Loading...
Loading...
Found 11,070 Skills
Review a skill and extract deterministic, mechanical steps into shell scripts. Makes skills more reliable by separating precision work (scripts) from judgment work (AI). Use when asked to extract scripts from a skill, make a skill more deterministic, or split a skill into script + prompt.
Critique-and-rewrite enforcement loop for voice fidelity. Validates generated content against negative prompt checklists and forces revision until it passes. Use when content has been generated in a target voice, voice output feels off, long-form content risks voice drift, or before final delivery of voice content. Use for "validate voice", "check voice", "voice feels wrong", "voice drift", or "rewrite for voice". Do NOT use for initial voice generation, voice profile creation, or content that has no voice target.
Merge validated feature to main via PR, tag release, cleanup worktree. Use after /feature-validate passes. Use for "release feature", "merge feature", "ship it", or "/feature-release". Do NOT use without passing validation or for hotfixes that skip the pipeline.
Initialize a .spec-driven/ directory in a project. Creates config.yaml and specs/ scaffold, then guides the user to fill in project context.
Modify an existing spec-driven change artifact (proposal.md, specs/ delta files, design.md, tasks.md, or questions.md). Preserves completed task state.
Saleor e-commerce API patterns for building storefronts. Use when working with Saleor's GraphQL API, products, variants, checkout, channels, permissions, or debugging API behavior. Framework-agnostic — applies to any Saleor storefront.
This skill should be used when the user asks to "execute this blueprint", "run the plan", "execute the plan", "start building from the plan", "implement the blueprint", "implement the plan", "continue the plan", "resume execution", or "execute 01_milestone_name.md".
Run Codex code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Task-based multi-agent coordination (includes Issue Remediation Loop)
Use before any non-instant feature work, refactor, behavior change, or requirements-shaping conversation where user intent is not yet locked. Extracts and confirms the decisions that planning will depend on, especially when the user knows what they want but has not fully thought through edge cases, scope boundaries, or expected behavior. Output is CONTEXT.md.
Use the emergent-thinking CLI to persist project-local requirements, plans, decisions, and thought trails across Codex or Claude Code sessions.
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.