Loading...
Loading...
Found 9,218 Skills
Use when installing or configuring OpenClaw with DingTalk, Feishu, Discord, and additional channels with Bailian/DashScope models on Linux hosts. Use when provisioning a new OpenClaw node, troubleshooting gateway/channel startup, standardizing openclaw.json mapping, or automatically discovering extra channels from https://docs.openclaw.ai/channels.
Explicit child skill for extracting reusable improvements from real Ghidra work, resolving overlap, and promoting tracked assets when one task provides complete evidence.
Use when starting a new feature branch, creating isolated development environments, or working on multiple tasks simultaneously without stashing or switching branches. Triggers: user says "worktree", "new branch for work", "parallel development", "isolated environment", needs to work on two things at once.
하네스 시스템 안내 전문가. "어떤 스킬", "어떻게", "도움말", "help", "가이드", "어디서 시작" 키워드로 트리거. 스킬 추천, 워크플로우 안내, 시스템 개념 설명을 제공하는 읽기전용 온보딩 스킬. (skills.sh 글로벌 설치 안내 포함)
Bootstrap a new thread from a goal, allocate a stable slug-tNN thread id, initialize thread files from templates, and honor env-driven defaults for thread creation.
Create a new runbook with guided assistance. A runbook is a structured markdown document that tells a coding agent how to accomplish a complex, multi-step task with evaluation loops and quality gates. Use this skill whenever the user wants to create, build, scaffold, or write a runbook — including 'create runbook', 'new runbook', 'build a runbook', 'make a runbook', 'runbook wizard', 'help me write a runbook', 'I need a runbook for...', 'automate this task with a runbook', or 'turn this into a runbook'. Also trigger when the user describes a multi-step agent task that would benefit from structured evaluation and iteration loops, even if they don't use the word 'runbook' — for example, 'I want to build an automated pipeline that evaluates its own output' or 'create a repeatable process with quality gates'.
Monitors TrueFoundry deployment rollouts after deploy/apply. Polls status, checks pod health and readiness, fetches logs on failure, and reports a final summary. Use after deploying or applying a manifest to track rollout progress.
CEO/Founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Adapted from gstack/plan-ceo-review (Garry Tan, MIT license).
Draft or update architecture documents under `easysdd/architecture/` — describe what a subsystem/module looks like currently, how it is divided, and how external interfaces operate, to provide pre-positioning input for subsequent feature-design. Information sources include code + user materials (oral accounts, scattered documents, compound deposits, existing decisions), and the output can be reverse-validated by anchoring to specific `file:line`. Two modes: new (draft a new architecture document from scratch), update (refresh an existing document based on the latest code status and new user materials). Single-target rule — only modify one document at a time. Trigger scenarios: user says "fill in an architecture doc", "draft an architecture document", "update the architecture directory", "write down the structure of this module", or when it is found that "something that should be in the architecture is missing" during the feature-design / feature-acceptance phase.
Shows a structured progress dashboard for an album with percentage complete per phase, blocking items, and status breakdown. Use for a quick visual overview of album progress.
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
Read-only Q&A mode — answers questions about the codebase, architecture, or any topic without modifying files. Use for research and exploration before making changes.