Claude Skills by glebis

Claude Skills

~100 skills for 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.

By Gleb Kalinin — Berlin-based technologist, AI educator, solopreneur, artist. Join the Claude Code Lab.

Install

# Plugin marketplace (recommended)
claude plugin marketplace add glebis/claude-skills
claude plugin install tdd@glebis-skills

# skills CLI
npx skills add glebis/claude-skills --skill tdd

# Manual
git clone https://github.com/glebis/claude-skills.git
cp -r claude-skills/<skill-name> ~/.claude/skills/

Per-skill setup (API keys, Python/Node deps) is documented in each skill's SKILL.md. See BUNDLES.md for curated groupings.

Contents

Recent additions · Screenshots · Meetings & transcripts · Research & knowledge · Writing, design & publishing · Images, audio & media · Communication · Development & release · Thinking & decisions · Personal analytics · Claude Code ops · Lab, consulting & business

Recent additions

Added	Skill	What it does
2026-11	bridgework	Consent-gated, names-only audit of your stack, then a local canvas for practising what two tools could do together, with an agent prompt at every step
2026-11	luma-event	AGENCY event on Lu.ma: generated cover, Zoom meeting, event page, contact invites, announcement draft
2026-11	research-to-integration	Research → bounded experiment → reusable implementation; configurable questions, autonomy and execution budgets
2026-11	pii-pdf	Local PDF PII detection/redaction (names, addresses, contacts, accounts, IBANs) with table-safe rules, JSON CLI, setup and diagnostic smoke checks; standalone toolkit
2026-11	app-map	Interactive map of an app's screens, scenarios, tests and jobs, with a ranked list of what to test next
2026-10	background-agents	Configure and run background agents across extensible execution backends; Trigger.dev and Cloudflare Workflows available
2026-10	cms-migration-checklist	Gated WordPress → Next.js + Payload migration checklist: audit, import reconciliation, URL parity, cutover
2026-10	firecrawl-api	Firecrawl API script with Alexandria structured-data tools and a 1,850-tool catalog; key from SOPS
2026-10	palmier-reels	Narrative 9:16 reels in Palmier Pro from a spec + style (presets or design tokens)
2026-07	font-features	Inspect and apply OpenType features — ligatures, stylistic sets, alternates
2026-07	typography	Deterministic smart quotes, dashes, non-breaking spaces (RU/EN/DE/FR)
2026-07	pre-session-portrait	7-lens JTBD client portrait before a paid consulting hour
2026-07	automation-advisor	Quantified ROI + break-even analysis for "should I automate this?"
2026-07	cull-release	Six-skill release orchestration suite (check, prepare, publish, verify, recover)
2026-07	elimination-research	Numeric, source-auditable shortlist comparisons for products and vendors
2026-07	nielsen-heuristics	Formal heuristic evaluation against Nielsen's 10 usability heuristics — moved to the humane plugin
2026-07	i18n-studio	Edit, translate, and review Astro-style i18n string corpora
2026-07	the-goal	Theory-of-Constraints diagnostic for deciding what to automate
2026-06	design-tokens	DTCG 2025.10 token sets — validate, resolve, export to CSS — moved to the humane plugin
2026-06	app-release	iOS/watchOS release pipeline to TestFlight and the App Store
2026-06	local-models	Offline llama.cpp inference reusing models Ollama already downloaded
2026-06	feature-factory	Solo-dev feature pipeline: goal-first, TDD, deterministic verification

Screenshots

app-map	synthetic-session-generator	gpt-image-2
<img src="./app-map/screenshot.png" alt="App map on its Test next tab: ranked screens with Copy prompt and Add to brief buttons" width="280">	<img src="./synthetic-session-generator/screenshot.png" alt="Generated case page for a fictional client, marked synthetic" width="280">	<img src="./gpt-image-2/screenshot.png" alt="Banner of sample images made with the skill" width="280">
Test next, from the made-up Tally example	Case page for a fictional persona	Sample image styles
luma-event	bridgework
<img src="./luma-event/screenshot.png" alt="Event cover with a wireframe terrain and a wave crest, for a made-up 2030 meetup" width="280">	<img src="./bridgework/screenshot.png" alt="Bridgework chain of three parts from a made-up stack, with an empty Your idea first box above example ideas" width="280">
Cover for a made-up event	Chain on the synthetic demo stack

Meetings & transcripts

Skill	What it does
fathom	Fetch Fathom meetings, transcripts, summaries, action items; download video
granola	Granola cache/API → transcripts and Obsidian export, with 15-min auto-sync
zoom	Create/manage Zoom meetings, access cloud recordings and transcripts
meeting-prep	Pull Cal.com bookings, research participants, audit past sessions, write prep notes
meeting-processor	Auto-detect meeting type and extract type-specific structured summaries
transcript-analyzer	Decisions, action items, opinions, terminology via Cerebras llama-3.3-70b
coaching-session-summarizer	Summarize coaching/therapy transcripts after a Fathom/Granola sync
session-anonymizer	Three-layer PII anonymization (Natasha NER + privacy filter + local LLM)
youtube-transcript	Transcript + metadata → Obsidian markdown, no video download
thinking-patterns	Longitudinal cognitive analysis across months of transcripts (12 dimensions, multi-agent)

