Prepare a weekly work review
Summarize completed work, blockers, and next decisions from a bounded evidence set.
Browse reusable instructions for your AI tools. Copy and customize a prompt, or download a skill for a supported agent.

Summarize completed work, blockers, and next decisions from a bounded evidence set.
Identify stale or conflicting instructions in a selected document set without silently rewriting them.
Assess inputs, failure modes, reversibility, and verification before creating a recurring workflow.
Convert a failed tool call into evidence, bounded recovery options, and an honest task status.
Summarize a task's objective, decisions, evidence, and remaining work for continuation.
Review skill metadata, referenced files, and executable or external-action behavior without running it.
Review code changes for real bugs, edge cases, and actionable improvements.
Turn an ambitious project into a small, testable build plan.
Design tests around behavior, invariants, and plausible failures.
Synthesize supplied material with traceable claims, disagreements, and limitations.
Find actionable accessibility issues in supplied markup, styles, and user flows.
Improve a prompt's goal, context, constraints, and output requirements.
Organize an OpenClaw workspace around clear, reusable instructions and discoverable skills.
Build a concise daily brief from the sources your OpenClaw agent is already allowed to read.
Diagnose why an OpenClaw skill is missing, overridden, or not being discovered.
Map a repository for Codex before starting a substantial change.
Give Claude Code a focused review workflow for an existing diff.
Review a UI component in Cursor for state coverage, semantics, and responsive behavior.
Investigate failures with evidence, ranked hypotheses, and a minimal regression-tested fix.
Check API contracts for consistent resources, ownership, validation, and failure behavior.
Plan a migration with compatibility checks, verification, and a recovery path.
Write task-focused documentation grounded in the actual product and code.
Edit for clarity, structure, and voice while preserving supplied facts.
Inspect dataset structure, missingness, duplication, and validity before analysis.
Try another platform, a broader search, or fewer filters.
Explore all resourcesResource formats: Prompts are ready to copy into a conversation. Skills install into the compatible agent shown on their page.
How it worksInclude the instructions, intended platforms, author, and license. Submissions are reviewed before publication.