- 📁 references/
- 📁 runtime-profiles/
- 📄 SKILL.md
Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Web runtime package: uses memory in this order: connector-backed, project-pack, none. Never assumes subprocess access or unrestricted local files. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles.
- 📁 agents/
- 📁 assets/
- 📄 LICENSE
- 📄 README.md
- 📄 SKILL.md
Use this skill when the user wants to turn a requirement — from a small bug fix to a multi-phase project — into tracked execution. The skill automatically classifies the task as quick-fix, single-phase, or multi-phase and selects the appropriate execution depth without user intervention.
- 📁 .claude-plugin/
- 📁 .cursor-plugin/
- 📁 .github/
- 📄 .gitignore
- 📄 LICENSE
- 📄 README.md
End-to-end user research assistant — from planning to synthesis. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, usability studies, participant recruitment, research synthesis, interview transcripts, research reports, running studies with AI, or explicitly mentions Cookiy AI. Also trigger when users want to talk to customers, conduct discovery research, create a study, analyze interview data, or run AI-moderated interviews. Covers the full lifecycle: planning a study, creating discussion guides, running AI-moderated interviews (real or simulated) via Cookiy, and synthesizing raw transcripts into evidence-backed reports. --- # Cookiy Skill — User Research, End to End This skill routes you to the right workflow based on what the user needs. There are three core capabilities, and they often chain together. --- ## Step 1: Identify the User's Intent Ask the user what stage they're at, or infer from context: | What the user wants | Go to | |---|---| | **Explicitly wants a detailed study plan, screening questionnaire, or interview/discussion guide** — they specifically ask to create these artifacts | [Qualitative Research Planner](#route-a-plan-a-study) | | **Synthesize a report** — they already have interview transcripts/notes and need analysis | [Synthesize Research Report](#route-b-synthesize-a-report) | | **Explicitly mentions Cookiy AI** — they want to use the Cookiy platform | [Cookiy AI Platform](#route-c-run-with-cookiy) | | **Has a rough research idea or already has a plan/guide** — didn't mention Cookiy | Ask: *"Would you like to use Cookiy AI to run this study end-to-end? Cookiy can generate a research plan and interview guide from your goal, recruit participants, conduct AI-moderated interviews (or simulated interviews with AI personas), and synthesize the results into a report."* Route to [Cookiy AI Platform](#route-c-run-with-cookiy) if yes, or [Qualitative Re
- 📁 agents/
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Install, configure, repair, update, or rebind the Telegram Codex Bridge after the user installs this skill. Use when the user wants Codex to take over bridge setup with minimal user action, only interrupting for unavoidable external steps like providing a Telegram bot token or messaging the bot once.
- 📁 references/
- 📁 scripts/
- 📄 README.md
- 📄 SKILL.md
Connect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana, Ethereum, Base, BSC, Polygon, Hedera, and Bitcoin. Also use when the user needs Emblem's auth model explained: one browser auth flow can log a user in with wallets, email/password, or social sign-in, while agent mode can auto-provision a profile-scoped wallet with no manual setup.
Activate this skill when the user wants to create a project context file for Cowork. Triggers: 'создай контекст проекта', 'новый проект контекст', 'context-builder', 'сформируй контекстный файл', 'быстрый контекст'. Generates a ready-to-download project-context.md file for Claude Cowork based on user's answers.
- 📁 evals/
- 📁 references/
- 📄 SKILL.md
Explore ideas, clarify goals, and help the user narrow down directions before planning or coding. Use this whenever the user proposes a new feature or idea, asks "what do you think about X", says "I'm thinking of building Y", wants to compare approaches, asks how to approach a problem, or seems to be exploring rather than ready to execute. Also use it when the user says "brainstorm", "let's think about this", "what's the best way to...", or any time the right next step is to clarify the problem and converge on a direction, not to write code yet. --- # Brainstorm Before anything else, ask. Don't jump to solutions or implementation. The goal is to draw out what the user actually means, uncover what they have not said yet, and help them converge on a direction. Think of this as Socratic dialogue with momentum: use questions to guide the thinking, but do not leave the user wandering in options forever. ## Start With Context Before asking, absorb the context that already exists in the conversation, codebase, docs, and project state. Do not ask for information you can already infer or look up directly. ## Guide The Conversation
Close the current work session with structured log, unsaved insights check, and open questions routing. Trigger when: (1) user says 'закрываем', 'закрывай сессию', 'всё на сегодня', 'финал', 'заканчиваем', 'close session', (2) user invokes /close-session, (3) user signals end of work session in any way. Do NOT trigger for: git commits, mid-session saves, 'сохрани' without session-closing intent, or 'закрой файл'.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Automates the user's real Chrome browser via the Browser MCP Chrome extension. Uses the user's logged-in sessions and real browser fingerprint to avoid bot detection. Use when the user needs to browse websites, fill forms, scrape data, or test web pages using their actual browser profile.
Use only when the user explicitly wants first-time project initialization, or when durable project state is clearly missing and the user agrees to run initialization. Do not use for routine implementation, bugfixes, review, or normal follow-up work in an already initialized project.