Research & knowledge

Skill	What it does
deep-research	OpenAI deep research (Responses API + web search) with prompt enhancement; saves raw response JSON, resumable background runs
firecrawl-api	Firecrawl API script: search, scrape, extract, map, Alexandria discover/contract/run, local tool catalog
firecrawl-research	Scrape and enrich notes with web sources; scientific writing with citations
elimination-research	Deterministic scoring, ownership costs, and audit trail for shortlists
doctorg	Evidence-based health research, GRADE-style ratings, Apple Health context
qmd-search	Local semantic + keyword search over an Obsidian vault; cross-lingual (EN↔RU)
vault-fs	Move, rename, or trash Obsidian notes without breaking wikilinks or markdown links
learning-vault	Learning profile for portable study vaults, with optional Dataview
open-knowledge-vault	Maintain source-grounded OKF vaults with optional Obsidian and Dataview
temple-generator	Turn a vault into a 3D interactive knowledge map with generative audio
daydream	Multi-agent mining of non-obvious connections between vault notes
insight-extractor	Parse /insights output into trackable markdown action items
weekly-digest	Research, score, and publish a weekly industry digest on any topic
wow-digest	Daily digest of genuinely surprising items, scored for epistemic friction
rag-eval	Tune RAG pipelines with structured evals instead of eyeballing
rigorous-experiments	Pre-registered n-of-1 experiments, permutation tests, FDR discipline
whitepaper-audit	Audit long-form technical documents against a research-grounded checklist
name-audition	Domain availability, collision research, and scoring for candidate names
google-image-search	Google CSE image search with LLM-powered selection and Obsidian enrichment

Writing, design & publishing

Skill	What it does
present	Narrated HTML presentations — dual article/slides mode, ElevenLabs voiceover
presentation-generator	Neobrutalist HTML decks with Anime.js; export to PNG/PDF/video
pii-pdf	Local PDF PII detection and replacement (Tesseract + spaCy + format rules) via a versioned JSON CLI; native, scanned and hidden-OCR pages
pdf-generation	Markdown → PDF via Pandoc; mobile (6×9in) and print (A4) layouts, EN/RU
tufte-report	Tufte-style data reports and dashboards as standalone HTML
brand-agency	Agency brand colors, typography, and 11 social templates via Playwright
design-tokens	DTCG token sets, CSS export, APCA/WCAG contrast — moved to the humane plugin
typography	Locale-correct quotes, dashes, and non-breaking spaces via pinned CLI
font-features	Inspect and apply ligatures, stylistic sets, and character variants
nielsen-heuristics	Evidence-backed heuristic usability evaluation — moved to the humane plugin
de-ai	Humanize AI-sounding text across 5 languages, preserving meaning and facts
i18n-studio	Edit, translate, and review i18n string corpora
sketch	Sketch/diagram generation support
publish-skill	Publish or update a skill on the claude-skills-site Astro website
telegram-post	Draft → preview → publish formatted Telegram channel posts
agency-socials	Event covers, YouTube thumbnails, and social assets for AGENCY Community

Images, audio & media

Skill	What it does
gpt-image-2	OpenAI GPT Image 2 — thinking mode, 14 style presets, draft mode, cost controls
nano-banana	Gemini image generation and editing with style and platform presets
vision-bench	Score and compare images using vision LLMs as judges (11 criteria presets)
elevenlabs-tts	Text → audio via ElevenLabs with voice presets and tunable parameters
palmier-reels	Vertical narrative reels in Palmier Pro via MCP — beat-cut, word-by-word typography, card wipes, film jitter, ElevenLabs SFX; style presets or DTCG design tokens

Communication

Skill	What it does
telegram	Fetch, search, send, schedule Telegram messages and media
telegram-telethon	Full Telethon wrapper + daemon that spawns Claude sessions on triggers
tg-responder	Review and send response drafts; track unanswered outbound messages
gws	Google Workspace CLI reference — Gmail, Calendar, Drive, Sheets, Docs, Chat
gmail	Gmail search, fetch, attachments, labels via API
browser-mate	Automate a logged-in Chrome without disturbing the user's open tabs

