Loading...
Loading...
Found 19 Skills
Use when the user's product is built (or nearly built) and they want to get it live and accessible to customers. Triggers on phrases like "create my launch checklist", "how do I deploy this", "help me launch", "get this live", "put this in production", "ship it to customers", "what do I need to do to go live", or any request for a step-by-step path from working code to a product customers can use. Audits the current codebase — stack, services, environment variables, payments, deploy config — then writes a plain-English, step-by-step launch guide to `docs/launch-checklist.md`. Every step is marked as something the user must do themselves, something their coding agent can do, or both together, and all technical terms are explained for non-technical founders.
Generates eval test cases from an eval suite plan (output of /eval-suite-planner) or a plain-English agent description. Supports both single-response and conversation (multi-turn) evaluation modes. Outputs a Copilot Studio test set table, a CSV file for import (single-response only), and a docx report for human review.
make a pull request with a plain-English title and a thematic summary built from the branch diff. Triggers: open a PR, create a pull request, submit a PR. Flags: --target <branch> (default main), --ticket <id> (prefix title with the ticket), --conventional (conventional-commit title).
SysWatch is a single-host system diagnostics TUI for macOS and Linux with twelve tabs, plain-English insights, and session scrubbing.
Prepares tax-season materials for small business owners — framed as deliverables for their accountant, not tax advice. Two modes: (1) quarterly estimated tax calculation — pulls YTD net income from QuickBooks and calculates the federal income tax + self-employment tax liability and quarterly payment due; (2) year-end 1099 prep — scans QuickBooks, PayPal, and Stripe for contractors paid over $600, builds a 1099-NEC candidate list with missing W-9 flags, and produces a plain-English summary a CPA can work from directly. Trigger this skill whenever the user mentions: quarterly taxes, estimated tax payment, how much to set aside for taxes, 1099s, 1099-NEC, year-end tax prep, contractor payments, W-9s, or any phrase suggesting they are preparing for a tax deadline or handing materials to an accountant. Also trigger proactively when a user asks about net profit or YTD income in a context that suggests they are worried about their tax bill.
Walks an SMB owner through month-end close: reconciles QuickBooks against PayPal (and Square/Stripe) settlements, flags uncategorized transactions, suspicious duplicates, and missing receipts, then writes a plain-English P&L narrative and exports a close packet (xlsx + one-page PDF). Use when the user says "close the month," "month-end," "reconcile," "what's missing," "P&L," or asks why revenue or margin changed this month.
Perform statistical hypothesis testing, regression analysis, ANOVA, and t-tests with plain-English interpretations and visualizations.
Transform CSV/Excel data into narrative reports with auto-generated insights, visualizations, and PDF export. Auto-detects patterns and creates plain-English summaries.
Author a working Claude Code hook from a plain-English description of what it should guarantee or do. You describe the behavior ("never let the agent edit my migrations", "don't stop until the tests pass", "log every command"); this skill picks the right lifecycle event, writes the hook script, and wires it into .claude/settings.json. Use when you want a deterministic guarantee or automation in your AI Layer and don't want to write the hook by hand. The meta-tool for the hooks primitive.
Use when the user is starting a new project or feature, or mentions "concept", "roadmap", "feature", "spec", "plan", "idea", or "what to build". Walks them through three plain-English phases — Concept (what & why) → Roadmap (the path) → Features (the work) — producing one-page markdown artifacts under `specdriven/` that anchor every later turn. Skip when the task is already small and well-scoped (a rename, a one-line bug fix).
Drive Blender from natural language. Converts plain-English requests ("model a sword and render it with cinematic lighting", "make this glass look frosted", "set up three-point lighting", "export this scene as glTF for the web") into Blender Python code executed via the Blender MCP server. Acts as the orchestrator that picks and chain-loads specialised sub-skills (blender-modeling, blender-materials, blender-lighting, blender-cameras, blender-rendering, blender-animation, blender-export, wireframe-to-3d, blender-pro-workflow, blender-skill-harmonizer, quality-refinement-autoloop). Use this skill whenever the user wants Claude to do anything in Blender, including creating geometry, applying materials, lighting a scene, framing a camera, rendering, animating, or exporting. Make sure to invoke this skill even if the user does not say "Blender" — also covers requests like "create a 3D model of...", "render this...", "make a glTF from...", "set up a scene with...", or any 3D-creation task. Requires the Blender MCP addon (ahujasid/blender-mcp) running on port 9876.
Use when an agent is asked to draft, rewrite, edit, review, polish, copyedit, simplify, humanize, or create written prose, including creative writing, essays, posts, scripts, speeches, emails, documentation, product copy, and other style-sensitive text. Apply George Orwell's six rules and ASD-STE100 Simplified Technical English as a plain-English discipline while preserving the user's intended meaning, audience, tone, and explicit constraints.