glebis-skills

CONFIDE — local-first de-identification toolkit (8 skills): confide:setup, confide:anon (redact + reversible map), confide:red (residual re-id risk), confide:rehydrate (restore locally), confide:view (HTML diff), confide:audit (stats-only corpus scan), confide:vault (three-locks storage), confide:annotate (gold + IAA). Privacy-first; raw text and the reversible map never leave the machine.

8 skills

End-to-end pipeline for publishing Claude Code lab meetings. Accepts optional args: date (YYYYMMDD, "yesterday", "today"

1 skill

Configure and run background agents with reusable profiles for agent engines, model providers and extensible execution backends. Trigger.dev and Cloudflare Workflows are available options; includes optional source-backed evidence review.

1 skill

Constructive, evidence-based dialogue mode that avoids sycophancy. This skill should be used when the user wants balance

1 skill

Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interf

1 skill

Query browsing history from all synced devices (iPhone, Mac, iPad, desktop). Supports natural language queries for filte

1 skill

Query Chrome browsing history with natural language. Filter by date range, article type, keywords, and specific sites.

1 skill

Evidence-based CBT and DBT intervention skills for AI assistants. Implements 7-step thought records with Burns' distortion detection, Opposite Action, DEAR MAN roleplay, TIPP crisis survival, Wise Mind, and affect labeling. Configurable pushback levels 0–3. Optional HRV biofeedback via Apple Health and Aurora Ring.

1 skill

Generate interactive AI transformation context-builder prompts for consulting clients. Use when creating structured disc

1 skill

daydream

1 skill

Generate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dash

1 skill

This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. It aut

1 skill

Scan and clean macOS caches, package-manager data, crash dumps, and app caches to reclaim disk space. Deterministic — a config registry (targets.json) plus survey.py (read-only) and clean.py (executor) do all measuring and deleting. Use for: freeing disk space, "disk is full", "clean up my Mac", "what's eating my disk".

1 skill

Evidence-based health research using tiered trusted sources with GRADE-inspired evidence ratings. Integrates Apple Healt

1 skill

This skill converts text to high-quality audio files using ElevenLabs API. Use this skill when users request text-to-spe

1 skill

Fetch meetings, transcripts, summaries, and action items from Fathom API. Use when user asks to get Fathom recordings, s

1 skill

This skill should be used when the user requests to research topics using FireCrawl, enrich notes with web sources, sear

1 skill

Publish files or Obsidian notes as GitHub Gists. Use when user wants to share code/notes publicly, create quick shareabl

1 skill

This skill should be used when searching, fetching, or downloading emails from Gmail. Use for queries like "search Gmail

1 skill

Search and download images via Google Custom Search API with LLM-powered selection. This skill should be used when findi

1 skill

Generate and edit images using OpenAI's GPT Image 2 API. Supports style presets (including text-heavy ones like infograp

1 skill

This skill should be used when importing, listing, or exporting Granola meeting recordings and transcripts. Queries Gran

1 skill

This skill should be used when interacting with Google Workspace services via the gws CLI — Gmail (search, triage, send,

1 skill

Hand a written brief to an ACP agent in its own git worktree and herdr workspace: dated doc, optional beads epic, handoff branch, launch via acp-run, then collect (commits, stray changes, the brief's checks) and close once merged. Use for: "hand this off", "create a handoff", "start it in its own worktree".

1 skill

Query Apple Health SQLite database for vitals, activity, sleep, and workouts. Supports Markdown, JSON, and FHIR R4 outpu

1 skill

insight-extractor

1 skill

Terminal-first JTBD engine for founders and product people. Interview fast, kill jargon, capture real switching forces (

1 skill

Final retrospective and self-assessment for participants of Claude Code Lab. Runs four sequential interactive parts — pr

1 skill

Manage Linear issues, projects, and workflows via CLI. This skill should be used when the user wants to create, list, up

1 skill

Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and int

1 skill

This skill should be used when processing meeting transcripts to auto-detect meeting type (leadgen, partnership, coachin

1 skill

Generate and edit images using Google's Gemini image generation models (Nano Banana family). Supports style presets, pla

1 skill

Portable Open Knowledge Format vault setup and maintenance, with optional Obsidian and Dataview views

1 skill

Professional PDF generation from markdown using Pandoc with Eisvogel template and EB Garamond fonts. Use when converting

1 skill

Generate interactive HTML presentations with neobrutalism styling, ASCII art decorations, and Agency brand colors. Outpu

1 skill

Demo/recording mode that redacts personally identifiable and sensitive information from Claude Code's outputs. Use when

1 skill

Research technical approaches, run bounded comparisons, and deliver reusable code with reproducible tests and configurable autonomy.

1 skill

retrospective

1 skill

Index and search Claude Code sessions using semantic embeddings (Gemini). Find past sessions by topic, relaunch the best

1 skill

This skill should be used when searching Claude Code session transcripts with semantic understanding. Triggers on querie

1 skill

sketch

1 skill

Interview-driven automation design tool. This skill should be used when the user wants to design a new skill, agent, aut

1 skill

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces

1 skill

This skill should be used when fetching, searching, downloading, sending, editing, or publishing messages on Telegram. U

1 skill

telegram-post

1 skill

This skill should be used for comprehensive Telegram automation via Telethon API. Use for sending/receiving messages, mo

1 skill

Generate a 3D interactive knowledge map (Inner Temple) from any Obsidian vault or document set. Supports multi-scale abs

1 skill

thinking-patterns

1 skill

Control timeBuzzer hardware LED via MIDI — set color, effects (pulse, strobe, rainbow, fade), and semantic status signals

1 skill

This skill analyzes meeting transcripts to extract decisions, action items, opinions, questions, and terminology using C

1 skill

Create Tufte-inspired data reports and infographic dashboards as standalone HTML files. Uses EB Garamond for text, Monas

1 skill

Score and compare images using vision LLMs as judges. YAML-defined criteria presets for 11 use cases (text-to-image, pho

1 skill

This skill should be used when analyzing Wispr Flow voice dictation history for self-reflection, work patterns, mental h

1 skill

"Extract YouTube video transcripts with metadata and save as Markdown to Obsidian vault. Use this skill when the user re

1 skill

Create and manage Zoom meetings and access cloud recordings via the Zoom API. Use for queries like "create a Zoom meetin

1 skill