Continuous performance optimization from Datadog, Prometheus or imported data: p75 user journeys against targets, proxy benchmarks whose CI ceilings only move down, a change ledger with measured effects, a dashboard Artifact and an optional blog-style write-up.
Plugin speedup from marketplace 10x-agent-marketplace in jacquelineadean/10x-agent-marketplace. Commands read from the repo's manifest — yesterday.
measurePull the latest p75 values for every journey from Datadog, Prometheus or files, rebuild the performance dashboard, and flag regressions with likely suspects. Use for a daily or on-demand performance check, "did anything get slower", "how fast are we now", or as the scheduled step of continuous optim
optimizeRun one optimization cycle on the slowest user journey: find the hot path, build a deterministic proxy benchmark, make the change, prove it with before and after numbers, guard it with a CI ceiling that only moves down, and log it for the dashboard. Use when someone asks to make the app faster, fix
reportPublish the performance dashboard as a private claude.ai Artifact (overall speedup, journeys against targets, change ledger with measured effects, guardrail ceilings) and optionally write a blog-style post of every step taken, with each number filled in from the data. Use when someone wants a perfor
setupSet up continuous performance work for an application: choose the user journeys to speed up from Datadog RUM, APM or Prometheus data, set p75 targets and a baseline, write perf/speedup.json, add the CI guardrail, and take the first measurement. Use when someone wants to start optimizing app performa
perf-gathererReads performance data for speedup journeys from a connected observability tool (the Datadog connector first, or another monitoring MCP server) and writes import files or a candidate list into a data folder. Use from the speedup setup and measure skills when no API keys are set, so raw tool output s
perf-writerWrites writeup.src.md, a blog-style post on how an application got faster, into a speedup data folder from digest.md and the write-up outline, with every number as a metrics token. Use after speedup report when the user asked for a write-up.
Interactive system and data design visuals and prototypes: technical architecture diagrams laid out in code, sequence diagrams and ERDs played step by step, pages with part details, pins and a step player, ERDs read live from Postgres or Oracle, Unity Catalog lineage, clickable prototype screens fed by facts, and a solution visualizer that simulates approaches to a design question across scenarios before one is implemented.
3 skills · 1 agent
Illustrated, interactive story pages (Artifacts) designed for their subject, and painted or drawn animations in the same style: status stories, launches, onboarding handbooks, field guides with rigged animals, map tours and rooms, gamified training and podcast companions, from a brief, the material a researcher digests, and company facts through the sources plugin.
2 skills · 1 agent
Token optimization for Claude Code: audits session transcripts, applies low-risk reversible fixes, recommends model, workflow and instruction changes with evidence, guards against retry loops and writes handoff files.
2 skills · hooks
Slide decks and KPI dashboards from facts as Artifacts: 16:9 slides with builds, notes and stepped animations, and dashboards with targets, status by rule, filters and the query behind every number; a brand kit, refresh with no model call, and exports to claude.ai Slides and Dashboard, Google Drive, Microsoft 365, PDF and PNG.
2 skills
Pull request descriptions a reviewer can approve fast (template, Playwright screenshots and recordings, GitHub advanced formatting), branch names and Conventional Commit messages, deferring to each repo's own rules.
2 skills
Turn GitHub activity for one person, a team, an organization or an enterprise, over any timeframe, into metrics, a dashboard, a rubric-based review, highlight bullets and STAR stories.
1 skill · 1 agent
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.