feedback-learning
Classify and record explicit corrective feedback without turning skills or instructions into append-only knowledge dumps.
⌘ K
Newest skills
1229 skills
digest
Generate a daily or weekly digest of activity across all connected sources. Use when catching up after time away, starting the day and wanting a summary of mentions and action items, or reviewing a week's decisions and document updates grouped by project.
release
Release vercel-plugin — run gates, bump version, generate artifacts, commit, and push. Use when asked to "release", "ship", "bump and push", or "cut a release".
author-contributions
Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.
standup
Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into yesterday/today/blockers, or structuring a few rough notes into a shareable update.
benchmark-testing
Create and launch benchmark test projects to exercise vercel-plugin skill injection across realistic scenarios. Sets up isolated directories, installs the plugin, and spawns WezTerm panes running Claude Code with crafted prompts.
research
Deep research on a given topic. Use for comprehensive topic exploration — technical subjects, market analysis, architecture deep-dives, competitive analysis, etc. Also use when the user asks to 'research', 'deep dive', 'investigate', or 'find out about' a topic that requires multi-source synthesis. You should run MULTIPLE subagents in parallel to explore multiple angles and topics.
incident-response
Run an incident response workflow — triage, communicate, and write postmortem. Trigger with "we have an incident", "production is down", an alert that needs severity assessment, a status update mid-incident, or when writing a blameless postmortem after resolution.
benchmark-e2e
End-to-end benchmark suite for vercel-plugin. Runs realistic projects through skill injection, launches dev servers, verifies everything works, analyzes conversation logs, and produces an improvement report for overnight self-improvement loops.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
council-review
Multi-model council review for diffs, pull requests, and risky changes — CRITICAL after non-trivial development. USE FOR: "review a diff or pull request", "bug hunt in recent edits", "multiple models inspect the same change independently", "cross-review or debate findings between models", "review after any non-trivial development phase". DO NOT USE FOR: "plan a new implementation", "write code without a review".
setup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
V3 Performance Optimization
Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.
inbox-search-issues
Search GitHub issues and PRs assigned to you, needing triage, or matching custom queries
code-review
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.
update-shop
Update an existing Vercel Shop storefront with newer template changes. Use when the user wants to check drift, plan an upgrade, or apply template updates to a project scaffolded from Vercel Shop.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
statistical-analysis
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.
shopify-graphql-reference
Integrate Shopify-validated Storefront or Customer Account GraphQL into Vercel Shop. Use after Shopify AI Toolkit has supplied and validated an API operation, or when adapting existing GraphQL to the template's operation placement, fragments, domain transforms, locale flow, cache role, invalidation, and route architecture.