Development & release

Skill	What it does
app-map	Map screens, workflows and real tests into one page: what to test next, testing gaps, thin jobs and agent hand-off prompts
tdd	Multi-agent TDD with enforced context isolation across RED→GREEN→REFACTOR
feature-factory	Solo-dev pipeline from feature intent to shipped, with evidence gates
cms-migration-checklist	WordPress → Next.js + Payload migration: phase detection, evidence-backed gates, known pitfalls, cutover runbook
skills/release	Config-driven releases with a tiered compatibility policy (COMPATIBILITY.md)
cull-release	Cull release suite: check, prepare, publish, verify, recover
app-release	iOS/watchOS → TestFlight and App Store
init-tauri-app	Scaffold Tauri v2 projects with house conventions
init-xcode-app	Scaffold SwiftUI apps via XcodeGen (macOS, iOS, iOS+watchOS)
agent-cli	Add agent-friendly --json NDJSON output to Python CLIs
repo-prep	Prepare a repo for publication — LICENSE, README, metadata, community docs
llm-cli	One CLI across 6 LLM providers and 40+ models
local-models	Cheap offline inference via llama.cpp on Ollama-downloaded models
codex	Drive OpenAI Codex CLI for analysis, refactoring, automated edits
peer-agent-collaboration	Have Claude Code, Codex, and other agents work together as peers
agent-roundtable	Multi-agent audit over ACP (Codex, Command Code, Gemini, OpenCode, Claude) that converges on a spec and task list
linear	Create, list, update, and search Linear issues and projects
github-gist	Publish files or notes as secret/public gists
skills/job-babysitter	Watch long-running background jobs (encodes, embeddings, batch pipelines)
skills/cmux	Control the cmux terminal app via its CLI socket API

Thinking & decisions

Skill	What it does
bridgework	Audit your stack (read-only, with permission), then practise combining its parts on a local canvas
the-goal	Theory-of-Constraints diagnostic before building any automation
automation-advisor	8 questions → break-even math, with voice-enabled web UI
decision-toolkit	7 frameworks, 20+ bias counter-questions, interactive HTML wizards
jtbd	Jobs-to-be-Done interviews, switching forces, messaging and GTM briefs — moved to the humane plugin
balanced	Anti-sycophantic multi-perspective analysis and Socratic dialogue
cognitive-toolkit	CBT/DBT interventions — thought records, DEAR MAN, crisis skills (separate repo)
synthetic-session-generator	Persona-consistent synthetic coaching/therapy transcripts for evals

Personal analytics

Skill	What it does
health-data	Query Apple Health SQLite — vitals, activity, sleep, workouts (MD/JSON/FHIR)
wispr-analytics	Analyze Wispr Flow dictation history; manage the dictation dictionary
browsing-history	Query history across all synced Chrome devices with natural language
chrome-history	Query local Chrome history by date, type, keyword, site
session-finder	Semantic index of Claude Code sessions (Gemini embeddings); relaunch best match
session-search	Search session transcripts with synonym-aware semantic matching
sessiondex	One full-text index of Codex, Claude Code, OpenCode, and Pi sessions; recent, search, show, resume

Claude Code ops

Skill	What it does
ecosystem	Audit skill health, project pulse, CLAUDE.md drift, service status
retrospective	Extract learnings from one session or all of today's, update skills and memory
skill-studio	Interview-driven skill/automation design; analyze sessions into new skills
recording	Demo mode — redact PII from outputs in real time while screen-sharing
skills/disk-cleanup	Survey and clean macOS caches, package data, crash dumps
skills/handoff	Hand a brief to an ACP agent in its own worktree and herdr workspace, then verify its work
wispr-fix	Queue and batch-apply Wispr dictation corrections
context-builder	Generate AI-transformation discovery prompts for consulting clients
meta	Run Claude Code commands against the telegram_agent project

Lab, consulting & business

Skill	What it does
luma-event	Cover → Zoom → Lu.ma event → invites to calendar contacts → announcement draft
agency-docs-updater	Lab meeting pipeline: transcript → video → YouTube → summary → MDX → deploy
agency-meetup-publish	Zoom recording → intro/outro, thumbnail, timecodes, YouTube, playlist
lab-retro	Four-part retrospective and self-assessment for Lab participants
skills/library-sync	Sync bilingual (EN/RU) library content for agency-docs
site-diagnosis	Pre-consultation questionnaire for clients building sites with AI tools
sorted	getSorted.de automation — invoicing, expenses, German VAT/ZM filings
cull	View, rate, organize, search, and export images with the Cull app
timebuzzer-led	Control timeBuzzer hardware LED via MIDI — colors, effects, status signals

Skill structure

skill-name/
├── SKILL.md          # Metadata, triggers, usage
├── CHANGELOG.md      # Version history
├── screenshot.png    # What it produces, using synthetic data
├── scripts/          # Executable orchestration
├── assets/           # Resources
└── references/       # Detailed docs

Contributing

Fork, add a skill following the structure above, document it, open a PR. For guidance on authoring skills, see the Claude Code skills docs.

License

MIT — see individual skill directories for exceptions.

---

Skills require Claude Code to function; they are not standalone tools. Support this work and learn Claude Code →