build-agents
Default guidance for building AI agents. Use for generic requests to build, create, scaffold, design, architect, or implement an AI agent, agent app, tool-calling agent, durable agent, multi-agent system, or scheduled agent.
⌘ K
Newest skills
455 skills
harness-similarity
ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics, categorical agreement over 4 enums, jaccard over agent_topology). Unblocks ADR-151 §3.2 Recommender, §3.3 Drift Detection, §3.5 Plugin Compat. Pure-TS, no `@metaharness/*` dep — preserves ADR-150's four architectural constraints.
sweeper-fix
Implement a VS Code Sweeper fix spec — fetch the sweeper's agent-fixable review record from its public state repo, implement the narrow fix in the current vscode checkout, and — after showing the diff — open a draft PR. Use ONLY when the request explicitly asks for the sweeper — "sweeper-fix", "sweeper", "vscodesweeper", a sweeper record, or a sweeper fix spec. Do NOT use for a plain "fix this issue" request that doesn't mention the sweeper; fix those directly with your normal tools instead.
incident-sitrep
Post a sitrep (situation report) for a live incident, in its incident channel: a short update in a fixed layout for people who have not read the whole channel — the current picture and what moved since the previous update, nothing more. Use on "sitrep", "status update", "where are we", "what's the latest", "catch me up", "summarize the incident so far", "update for leadership / support / customers", or when asked to keep posting one on a schedule ("post a sitrep every hour until this is resolved"); also when the oncall memory sets an update cadence for incidents of this severity and the person
ai-sdk
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
harness-mint
Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.
vercel-plugin-eval
Run live eval sessions against the vercel-plugin to verify hook behavior, skill injection, dedup correctness, and coverage. Launches real Claude Code sessions via WezTerm, monitors debug logs, and produces a structured coverage report.
harness-gepa
Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript. The `gepaOptimize` loop itself is library-only (bring your own evaluator) and not surfaced here — use `harness-evolve` for sandbox-scored evolution. Degrades gracefully when @metaharness/darwin is absent.
policy-and-managed-settings
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.
session-report
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
plugin-audit
Audit vercel-plugin performance on real-world projects. Extracts tool calls from Claude Code conversation logs, tests hook matching against actual inputs, identifies pattern coverage gaps, and checks plugin cache staleness. Use when asked to audit, test, or investigate plugin skill injection on a real project.
harness-genome
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
customizations-in-the-agent-host
Architecture and hard-won debugging lessons for customization enablement (plugins, MCP servers, agents, skills, instructions) in the agent host. Use when changing how customizations are discovered, published, enabled/disabled, or handed to a provider SDK; when a customization shows the wrong enabled state in the UI; or when a disabled MCP server or plugin is still reaching the model.
receipts
Generate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for justifying Claude Code usage/spend to a manager, self-review, or "what have I been using this for" check-ins. Mines ~/.claude/projects locally (no extra API calls beyond one final write-up), cross-references local git history, and writes a markdown report plus a self-contained HTML receipt to your home directory. Use when the user asks for "receipts", an "impact report", "usage report", wants to "show my Claude Code activity", "prove the value of Claude Code", or runs `/receip
benchmark-sandbox
Run vercel-plugin eval scenarios in Vercel Sandboxes instead of local WezTerm panels. Provisions ephemeral microVMs with Claude Code + plugin pre-installed, runs benchmark prompts, extracts hook artifacts, and produces coverage reports.
code-oss-logs
Find and read timestamped process logs from Code OSS dev builds, including main.log, renderer.log, extension host logs, and agenthost.log. For bundles produced by Export Agent Host Debug Logs, use agent-host-logs.
project-artifact
Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks & open questions, and decisions/FAQ when they earn a tab) — published with the built-in Artifact tool to a default-private claude.ai page the user can share with teammates. Use when a piece of work spans several workstreams and you want a shareable overview kept current. Each artifact is backed by a small per-project config in the plugin data dir, so refreshing it re-gathers live
benchmark-agents
Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow SDK, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration. Designed to stress-test skill injection for complex, multi-system builds.
chat-customizations-editor
Use when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.
skill-development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.