults, with optional Dataview |\n| [open-knowledge-vault](./open-knowledge-vault/) | Maintain source-grounded OKF vaults with optional Obsidian and Dataview |\n| [temple-generator](./temple-generator/) | Turn a vault into a 3D interactive knowledge map with generative audio |\n| [daydream](./daydream/) | Multi-agent mining of non-obvious connections between vault notes |\n| [insight-extractor](./insight-extractor/) | Parse `/insights` output into trackable markdown action items |\n| [weekly-digest](./weekly-digest/) | Research, score, and publish a weekly industry digest on any topic |\n| [wow-digest](./wow-digest/) | Daily digest of genuinely surprising items, scored for epistemic friction |\n| [rag-eval](./rag-eval/) | Tune RAG pipelines with structured evals instead of eyeballing |\n| [rigorous-experiments](./rigorous-experiments/) | Pre-registered n-of-1 experiments, permutation tests, FDR discipline |\n| [whitepaper-audit](./whitepaper-audit/) | Audit long-form technical documents against a research-grounded checklist |\n| [name-audition](./name-audition/) | Domain availability, collision research, and scoring for candidate names |\n| [google-image-search](./google-image-search/) | Google CSE image search with LLM-powered selection and Obsidian enrichment |\n\n## Writing, design & publishing\n\n| Skill | What it does |\n| --- | --- |\n| [present](./present/) | Narrated HTML presentations — dual article/slides mode, ElevenLabs voiceover |\n| [presentation-generator](./presentation-generator/) | Neobrutalist HTML decks with Anime.js; export to PNG/PDF/video |\n| [pdf-generation](./pdf-generation/) | Markdown → PDF via Pandoc; mobile (6×9in) and print (A4) layouts, EN/RU |\n| [tufte-report](./tufte-report/) | Tufte-style data reports and dashboards as standalone HTML |\n| [brand-agency](./brand-agency/) | Agency brand colors, typography, and 11 social templates via Playwright |\n| [design-tokens](https://github.com/glebis/humane-agentic-design) | DTCG token sets, CSS export, APCA/WCAG contrast — **moved to the humane plugin** |\n| [typography](./typography/) | Locale-correct quotes, dashes, and non-breaking spaces via pinned CLI |\n| [font-features](./font-features/) | Inspect and apply ligatures, stylistic sets, and character variants |\n| [nielsen-heuristics](https://github.com/glebis/humane-agentic-design) | Evidence-backed heuristic usability evaluation — **moved to the humane plugin** |\n| [de-ai](./de-ai/) | Humanize AI-sounding text across 5 languages, preserving meaning and facts |\n| [i18n-studio](./i18n-studio/) | Edit, translate, and review i18n string corpora |\n| [sketch](./sketch/) | Sketch/diagram generation support |\n| [publish-skill](./publish-skill/) | Publish or update a skill on the claude-skills-site Astro website |\n| [telegram-post](./telegram-post/) | Draft → preview → publish formatted Telegram channel posts |\n| [agency-socials](./agency-socials/) | Event covers, YouTube thumbnails, and social assets for AGENCY Community |\n\n## Images, audio & media\n\n| Skill | What it does |\n| --- | --- |\n| [gpt-image-2](./gpt-image-2/) | OpenAI GPT Image 2 — thinking mode, 14 style presets, draft mode, cost controls |\n| [nano-banana](./nano-banana/) | Gemini image generation and editing with style and platform presets |\n| [vision-bench](./vision-bench/) | Score and compare images using vision LLMs as judges (11 criteria presets) |\n| [elevenlabs-tts](./elevenlabs-tts/) | Text → audio via ElevenLabs with voice presets and tunable parameters |\n\n## Communication\n\n| Skill | What it does |\n| --- | --- |\n| [telegram](./telegram/) | Fetch, search, send, schedule Telegram messages and media |\n| [telegram-telethon](./telegram-telethon/) | Full Telethon wrapper + daemon that spawns Claude sessions on triggers |\n| [tg-responder](./tg-responder/) | Review and send response drafts; track unanswered outbound messages |\n| [gws](./gws/) | Google Workspace CLI reference — Gmail, Calendar, Drive, Sheets, Docs, Chat |\n| [gmail](./gmail/) | Gmail search, fetch, attachments, labels via API |\n| [browser-mate](./browser-mate/) | Automate a logged-in Chrome without disturbing the user's open tabs |\n\n## Development & release\n\n| Skill | What it does |\n| --- | --- |\n| [tdd](./tdd/) | Multi-agent TDD with enforced context isolation across RED→GREEN→REFACTOR |\n| [feature-factory](./feature-factory/) | Solo-dev pipeline from feature intent to shipped, with evidence gates |\n| [skills/release](./skills/release/) | Config-driven releases with a tiered compatibility policy (`COMPATIBILITY.md`) |\n| [cull-release](./cull-release/) | Cull release suite: [check](./cull-release-check/), [prepare](./cull-release-prepare/), [publish](./cull-release-publish/), [verify](./cull-release-verify/), [recover](./cull-release-recover/) |\n| [app-release](./app-release/) | iOS/watchOS → TestFlight and App Store |\n| [init-tauri-app](./init-tauri-app/) | Scaffold Tauri v2 projects with house conventions |\n| [init-xcode-app](./init-xcode-app/) | Scaffold SwiftUI apps via XcodeGen (macOS, iOS, iOS+watchOS) |\n| [agent-cli](./agent-cli/) | Add agent-friendly `--json` NDJSON output to Python CLIs |\n| [repo-prep](./repo-prep/) | Prepare a repo for publication — LICENSE, README, metadata, community docs |\n| [llm-cli](./llm-cli/) | One CLI across 6 LLM providers and 40+ models |\n| [local-models](./local-models/) | Cheap offline inference via llama.cpp on Ollama-downloaded models |\n| [codex](./codex/) | Drive OpenAI Codex CLI for analysis, refactoring, automated edits |\n| [peer-agent-collaboration](./peer-agent-collaboration/) | Have Claude Code, Codex, and other agents work together as peers |\n| [linear](./linear/) | Create, list, update, and search Linear issues and projects |\n| [github-gist](./github-gist/) | Publish files or notes as secret/public gists |\n| [skills/job-babysitter](./skills/job-babysitter/) | Watch long-running background jobs (encodes, embeddings, batch pipelines) |\n| [skills/cmux](./skills/cmux/) | Control the cmux terminal app via its CLI socket API |\n\n## Thinking & decisions\n\n| Skill | What it does |\n| --- | --- |\n| [the-goal](./the-goal/) | Theory-of-Constraints diagnostic before building any automation |\n| [automation-advisor](./automation-advisor/) | 8 questions → break-even math, with voice-enabled web UI |\n| [decision-toolkit](./decision-toolkit/) | 7 frameworks, 20+ bias counter-questions, interactive HTML wizards |\n| [jtbd](https://github.com/glebis/humane-agentic-design) | Jobs-to-be-Done interviews, switching forces, messaging and GTM briefs — **moved to the humane plugin** |\n| [balanced](./balanced/) | Anti-sycophantic multi-perspective analysis and Socratic dialogue |\n| [cognitive-toolkit](https://github.com/glebis/claude-cognitive-toolkit) | CBT/DBT interventions — thought records, DEAR MAN, crisis skills (separate repo) |\n| [synthetic-session-generator](./synthetic-session-generator/) | Persona-consistent synthetic coaching/therapy transcripts for evals |\n\n## Personal analytics\n\n| Skill | What it does |\n| --- | --- |\n| [health-data](./health-data/) | Query Apple Health SQLite — vitals, activity, sleep, workouts (MD/JSON/FHIR) |\n| [wispr-analytics](./wispr-analytics/) | Analyze Wispr Flow dictation history; manage the dictation dictionary |\n| [browsing-history](./browsing-history/) | Query history across all synced Chrome devices with natural language |\n| [chrome-history](./chrome-history/) | Query local Chrome history by date, type, keyword, site |\n| [session-finder](./session-finder/) | Semantic index of Claude Code sessions (Gemini embeddings); relaunch best match |\n| [session-search](./session-search/) | Search session transcripts with synonym-aware semantic matching |\n\n## Claude Code ops\n\n| Skill | What it does |\n| --- | --- |\n| [ecosystem](./ecosystem/) | Audit skill health, project pulse, CLAUDE.md drift, service status |\n| [retrospective](./retrospective/) | Extract learnings from one session or all of today's, update skills and memory |\n| [skill-studio](https://github.com/glebis/skill-studio) | Interview-driven skill/automation design; analyze sessions into new skills |\n| [recording](./recording/) | Demo mode — redact PII from outputs in real time while screen-sharing |\n| [skills/disk-cleanup](./skills/disk-cleanup/) | Survey and clean macOS caches, package data, crash dumps |\n| [wispr-fix](./wispr-fix/) | Queue and batch-apply Wispr dictation corrections |\n| [context-builder](./context-builder/) | Generate AI-transformation discovery prompts for consulting clients |\n| [meta](./meta/) | Run Claude Code commands against the telegram_agent project |\n\n## Lab, consulting & business\n\n| Skill | What it does |\n| --- | --- |\n| [agency-docs-updater](./agency-docs-updater/) | Lab meeting pipeline: transcript → video → YouTube → summary → MDX → deploy |\n| [agency-meetup-publish](./agency-meetup-publish/) | Zoom recording → intro/outro, thumbnail, timecodes, YouTube, playlist |\n| [lab-retro](./lab-retro/) | Four-part retrospective and self-assessment for Lab participants |\n| [skills/library-sync](./skills/library-sync/) | Sync bilingual (EN/RU) library content for agency-docs |\n| [site-diagnosis](./site-diagnosis/) | Pre-consultation questionnaire for clients building sites with AI tools |\n| [sorted](./sorted/) | getSorted.de automation — invoicing, expenses, German VAT/ZM filings |\n| [cull](./cull/) | View, rate, organize, search, and export images with the Cull app |\n| [timebuzzer-led](./timebuzzer-led/) | Control timeBuzzer hardware LED via MIDI — colors, effects, status signals |\n\n## Skill structure\n\n```\nskill-name/\n├── SKILL.md          # Metadata, triggers, usage\n├── CHANGELOG.md      # Version history\n├── scripts/          # Executable orchestration\n├── assets/           # Resources\n└── references/       # Detailed docs\n```\n\n## Contributing\n\nFork, add a skill following the structure above, document it, open a PR. For guidance on authoring skills, see the [Claude Code skills docs](https://docs.claude.com/docs/claude-code/skills).\n\n## License\n\n[MIT](./LICENSE) — see individual skill directories for exceptions.\n\n---\n\nSkills require Claude Code to function; they are not standalone tools. [Support this work and learn Claude Code →](https://claude.salient.community/)\n"}