Trending Skills
The hottest skills gaining momentum in the community right now.
gitcrawl
by openclaw
"GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work."
graincrawl
by openclaw
"Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work."
slack
by openclaw
"Slack messaging workflows through OpenClaw's message tool."
memory
by lossless-claude
Run one lcm CLI command and show its output verbatim. Usage: /memory <command> [options]
code-review
by lossless-claude
Review code changes in the lcm repository. Use when asked to review a PR, diff, or code change. Encodes project-specific rules for the SQLite daemon, connection lifecycle, type safety, performance gates, test coverage, transactions, migrations, and error handling.
lcm-dogfood
by lossless-claude
Exercise a live lcm install (installed plugin, real summarizer, the user's own data) and report a scorecard. Usage: /lcm-dogfood [health capture import compact sensitive mcp integrity]
lcm-memory
by lossless-claude
Search and store lcm memory with the lcm CLI. Use before a code task in this project, before asking the user about something a past session may have settled, and when a durable insight (decision, preference, root-cause, pattern, gotcha, solution, workflow) surfaces.
voice-call
by openclaw
"Start voice calls via the OpenClaw voice-call plugin."
release-openclaw-announcement
by openclaw
"Draft or post OpenClaw beta, stable, or extended-stable Discord release announcements from changelog, tag, registry, and validation evidence. Use when announcing a release, release candidate, or asking what users should test after an OpenClaw release."
browser-automation
by openclaw
Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
release-openclaw-maintainer
by openclaw
"Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports."
qa-frontend
by PostHog
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review, "check my changes", CI debugging, or security audit; use qa-team, debugging-ci-failures, or security-audit instead. Runs in PR mode or local mode, plans adaptive browser and visual checks, drives browser MCP/tooling such as Playwright MCP or Chrome DevTools MCP, captures evidence, and applies only approved/narrow fixes.
release-openclaw-plugin-testing
by openclaw
Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.
control-ui-e2e
by openclaw
Control UI browser tests, visual reviews and recordings, interaction performance audits, and Run Inspector evidence.
1k-retrospective
by OneKeyHQ
Analyze accumulated bug fix cases and propose updates to the self-testing checklist. Use periodically (weekly/monthly) to evolve quality checks based on real issues.
writing-code-comments
by PostHog
Gates whether a code comment should exist and forces the ones that stay to explain why, not what. Use ALWAYS before writing or editing a comment in any language (Python, TypeScript, Go, Rust, SQL), and when reviewing a diff that adds comments. Removes the comment types that clutter the codebase: narration that restates the code, change-history and chat-context notes ("previously did X", "per PR #123", "AI:"), perishable measurements and current-state stamps ("~20 min build", "currently", "today"), commented-out code, and redundant docstrings. Keeps the ones that earn their place: a non-obvious why, a warning about a non-local consequence, a pointer to context a future reader can't reconstruct. Not for user-facing copy (see /writing-user-facing-copy) or commit messages.
1k-defi-module-integration
by OneKeyHQ
Implement and debug OneKey Earn, Borrow, Staking, and DeFi Portfolio flows, including protocol actions, approval, positions, settlement, and refresh.
1k-architecture
by OneKeyHQ
OneKey monorepo architecture, project structure, package relationships, and import hierarchy rules.
1k-analytics
by OneKeyHQ
OneKey analytics and server event tracking with LogToServer, logger scopes/scenes, and business metrics. Use for 埋点, analytics, or tracking events.
1k-state-management
by OneKeyHQ
Jotai state management patterns — atoms, globalAtom, contextAtom, and persistence.
1k-monitor-pr-ci
by OneKeyHQ
Monitor OneKey PR checks and review threads, fix failures, address comments, and continue until the PR is ready.
1k-coding-patterns
by OneKeyHQ
OneKey coding patterns for TypeScript, React, promises, date formatting, and error handling.
1k-sentry
by OneKeyHQ
Configure OneKey Sentry and filter events across desktop, mobile, web, and extension.
1k-startup-profile
by OneKeyHQ
"Deep startup profiling for OneKey mobile — per-module JS factory timings, HBC I/O/parse breakdown, per-segment timings. Gated behind the single env var ONEKEY_STARTUP_PROFILE=1. Zero overhead when disabled (default). Use when diagnosing cold-start regressions, sizing main.bundle parse cost, finding slow modules, measuring segment load, or auditing what a 1.7s require('./App') actually contains. Triggers on: startup profile, 启动性能分析, module timing, HBC parse time, segment timing, require cost, StartupProfile, ONEKEY_STARTUP_PROFILE, __d patcher, inline-requires."