Agent Skills

alloc-profile

✓★ 48,500

by clickhouse

Analyze a jemalloc (or other) allocation profile in collapsed stack format. Use when the user wants to analyze memory allocations, find top allocators, or…

🧰 Not standalone — use together with clickhouse/clickhouse

write-example

★ 48,500

by tldraw

Writing examples for the tldraw SDK examples app. Use when creating new examples, adding SDK demonstrations, or writing example code in apps/examples.

🧰 Not standalone — use together with tldraw/tldraw

cpu-profile

✓★ 48,500

by clickhouse

Profile a ClickHouse query using the sampling query profiler and system.trace_log. Use when the user wants to find CPU hotspots, analyze where time is spent in…

🧰 Not standalone — use together with clickhouse/clickhouse

clean-copy

★ 48,500

by tldraw

Reimplement the current branch on a new branch with a clean, narrative-quality git commit history. Use when asked to make a clean copy branch, clean up commit…

🧰 Not standalone — use together with tldraw/tldraw

commit-changes

★ 48,500

by tldraw

Create a git commit for the current changes. Use when asked to commit changes, make a commit, generate a commit message, or commit the current worktree with…

🧰 Not standalone — use together with tldraw/tldraw

pr-walkthrough

★ 48,500

by tldraw

Create a narrated video walkthrough of a pull request with code slides and audio narration. Use when asked to create a PR walkthrough, PR video, or walkthrough…

🧰 Not standalone — use together with tldraw/tldraw

review-docs

★ 48,500

by tldraw

Review and improve documentation with parallel evaluation and iterative improvement loop.

🧰 Not standalone — use together with tldraw/tldraw

shepherd-pr

★ 48,500

by tldraw

shepherd-pr — an installable skill for AI agents, published by tldraw/tldraw.

🧰 Not standalone — use together with tldraw/tldraw

skill-creator

★ 48,500

by tldraw

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI agent's…

🧰 Not standalone — use together with tldraw/tldraw

developing-with-streamlit

★ 45,100

by streamlit

**[REQUIRED]** Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, or optimizing Streamlit applications. Also required…

🧰 Not standalone — use together with streamlit/streamlit

fixing-flaky-e2e-tests

★ 45,100

by streamlit

Diagnose and fix flaky Playwright e2e tests. Use when tests fail intermittently, show timeout errors, have snapshot mismatches, or exhibit browser-specific…

🧰 Not standalone — use together with streamlit/streamlit

understanding-streamlit-architecture

★ 45,100

by streamlit

Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues,…

🧰 Not standalone — use together with streamlit/streamlit

addressing-pr-review-comments

★ 45,100

by streamlit

Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review comments and general PR (issue)…

🧰 Not standalone — use together with streamlit/streamlit

cell-architecture

✓★ 44,200

by sentry

Status : Active migration in progress. Migration-specific sections should be removed once complete, leaving a stable architecture reference.

🧰 Not standalone — use together with getsentry/sentry

Impeccable

★ 43,400

by pbakaus

This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.

🧰 Not standalone — use together with pbakaus/impeccable

impeccable

★ 43,400

by pbakaus

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts,...

🧰 Not standalone — use together with pbakaus/impeccable

auditing-experiments-flags

★ 35,300

by posthog

Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check,…

🧰 Not standalone — use together with posthog/posthog

diagnosing-failed-warehouse-syncs

★ 35,300

by posthog

Work top-down when a data warehouse source or table is failing, stuck, or producing bad data: source → schema → recovery action. Do not jump straight to "resync from scratch" — that discards synced data and restarts from zero, which is rarely the right first step.

🧰 Not standalone — use together with posthog/posthog

analyzing-experiment-session-replays

★ 35,300

by posthog

Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with…

🧰 Not standalone — use together with posthog/posthog

cleaning-up-stale-feature-flags

★ 35,300

by posthog

Identify and clean up stale feature flags in a PostHog project. Use when the user wants to find unused, fully rolled out, or abandoned feature flags, review…

🧰 Not standalone — use together with posthog/posthog

configuring-experiment-analytics

★ 35,300

by posthog

Guides experiment analytics configuration: exposure criteria, metric types, metric setup, and interpreting results. Covers who is included in the analysis, how…

🧰 Not standalone — use together with posthog/posthog

configuring-experiment-rollout

★ 35,300

by posthog

Guides rollout configuration for experiments: variant splits, overall rollout percentage, and the critical disambiguation when a user mentions a specific…

🧰 Not standalone — use together with posthog/posthog

creating-experiments

★ 35,300

by posthog

Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions…

🧰 Not standalone — use together with posthog/posthog

diagnosing-missing-recordings

★ 35,300

by posthog

When a user asks "why wasn't this session recorded?" or "why don't I have any recordings?", follow this workflow to systematically diagnose the cause.

🧰 Not standalone — use together with posthog/posthog

exploring-llm-clusters

★ 35,300

by posthog

Investigate LLM analytics clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into…

🧰 Not standalone — use together with posthog/posthog

managing-subscriptions

★ 35,300

by posthog

Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots. Use when the user wants to subscribe to an…

🧰 Not standalone — use together with posthog/posthog

react-doctor

★ 35,300

by posthog

Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.

🧰 Not standalone — use together with posthog/posthog

signals

★ 35,300

by posthog

How to query the document_embeddings table for signals data using HogQL. Read when you need to perform semantic search over signals, fetch signals for a report…

🧰 Not standalone — use together with posthog/posthog

survey-sdk-audit

★ 35,300

by posthog

Audit PostHog survey SDK features and version requirements

🧰 Not standalone — use together with posthog/posthog

tuning-incremental-sync-config

★ 35,300

by posthog

A sync's configuration lives on the ExternalDataSchema and can be changed any time via external-data-schemas-partial-update . Most changes are non-destructive (take effect on the next sync), but a few (switching sync_type, changing primary keys) require careful handling to avoid corrupting the synced data.

🧰 Not standalone — use together with posthog/posthog