verification-loops
Verification Loops are systematic evaluation pipelines that validate agent outputs at every stage of execution.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-22 00:12
259,203 results
Verification Loops are systematic evaluation pipelines that validate agent outputs at every stage of execution.
Web Asset Generation automates the creation of favicons, PWA icons, Open Graph images, social media meta tags, and Apple touch icons from a single source image…
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting…
Molecular biology toolkit: sequence manipulation, FASTA/GenBank/PDB I/O, NCBI Entrez, BLAST automation, pairwise/MSA alignment, Bio.PDB, phylogenetic trees.…
Deep OWASP API Security Top 10 testing for REST, GraphQL, gRPC, and WebSocket APIs — BFLA, mass assignment, rate limiting, and unsafe consumption.
Remove the AI flavor from Chinese text so it reads like it was written by a real person. Use when editing, reviewing, or rewriting Chinese content. Based on a Chinese-localized version of blader/humanizer (Wikipedia "Signs of AI writing"), combined with Chinese community discussions and AIGC detection research (CCL 2023…
Verify citations and references in scientific documents to detect hallucinated or invalid sources. Extracts DOIs, URLs, arXiv IDs, PubMed IDs, and ISBNs from…
When touching existing code and wanting to leave it better. Use when the user says "clean this up while I'm here," "should I fix this," "tech debt," "while I'm…
WordPress site and codebase onboarding review. Use when inheriting a WordPress repo, auditing an unfamiliar site or project, scoping technical risk before…
This skill should be used to retroactively record an architectural decision that was made in the past but never written up as an ADR — typically surfaced by a…
Comprehensive Modal.com platform knowledge covering all features, pricing, and best practices
Create or improve concise, useful, agent-safe repository READMEs. Use for new README drafts, rewrites, quickstarts, local setup, getting started, contributor…
Map unfamiliar code one layer up: modules, callers, callees, entrypoints, boundaries, dependencies, and data flow. Trigger on zoom out, call graph, module map,…
Download and transcribe videos from YouTube, Bilibili, TikTok and 1000+ platforms. Use when user requests video download, transcription (转录/字幕提取), or…
Track upcoming catalysts for A-share coverage universe — earnings dates, regulatory announcements, sector conferences, product launches, and policy events…
Design or refine springs, gestures, and interruptible motion when physical continuity or direct manipulation matters.
Audit one or more existing Kestra flows and add production-hardening controls — retries, timeouts, concurrency limits, error/finally/afterExecution handlers,…
Netra MCP trace-debugging workflow focused on query_traces, get_trace_by_id, and get_session_details, including exact input parameters, filter schema,…
Guide a visible, verified code walkthrough in Neovim with Terminal Control and Navi, optionally recording the presentation with OBS or retaining terminal…
Use when: A requirement change occurs during a project, the change impact scope and risks need to be assessed, and the change history needs to be recorded Do NOT use when: The change is extremely minor and requires no formal assessment, or the change already has a clear decision and requires no analysis
Use when: after the technical solution is determined, multi-department collaboration is involved, the collaboration process and division of responsibilities need to be clarified, and cross-team communication is difficult Do NOT use when: a single team completes it independently, or the collaboration relationships are already clear and do not need to be sorted out
Use when: Need to design product data metrics, plan data tracking, establish a data monitoring system, conduct data analysis and trend forecasting Do NOT use when: Data metrics are already clear, only simple statistics are needed and no metric system is required
Use when: managing multiple product lines requires portfolio decisions, BCG matrix analysis, product life cycle assessment, and resource allocation Do NOT use when: a single product does not require portfolio management, or the product line is already fixed and does not need adjustment
Use when: risk control is complete and you are preparing for release, need to create a go-live checklist and rollback plan, or are following the formal release process Do NOT use when: the go-live process is already standardized and executed automatically by operations, or only a simple release is needed without a checklist