dglabs-deepclaw
github.com/deepgram/dglabs-deepclaw
| Skill | Added | Review |
|---|---|---|
merge-pr .agents/skills/merge-pr/SKILL.md Merge a GitHub PR via squash after /preparepr. Use when asked to merge a ready PR. Do not push to main or modify code. Ensure the PR ends in MERGED state and clean up worktrees after success. | 68 68 Impact — No eval scenarios have been run Securityby  Low Low-risk findings worth noting Version: ec8d4f8 | |
model-usage skills/model-usage/SKILL.md Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON. | 68 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: ec8d4f8 | |
nano-banana-pro skills/nano-banana-pro/SKILL.md Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). | 72 72 7.23x Agent success vs baseline Impact 94% 7.23xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
nano-pdf skills/nano-pdf/SKILL.md Edit PDFs with natural-language instructions using the nano-pdf CLI. | 68 68 2.61x Agent success vs baseline Impact 81% 2.61xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
notion skills/notion/SKILL.md Notion API for creating and managing pages, databases, and blocks. | 67 67 1.57x Agent success vs baseline Impact 99% 1.57xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
obsidian skills/obsidian/SKILL.md Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli. | 68 68 2.12x Agent success vs baseline Impact 100% 2.12xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
openai-image-gen skills/openai-image-gen/SKILL.md Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: ec8d4f8 | |
openai-whisper skills/openai-whisper/SKILL.md Local speech-to-text with the Whisper CLI (no API key). | 76 76 0.91x Agent success vs baseline Impact 91% 0.91xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
openai-whisper-api skills/openai-whisper-api/SKILL.md Transcribe audio via OpenAI Audio Transcriptions API (Whisper). | 76 76 2.27x Agent success vs baseline Impact 91% 2.27xAverage score across 3 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: ec8d4f8 | |
openhue skills/openhue/SKILL.md Control Philips Hue lights/scenes via the OpenHue CLI. | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: ec8d4f8 | |
oracle skills/oracle/SKILL.md Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns). | 67 67 1.70x Agent success vs baseline Impact 99% 1.70xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
ordercli skills/ordercli/SKILL.md Foodora-only CLI for checking past orders and active order status (Deliveroo WIP). | 71 71 8.30x Agent success vs baseline Impact 83% 8.30xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
peekaboo skills/peekaboo/SKILL.md Capture and automate macOS UI with the Peekaboo CLI. | 56 56 1.92x Agent success vs baseline Impact 77% 1.92xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
prepare-pr .agents/skills/prepare-pr/SKILL.md Prepare a GitHub PR for merge by rebasing onto main, fixing review findings, running gates, committing fixes, and pushing to the PR head branch. Use after /reviewpr. Never merge or push to main. | 68 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: ec8d4f8 | |
prose extensions/open-prose/skills/prose/SKILL.md OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows. | 72 72 2.09x Agent success vs baseline Impact 92% 2.09xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
review-pr .agents/skills/review-pr/SKILL.md Review-only GitHub pull request analysis with the gh CLI. Use when asked to review a PR, provide structured feedback, or assess readiness to land. Do not merge, push, or make code changes you intend to keep. | 68 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: ec8d4f8 | |
sag skills/sag/SKILL.md ElevenLabs text-to-speech with mac-style say UX. | 67 67 3.50x Agent success vs baseline Impact 91% 3.50xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
session-logs skills/session-logs/SKILL.md Search and analyze your own session logs (older/parent conversations) using jq. | 69 69 1.91x Agent success vs baseline Impact 94% 1.91xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
sherpa-onnx-tts skills/sherpa-onnx-tts/SKILL.md Local text-to-speech via sherpa-onnx (offline, no cloud) | 50 50 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: ec8d4f8 | |
skill-creator skills/skill-creator/SKILL.md Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets. | 48 48 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: ec8d4f8 | |
slack skills/slack/SKILL.md Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs. | 85 85 3.84x Agent success vs baseline Impact 100% 3.84xAverage score across 3 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: ec8d4f8 | |
songsee skills/songsee/SKILL.md Generate spectrograms and feature-panel visualizations from audio with the songsee CLI. | 86 86 19.20x Agent success vs baseline Impact 96% 19.20xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: ec8d4f8 | |
sonoscli skills/sonoscli/SKILL.md Control Sonos speakers (discover/status/play/volume/group). | 61 61 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: ec8d4f8 | |
spotify-player skills/spotify-player/SKILL.md Terminal Spotify playback/search via spogo (preferred) or spotify_player. | 74 74 12.50x Agent success vs baseline Impact 100% 12.50xAverage score across 3 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: ec8d4f8 | |
summarize skills/summarize/SKILL.md Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”). | 86 86 3.44x Agent success vs baseline Impact 100% 3.44xAverage score across 3 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: ec8d4f8 |