Browse the skill radar
Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.
✨ Quick picks
🏷 Categories · coding-agents-and-ides
🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.
🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got.
📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.
⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.
🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.
Results
rotate-openrouter-key
Safely rotate the OpenRouter API key across all config files in an OpenClaw installation. Finds every location where the key is stored, updates them, restarts the gateway, and verifies the new key works. Use when asked to "rotate openrouter key", "change openrouter api key", "update openrouter key", or "replace openrouter key".
+ 1 more
2nd-brain
|
+ 1 more
audio-upload-aioz-stream
Quick upload audio to AIOZ Stream API. Create audio objects with default or custom encoding configurations, upload the file, complete the upload, then return the audio link to the user.
+ 1 more
claude-usage
Calculate Claude Max subscription usage from OpenClaw session data. Shows credits consumed, weekly budget percentage, 5-hour rate limit window, and per-session breakdown.
+ 1 more
context-budgeting
Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce token costs and latency for long-running tasks.
+ 1 more
cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction
Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation compression, and progressive context loading.
+ 1 more
deterministic-controller
Deterministic, evidence-gated controller templates for OpenClaw (HEARTBEAT/ACTIVITIES + sprint template + poll cron payload). Docs-only: installs no services and makes no config changes by itself.
+ 1 more
embedded-review
Expert code review for embedded/firmware projects with dual-model cross-review (Claude + Codex via ACP). Detects memory safety, interrupt hazards, RTOS pitfalls, hardware interface bugs, and C/C++ anti-patterns.
+ 1 more
fhir-questionnaire
Helps creating FHIR conforming questionnaire definitions from plain requirement ideation docs. Contains scripts to look up LOINC and SNOMED CT codes for medical conditions, findings, observations, medications, procedures from a official coding APIs. No API keys required at the moment.
+ 1 more
haqq-content-workbench
Create, verify, and package Islamic-ethics content for discussion. Use when the user asks for: (1) summarizing long texts, (2) checking sources/claims, (3) producing multiple post variants to avoid duplication, (4) generating discussion questions, or (5) archiving ideas for later publishing.
+ 1 more
interview-designer
Analyze resumes and design interview strategies using evidence-based methodology. Transforms interview prep from "read resume → ask questions" into "define standard → forensic evidence → future simulation". Combines Geoff Smart's Topgrading, Lou Adler's performance-based hiring, and Daniel Kahneman's bias control. Use when preparing for interviews, creating structured interview guides, or designing questions to validate candidate competencies.
+ 1 more
liblib-ai-gen
Generate images with Seedream4.5 and videos with Kling via LiblibAI API. Use when user asks to generate/create images, pictures, illustrations, or videos using LiblibAI, Seedream, or Kling models.
+ 1 more
model-matrix
Weighted model-routing matrix for OpenClaw (cost-aware, policy-aware, daily scorecard template).
+ 1 more
opc
OPC (One-Person Company) Framework - Complete AI agent system for solo entrepreneurs with 14 integrated skills. From ideation to deployment - creative planning, market research, proposal writing, PRD generation, development, testing, deployment, operations, and more.
+ 1 more
personal-ideas
Acts as the user's idea capture and brainstorm partner in the Ideas topic. Catches ideas, develops them, connects dots between past ideas. Use when in Personal chat Ideas topic, or when user mentions idea, thought, concept, brainstorm, startup, project idea, or "what if".
+ 1 more
tpm-copilot
AI-powered operating system for Technical Program Managers and Project Managers. Pulls data from Jira, Linear, GitHub, and calendars to auto-generate status reports, track risks and blockers, manage meeting workflows, map dependencies, and deliver stakeholder dashboards. Use when: (1) generating status reports or program updates, (2) tracking risks, blockers, or stale tickets, (3) preparing meeting agendas or extracting action items, (4) mapping cross-team dependencies, (5) creating stakeholder dashboards, (6) monitoring sprint health or velocity, (7) writing executive summaries, or (8) automating any TPM/PM workflow.
+ 1 more
video-upload-aioz-stream
Quick upload video to AIOZ Stream API. Create video objects with default or custom encoding configurations, upload the file, complete the upload, then return the video link to the user.
+ 1 more
visual-prompt-engine
Generate diverse, non-repetitive image prompts powered by real visual references from Dribbble and design platforms. USE WHEN: user wants an image prompt, needs creative visual inspiration, asks for design-informed prompts, wants to avoid repetitive AI image generation, or says 'generate a prompt for an image', 'give me a creative image idea', 'make me a unique visual prompt'. DON'T USE WHEN: user wants to generate the image itself (use an image generation tool), wants to edit an existing image, or needs text-only content. EDGE CASES: 'make me an image' → use image generation tool, then optionally this skill for the prompt. 'improve this image prompt' → this skill. 'I keep getting similar AI images' → this skill (solves repetition).
+ 1 more
wip-file-guard
Hook that blocks destructive edits to protected identity files. For Claude Code CLI and OpenClaw.
+ 1 more
ai-notes-ofvideo
Generate AI-powered notes from videos (document, outline, or graphic-text formats)
+ 1 more
approve-pairing
Approve a pending DM pairing request without the openclaw CLI, by directly editing credential files. Use when `openclaw pairing approve` is unavailable (CLI not in PATH, elevated access not configured, sandbox environment). Supports telegram, whatsapp, signal, imessage, discord, slack, feishu.
+ 1 more
arxiv-osiris
Search and download research papers from arXiv.org - Research version for OpenClaw agents
+ 1 more
asura
Krump Knowledge and Personality Identity — embodies Asura's legacy, lineage, and technical expertise
+ 1 more
calendar
Calendar management and scheduling. Create events, manage meetings, and sync across calendar providers.