diff auditor
by Shippers
AI coding agents routinely return a diff that answers a slightly different question than the one asked — extra scope, mi
New: Skill bounties are live. Post a request, fund the bounty, and creators compete for 7 days to build it -> See open bounties
THE AGENSI STORE
484 skills found
by Shippers
AI coding agents routinely return a diff that answers a slightly different question than the one asked — extra scope, mi
by Nex AI
Generate production-grade, idempotent FastAPI webhook handlers with signature verification and audit logging.
by Vivek K
Turn a research question into a decision-ready report with source grades, claim-to-source mapping, contradictions, and confidence levels.
by YK
Eliminate technical debt by enforcing a single source of truth for schemas, types, and constants across the stack.
by heyhridyansh
Diagnose tool-calling failures, schema mismatches, and unsafe agentic workflows with a structured audit framework.
by heyhridyansh
Detects mismatches between API specifications, code implementations, and client expectations to prevent breaking changes.
by Ahmed Rehan
Design-system work inside your agent via the Penpot MCP server.
by heyhridyansh
Audit monorepo architecture for circular dependencies, forbidden imports, and package boundary violations.
by Vivek K
Checks whether a React or Next.js site is ready to launch — scores 8 areas, lists what to fix first, and gives a clear SHIP, FIX-FIRST, or BLOCK decision.
by heyhridyansh
Production-grade reliability and security audit for inbound and outbound webhook integrations.
by Jose Luis
An MCP-powered skill to check real-time flight availability, prices, and airline details between airport codes.
by PromptWagon
Builds grant application narratives, eligibility responses, project summaries, needs statements, project plans, budget notes, impact statements, evaluation plans, funder-alignment notes, evidence prompts, review checklists, and submission-readiness packs for nonprofits, creators, researchers, social enterprises, community groups, educators, and small businesses seeking funding.
by 0m3rexe
Architectural advisor for designing independently deployable microservices based on Sam Newman's principles.
by heyhridyansh
Diagnose RAG hallucinations, retrieval failures, and citation errors with a structured root-cause audit.
by Nex AI
End-to-end domain migration and rebranding for web projects, including DNS, OAuth, and codebase updates.
by Ilya Demidov
⚠️ Attention. This is 1 of 6 skills that cover the entire product build lifecycle. Feel free to download other OptiTech skills to build your production-ready products.
by Vivek K
Designs a production-grade MCP server: atomic tools, full contracts, risk classes, approval gates, idempotency, discoverability, and a READY-TO-IMPLEMENT / HARDEN-FIRST / BLOCK verdict — without deploying anything.
by Vivek K
Designs a scored eval suite for an AI agent or SKILL.md skill, measures trigger accuracy, catches regressions against a baseline, and issues a PASS / PASS-WITH-WARNINGS / FAIL release gate.
by Vivek K
Finds why an app bug is happening using a step-by-step method (reproduce, isolate, test ideas, 5 Whys), then gives a small correct fix and a regression test — without guessing first.
by Vivek K
Turn messy CI/CD, Docker, and Kubernetes failure logs into an evidence-backed Root Cause Analysis and a safe, human-run recovery plan.
by PromptWagon
Turns project outcomes, metrics, activities, beneficiary stories, case notes, delivery evidence, evaluation findings, photos captions, lessons learned, and future plans into polished impact reports, funder updates, stakeholder summaries, annual review sections, board-ready impact notes, and donor-friendly communication packs for charities, social enterprises, educators, community groups, and funded projects.
by tamim boy
A systematic diagnostic framework for debugging AI pipelines, prompt drift, RAG failures, and agent orchestrations.
by tamim boy
Conducts structured 5-layer competitive intelligence for AI companies, models, and technical products.
by Jiangdongbo
Transforms vague, one-liner requests into structured, professional-grade AI prompts.