vishalsachdev

Load for ANY bug-fix task — code, UI/UX, content, docs, accessibility, or workflow. Reproduce → isolate → fix → prevent cycle with real-session patterns. GEPA-evolved from 353 real Claude Code session bugfixes (+31pp holdout).

Generate Canvas-ready HTML pages and assignments for BADM 350 Technology & AI Strategy course. Use when building weekly module content from markdown lesson plans, creating "Start Here" pages with Tuesday/Thursday session structure, or generating assignment HTML with rubrics. Triggers on requests to "build Canvas content", "create week X page", or "generate assignment for BADM 350".

This skill generates a structured chapter outline for intelligent textbooks by analyzing course descriptions, learning graphs, and concept dependencies. Use this skill after the learning graph has been created and before generating chapter content, to design an optimal chapter structure that respects concept dependencies and distributes content evenly across 6-20 chapters.

This skill generates comprehensive metrics reports for intelligent textbooks built with MkDocs Material, analyzing chapters, concepts, glossary terms, FAQs, quiz questions, diagrams, equations, MicroSims, word counts, and links. Use this skill when working with an intelligent textbook project that needs quantitative analysis of its content, typically after significant content development or for project status reporting. The skill creates two markdown files - book-metrics.md with overall statistics and chapter-metrics.md with per-chapter breakdowns - in the docs/learning-graph/ directory.

This skill generates interactive Chart.js bubble chart visualizations for priority matrices and multi-dimensional data analysis. Use this skill when users need to create scatter plots with variable bubble sizes, particularly for 2x2 priority matrices (Impact vs Effort, Risk vs Value, etc.), portfolio analysis, or any visualization comparing items across two dimensions with a third dimension represented by size. The skill creates a complete MicroSim package with HTML, CSS, and documentation.

This skill generates comprehensive chapter content for intelligent textbooks after the book-chapter-generator skill has created the chapter structure. Use this skill when a chapter index.md file exists with title, summary, and concept list, and detailed educational content needs to be generated at the appropriate reading level with rich non-text elements including diagrams, infographics, and MicroSims. (project, gitignored)

This skill generates interactive Chart.js visualizations for use in iframes using any chart type supported by the library (line, bar, pie, doughnut, radar, polar area, bubble, scatter). Use this skill when users need to create data visualizations for educational content, reports, or dashboards. The skill creates complete MicroSim packages with HTML, CSS, and documentation.

Apply the codebase singularity approach: reliable codebase understanding and change with a repeatable workflow, guardrails, and verification gates. Use for repo work (feature, bugfix, refactor, migration) when you need high trust, minimal diffs, and explicit validation and exit criteria.

Convene a 3-model council (Claude + GPT via codex CLI + Gemini CLI) on a high-stakes decision. Forces cross-critique between members and surfaces where they actually disagree, breaking Claude's default agreeableness. Use when the user asks to "convene a council", "get a second opinion", "ask GPT and Gemini", "what would other models say", or has an architecture / strategy / hiring / pricing decision where being wrong is expensive. Skip for factual questions, code with one right answer, or anything premortem-shaped (route to premortem skill instead).

Architect, execute, and iterate on AI evaluations using the Data-Task-Score framework. Treats evals as the modern, quantifiable version of a PRD. Use when the user asks to "build an eval," "improve model quality," "test an agent workflow," "quantify product intuition," "move beyond vibe checks," "measure AI output," "score LLM responses," "benchmark a prompt," or "set up evaluation infrastructure." Also triggers on phrases like "how do I know if this is working," "is the model getting better," or "eval-driven development."

Design and install validation hooks for coding agents (e.g., Claude Code) to make AI changes safer and more deterministic. Use when you want post-tool-use or stop hooks, automated tests/linters/formatters, parallel subagents with per-file validation, or a repeatable “agent pipeline” with audit logs.

Apply the codebase singularity approach: reliable codebase understanding and change with a repeatable workflow, guardrails, and verification gates. Use for repo work (feature, bugfix, refactor, migration) when you need high trust, minimal diffs, and explicit validation and exit criteria.

Use when user says "let's get started", "where are we", or at beginning of a session. Reads project context from CLAUDE.md, checks git status and recent commits, and provides orientation for the session. Works across all repo types (code, research, mixed).

Extract tweet series from X/Twitter profiles with full content, links, and engagement metrics. Use when: (1) User provides a tweet URL and wants similar tweets by the same author, (2) User asks to "extract tweets", "collect tweet series", or "scrape tweets", (3) User wants to analyze a user's recurring tweet format (e.g., daily updates, weekly roundups), (4) User needs tweet content with embedded links preserved for analysis. Requires Chrome browser automation tools (mcp__claude-in-chrome__*).

Use when user says "let's wrap up", "close shop", "done for today", or wants to end a session. Handles session wrap-up including git operations, documentation updates, roadmap updates, and preparing for next session. Works across all repo types.

Run a premortem on a plan, launch, product, hire, strategy, or decision — assumes it failed 6 months from now and works backward to find every reason why, then produces a revised plan. Use when the user has a concrete plan or commitment with high cost-of-being-wrong and asks to "premortem", "stress test", "find blind spots", "poke holes", "what could kill this", or "what am I missing". Skip for vague ideas without a plan, simple feedback requests, factual questions, or already-irreversible decisions.

