Operational gotchas and references for third-party integrations driven from Claude Code — Cloudflare Workers, Grafana, Notion, OpenPencil, Playwright, and MCP file transport.
Plugin integrations from marketplace claude-skills in cajias/claude-skills. Commands read from the repo's manifest — 1 month ago.
grafana-dashboard-datasource-uid-mismatchFix for Grafana dashboard panels silently showing "No data" even though Prometheus (or any other datasource) has the data and the same query works in Prometheus's own UI. Use when: (1) a freshly-imported or provisioned Grafana dashboard shows "No data" on every panel; (2) the metric exists in Promet
mcp-file-upload-base64-transport-limitWhy you cannot upload a real file (>~15 KB) through content-MCP tools that take base64 inline — Google Drive `create_file`, similar Notion/media MCPs — and what to do instead. Use when: (1) `create_file` (or any MCP upload) fails with "Request contains an invalid argument" on a .pptx/.pdf/.png/.zip;
notion-publish-generated-markdownGotchas when publishing AI/subagent-drafted Notion-flavored markdown via the Notion MCP (notion-create-pages / notion-update-page) — especially design-phase artifacts with callouts, <table> blocks, and mermaid diagrams. Use when: (1) a published Notion page shows literal "<callout" / "<table"
openpencil-mcp-gotchasOperational gotchas + recovery for driving the OpenPencil design editor through its MCP server (open-pencil / openpencil-mcp; the mcp__open-pencil__* tools — render, export_image, export_svg, set_image_fill, set_layout_child, set_font_range, new_document, save_file). Use when: (1) export_image retur
playwright-mcp-singleton-lock-workaroundWorkaround for "Browser is already in use for .../mcp-chrome-..., use --isolated to run multiple instances of the same browser" error from Playwright MCP. Use when: (1) You need to run browser automation but another teammate/session is already holding the Playwright MCP Chrome instance, (2) `mcp__pl
workers-best-practicesReviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards
wranglerCloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudfl
Hard-won gotchas from authoring and distributing Claude Code plugins, skills, hooks, and Workflow scripts. Bundles APM packaging traps, plugin cache and marketplace path failures, hook main-vs-subagent detection, Workflow meta parsing breaks, and orchestration verification playbooks.
16 skills
AIDE²-style recursive self-improvement loop: an outer agent iteratively rewrites an inner tree-search research agent, keeping a rewrite only when it beats the incumbent on private held-out scores under a fixed budget across an optimization / ML-engineering / harness-engineering battery. Standalone /rsi:autoresearch solves tasks by tree search; /rsi:init + /rsi:step + /rsi:run drive the outer loop.
2 skills · 6 commands · 2 agents · hooks
Design-and-build process skills: layered design docs, C4 architecture artifacts, Diataxis documentation, README authoring, a milestone execution harness, milestone goal-prompt generation, positive-framing spec guidance, and a schema drift playbook.
8 skills
Hard-won gotchas from real git and gh workflows: PR create/merge quirks, worktree races, rebase in non-interactive shells, squash-merge diagnosis, and deadlock recovery via plumbing.
6 skills
Hard-won gotchas from CI pipelines and build environments: GitHub Actions, Copilot CLI headless runs, cron block generation, Docker on Apple Silicon, and TypeScript monorepo scaffolding.
5 skills
Hard-won gotchas from the Python toolchain: importlib class identity, pip/PyPI name collisions, mock.patch.object vs __slots__, ruff on notebooks, and uv in fresh worktrees.
5 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · 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
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
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.