iusztinpaul

Harness-agnostic version of `/implement`. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as `agents/software-engineer.md` and `agents/tester.md` instead of being launched as subagents. Resolves the ticket from `implement_yourself/tasks/`, creates an `implementing/from-scratch` branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), adopts the software-engineer role to implement, then switches to the tester role to verify (logic tickets only). Loops on FAIL up to 3 times, moves the file to `tasks/done/`, then commits directly with `git commit -m`. Stops after one ticket. Trigger when the user types `/implement-universal`, asks to "implement task NNN without subagents", or is running in a harness (Cursor, Windsurf, plain Claude API client, etc.) that doesn't support Claude Code's `Task` tool.

Drive a single workshop ticket through the inner SWE↔Tester loop. Resolves the ticket from `implement_yourself/tasks/`, creates an `implementing/from-scratch` branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), launches the software-engineer agent to implement it, then routes by archetype — Tester runs on logic tickets, orchestrator spot-checks the SWE's AC walk on glue/bootstrap tickets, fast-path file existence check on docs tickets (Tester HARD-OFF). Loops on FAIL up to 3 times, moves the file to `tasks/done/`, then commits directly with `git commit -m`. Stops after one ticket — the human reviews the commit, talks through it, then re-invokes for the next ticket. Trigger when the user types `/implement`, asks to "implement task NNN", says "pick up the next ticket", or otherwise wants to ship one workshop ticket under supervision.

**[REQUIRED]** Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit applications. Also required for building custom components (inline or packaged), using st.components.v2, or any HTML/JS/CSS component work. Triggers: streamlit, st., dashboard, app.py, beautify, style, CSS, color, background, theme, button, widget styling, custom component, st.components, packaged component, pyproject.toml, asset_dir, CCv2, HTML/JS component.

Building chat interfaces in Streamlit. Use when creating conversational UIs, chatbots, or AI assistants. Covers st.chat_message, st.chat_input, message history, and streaming responses.

Builds bidirectional Streamlit Custom Components v2 (CCv2) using `st.components.v2.component`. Use when authoring inline HTML/CSS/JS components or packaged components (manifest `asset_dir`, js/css globs), wiring state/trigger callbacks, theming via `--st-*` CSS variables, or bundling with Vite / `component-template` v2.

Building dashboards in Streamlit. Use when creating KPI displays, metric cards, or data-heavy layouts. Covers borders, cards, responsive layouts, and dashboard composition.

Building multi-page Streamlit apps. Use when creating apps with multiple pages, setting up navigation, or managing state across pages.

Choosing the right Streamlit selection widget. Use when deciding between radio buttons, selectbox, segmented control, pills, or other option selection widgets. Helps pick the right widget for the number of options and selection type.

Bootstrap a new repo or component from the opinionated spec library (mode=create), or audit an existing scaffolded repo for drift against the scaffold rules (mode=evaluate, report-only).

Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals `/squid-refactor` can consume directly.

Plan a refactor as an ordered, commit-grain Tasks Plan with structural acceptance criteria (suite green at every step, no behaviour diff) that `/squid-implement-night` can execute end-to-end.

Bug intake — localise the suspected code, capture a deterministic reproducer, and emit a groomed bug task with a regression-test acceptance criterion, ready for /squid-implement-task or the full pipeline.

Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan, or when the user says "/squid-implement-night".

Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. Use when one or more GROOMED tasks are ready to build, or the user says "/squid-implement-task". To plan a feature first use /squid-plan; for the full end-to-end pipeline use /squid-implement-night.

Turn a raw feature spec into an approved Tasks Plan — grill the spec, have the Product Architect groom draft tasks (+ optional ADR and glossary additions), then run ONE human gate that decides everything touching the repo: tasks + storage, ADR, glossary, worktree, and which build to run.

Push the committed feature branch, create or update its PR, then run Product Architect acceptance and PR-Reviewer on it. Output: a clean PR with no blockers, or ONE rollup task. Trigger after a feature's tasks are implemented and committed, or when the user says "/squid-review".

Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM-related automation task.

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

How to use the Readwise CLI — access highlights, documents, and your entire reading library from the command line

Distill a research directory (produced by /research) into a single compact research.md containing a guideline-relative distillation of only the sources that were actually used in a piece of content. Use this skill whenever the user wants to extract used references from research, create a research appendix for an article, distill research into what was actually cited, or produce a portable reference file from a research directory. Trigger when the user says things like "distill my research", "extract used sources", "which research did I actually use", "create research.md", "compile references from research", or after finishing an article that used a research directory.

Health-check a research directory produced by /research. Runs seven checks — orphan sources, missing entity/concept hubs, missing comparison candidates, broken wikilinks, stale claims, contradictions, and open-question synthesis. Outputs a report; edits where safe (broken-link flags, open-question append, contradiction surfacing); flags-only otherwise. Always user-triggered, never automated. Trigger when the user says things like "lint my research", "health check my research", "check the wiki", "audit my research dir", "what's wrong with my wiki", "find orphans / contradictions / stale claims".

Generate a multi-form answer (Marp slide deck, matplotlib chart, Obsidian Canvas, or social content brief) from one or more wiki pages in a research directory and file the output back into wiki/renders/. Outputs compound — they appear in index.yaml/index.md and can be re-rendered idempotently. One run can render several forms at once. Use when the user wants to "make a slide deck on X", "chart the comparison of A vs B", "build a canvas of how these concepts connect", "render this as Marp", or "extract a post idea / content brief from my research". Trigger on phrasings like "render", "slide deck", "chart", "canvas", "marp", "brief", "post idea", "extract ideas for social".

Build, extend, AND query a persistent LLM-maintained wiki for any research topic. Conversational entry point that routes between four modes - query (fast read-only answer from existing wiki), append (ingest the sources the user provided, no discovery), deep (explicit discovery/deep research at a fast/light/deep depth preset), and init (create a new research directory). Ingests from your knowledge sources (Obsidian vault + Readwise + NotebookLM + GitHub repos + YouTube videos + web seeds + user-dropped PDFs) and maintains a wiki layer (per-source pages, entities, concepts, comparisons, overview, synthesis, open questions, contradictions). Use for any research interaction - first-time research on a topic, "what do I have on X", "load my research on Y", "add this PDF to my research", "deep dive on Z", "pull together my notes on Y", "extend my research with this file". Trigger on the phrases above plus "search my research", "use my research", "find sources about X".

Build production-ready Bright Data integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web scraping, search, browser automation, and structured data extraction. Covers Web Unlocker API, SERP API, Web Scraper API, and Browser API (Scraping Browser).

Create or update a GitHub pull request for the current branch. Use this skill whenever the user says "create PR", "open PR", "update PR", "push and PR", "/create-pr", or when the PR workflow step is reached in the development workflow. Handles both first-time PR creation and updating existing PRs with new changes.

Query, explore, and write to Tree's knowledge graph memory. Use when the user asks to recall, search, visualize, or ingest information (people, tasks, episodes, preferences, documents, URLs, files, conversations). PROACTIVE USE: Also use this skill to extract the current conversation whenever something meaningful was discussed (technical decisions, debugging sessions, architecture changes, new learnings) or when the user switches to a different topic. When extracting conversations proactively, always run the ingestion in a background agent to avoid blocking the user.