Loading...
Loading...
Found 7 Skills
Generate interactive TiddlyWiki-style HTML software manuals with screenshots, API docs, and multi-level code examples. Use when creating user guides, software documentation, or API references. Triggers on "software manual", "user guide", "generate manual", "create docs".
Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.
Generate a fully working React + Vite app that explains a codebase's workflows, data types, and architecture through interactive visuals — click-to-step animated walkthroughs with auto-play, sequence diagrams, animated packet tracers, message inspectors that toggle between named-field view and raw JSON, and collapsible code peeks with file:line citations. Splits the repo into 4–6 domain clusters and dispatches one content agent per cluster to write the pages in parallel. The skill bundles its own reference pages (under references/examples/) so it works in any repo. Use this skill whenever the user asks for interactive docs, animated explainers, an "agent team" for docs, one page per domain, wants to visualize a system's request flow or wire protocol, or any visual documentation site. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in .claude/settings.json.
Use when asked to explain visually with a code walkthrough.
Use when bootstrapping a new team AI directives repo, establishing team-wide principles for the first time, or amending the constitution in team-ai-directives.
Shows, copies or rebuilds scrolls-explainer.html: an interactive, offline page that explains how the scrolls skill family works (/scrolls-setup, /scrolls-update, /scrolls-hide, /scrolls-unhide, /scrolls-remove, /scrolls-restore, /scrolls-help) — one tab per command that animates, step by step, what the command does to docs/.scrolls/, SCROLLS.md, CLAUDE.md, AGENTS.md and git, with a callout explaining each step, a tab for how a new agent session reads the memory, and full keyboard navigation (arrows step, [ ] or digits switch tabs, Space pauses, ? lists shortcuts). Use this whenever the user runs /scrolls-explainer, or asks for a visual, diagram, animation, walkthrough, explainer or interactive page of how the scrolls commands or the scrolls memory work, or wants something to show a team. By default (same as --show) it opens the bundled page in place and copies nothing; -o/--output copies it to a file or folder (-o . for ./scrolls-explainer.html), -f/--force overwrites with -o, --open opens the copy, and --build to regenerate the bundled page from the scrolls-* skills as they are now (their tabs, lockstep version, and a review check when a SKILL.md changed). Works on macOS, Linux, and Windows (bash or PowerShell).
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, replacing, or archiving them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, or when pattern docs no longer reflect current code.