Accessibility audit and remediation for Canvas LMS courses. Scans content for WCAG violations, generates prioritized reports, guides fixes, and verifies remediation. Use when asked to "audit accessibility", "check WCAG compliance", "fix accessibility issues", or "run accessibility review".

Scaffold complete Canvas LMS course structures from specs, templates, or existing courses. Creates modules, pages, assignments, and discussions in bulk. Use when asked to "build a course", "scaffold modules", "create course structure", "set up a new course", or "copy course structure".

Learning designer quality check for Canvas LMS courses. Audits module structure, content completeness, publishing state, date consistency, and rubric coverage. Use when asked to "QC a course", "is this course ready", "pre-semester check", or "quality review".

Bulk grading workflows for Canvas LMS assignments using rubrics. Covers single grading, batch grading, and code execution strategies with safety-first dry runs.

Discussion forum facilitator for Canvas LMS. Helps students and educators browse, read, reply to, and create discussion posts. Trigger phrases include "discussion posts", "reply to students", "check discussions", "forum participation", "post a discussion", or any discussion-related Canvas task.

Educator morning course health check for Canvas LMS. Shows submission rates, struggling students, grade distribution, and upcoming deadlines. Trigger phrases include "morning check", "course status", "how are my students", or any start-of-day teaching review.

Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger phrases include "peer review status", "how are peer reviews going", "who hasn't reviewed", "review quality", or any peer review follow-up task.

Student weekly assignment planner for Canvas LMS. Shows all due dates, submission status, grades, and peer reviews across all courses. Use when a student says "what's due", "plan my week", "weekly check", or wants to organize their coursework.

Design Canvas LMS assignments using evidence-based learning science principles from the Four Learning Design Pillars. Use when educators want to create pedagogically sound assignments, need help writing assignment descriptions with clear objectives, want rubric suggestions, or are creating quizzes/discussions/peer reviews. Integrates with canvas-mcp for direct Canvas creation.

Audit an entire Canvas LMS course against the Four Learning Design Pillars (Clear Structure, Active Content, Continuous Practice, Intuitive UX). Use when users want to evaluate course quality, identify improvement areas, or prepare for course redesign. Requires canvas-mcp server for course data access. Triggers on "audit course", "course review", "evaluate my course", or Canvas course IDs/codes.

Generate learning science-backed feedback templates for Canvas assignments. Use when educators need feedback templates for grading, want to create rubric comments, need encouraging feedback language aligned with Pillar 3 principles (targeted, encouraging, immediate), or want to set up SpeedGrader comment libraries. Works with canvas-mcp for bulk grading.

Generate a quick compliance checklist from the Four Learning Design Pillars. Use when users want a practical checklist for reviewing content, a quick audit tool, or verification questions for specific pillars.

Review educational content against the Four Learning Design Pillars framework. Use when users want to evaluate course materials, lessons, tutorials, e-learning modules, or any instructional content for alignment with evidence-based learning design principles. Provides structured feedback with specific principle references (e.g., 1.1.1, 2.3.4) and actionable recommendations.

Estimate the value of a class action case for settlement and trial purposes. Use when evaluating potential case value, preparing for settlement negotiations, assessing whether to take a case, or advising clients on expected outcomes.

Analyze whether a case meets the requirements for class action certification under Federal Rule of Civil Procedure 23. Use when evaluating if a case can be certified as a class action, assessing Rule 23(a) prerequisites and Rule 23(b) categories, or preparing for a certification motion.

Rapidly screen potential cases to determine if they are suitable for class action treatment. Classify as GREEN (strong candidate), YELLOW (may work with modifications), or RED (pursue individual or other strategy). Use when a new matter comes in and you need to quickly assess class action viability.

Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.

Screen incoming NDAs and classify them as GREEN (standard), YELLOW (needs review), or RED (significant issues). Use when a new NDA comes in from sales or business development, when assessing NDA risk level, or when deciding whether an NDA needs full counsel review.

Weekly (normally Wednesday) preparation of welcome emails to parents of campers whose Illinois MakerLab summer camp starts the following Monday. Use when the user says "camp welcome emails", "send welcome emails", "welcome email for next week's camps", "prep Monday camp emails", or it's Wednesday during camp season and next week's camps need parent emails. Covers: refreshing FormBuilder registration data, building cross-verified per-session rosters (via the authoritative CODE_TO_SESSION mapping — never raw session-code inference), detecting all-day campers, resolving parent emails, drafting per-camp + combined all-day emails from canonical templates, and opening Outlook compose windows for human review/send. Project-specific to the makerlab repo.

End-to-end handling of an Illinois MakerLab summer-camp cancellation (and the waitlist backfill it triggers). Use when the user forwards a cancellation/ withdrawal request, a camp registration confirmation to be cancelled, or says "process this cancellation", "cancel this camper's camp", "refund this family", "handle this withdrawal", or "who's on the waitlist for the freed seat". Covers: parsing the request, computing the refund tier by REQUEST DATE, logging to data/cancellations.csv, drafting the Kip refund-authorization memo, the FormBuilder Cancel Registration (Chrome + SSO login handoff), refreshing the website availability badge, and offering the freed seat to a waitlister. Project-specific to the makerlab repo.

Add a new token to the VibeFunded dashboard. Use when user says "add token", "new token", "add project", or provides a GitHub Issue URL from the vibefunded repo with label "project-submission". Handles updating fetch_data.py, running verification, and updating documentation.