migration guard
by J. Shtal
Catches the database migrations that lock tables or lose data — before they hit production.
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
161 skills found
by J. Shtal
Catches the database migrations that lock tables or lose data — before they hit production.
by SkillForge
Enforce senior-level architectural thinking by making your agent write a 5-line Design Note before coding.
by Adis Cengic
Evidence-backed validation framework for AI agents, Cursor skills, MCP orchestrations, subagent graphs, hooks, and agentic repos — before deployment, not after.
by SkillForge
Force your AI agent to apply senior-level architectural judgment and design notes before writing any code.
A professional technical editor's review for your docs. Catches missing context, unclear writing, and unverifiable claims in READMEs, API docs, and changelogs before they ship — with a PASS/REVISE verdict and a prioritized fix list.
Check an invoice or estimate before you send it: missing document number, dates, or payment terms, totals that do not add up, tax gaps, missing remittance details, and slow terms with no late fee. Read-only, plain-English findings. Not accounting advice.
Stop building startups nobody wants. Get a brutal, venture-scout validation report: a weighted market score, competitor wedges, a strict MVP scope, and a 7-day no-code demand test for under $100, before you write a single line of code.
by Boubacar B
Claude defaults to complex. This skill does not let that happen. Before your session ships a 400-line solution to a 20-line problem, the simplicity filter stops it and asks: does this actually need to be this complex?
by PromptWagon
Creates social proof sections, testimonial layouts, review highlights, case study prompts, trust copy, proof blocks, credibility sections, logo-strip guidance, before-and-after proof prompts, and ethical usage notes for sales pages, service websites, landing pages, portfolios, product pages, and creator business websites.
Builds and documents the smallest possible POC or prototype to validate requirements before development starts. Part of the Gnosis Technology Product Suite
Adversarially audit your agent hooks before you trust them. Catches command injection, secret leakage, over-broad matchers, destructive actions, and blocking-logic mistakes in pre/post-tool-use, prompt, and stop hooks — with a PASS or REVISE verdict and severity-ranked fixes.
by Elston Gunn
Physically installs and launches your APK before the agent declares the build done. Catches broken artifacts every time.
A ruthless 5-stage elimination filter to triage digital product ideas and kill weak concepts before you build them.
by Timoranjes
Teaches AI coding agents to systematically verify their own work before declaring "done." Implements a structured five-check verification gauntlet (build/test/lint/git-diff/runtime) that the agent run
Review an AI-generated code diff for the failure modes coding agents actually have — claimed-done-but-not-done, gamed or weakened tests, stubs passed off as complete, silent scope creep, hallucinated APIs, and security regressions. Returns an APPROVE or REQUEST CHANGES verdict with a completion check and severity-ranked fixes.
Find and fix every legacy Salesforce API version before the Summer '27/'28 retirements break your integrations — scan, phased plan, CIO-ready report. Audits, reports, and upgrades legacy Salesforce API versions to prevent integration failures and 410 GONE errors.
Diagnoses NestJS ConfigModule, .env, and Docker/Kubernetes environment failures — finds missing vars and misconfigurations before your app boots.
Run this on your plan, spec, or prompt before any work starts. It surfaces the decisions you never made, names what an agent would silently assume for each, ranks them by the cost of a wrong guess, and hands back a short list of choices to make now — plus the gaps that are safe to leave open.
Before you send proprietary or sensitive data to an AI vendor, assess the risk. Classifies what's actually your moat versus regulated, contractual, or harmless data, maps the real exposure vectors by vendor tier, lists the questions to get in writing, and gives a send / send-with-controls / keep-in-house recommendation per data type.
Audit Agensi skill packages for marketplace readiness, formatting compliance, and safety pre-checks. Grade a skill package before you publish it: SKILL.md frontmatter, credits math, description routing, missing listing sections, and a light command-and-secret safety pre-check, scored 0 to 100 with plain-English fixes.
Red-team your own AI agent for prompt-injection and tool-misuse vulnerabilities before it ships — then fix them. Maps your attack surface, generates a defensive test plan with the safe behavior expected for each case, and gives a prioritized mitigations list. Defensive use only.
Before you point a bot or AI agent at X (Twitter), audit it against the platform's rules. Classifies each action as safe, risky, or likely-to-get-you-suspended, names the rule it hits, and rewrites the dangerous parts into a compliant, account-safe version. For keeping your own account safe — not for spam or evasion.
Map your real cloud dependency tree — data plane and control plane — find the single points of failure ranked by blast radius, catch the classic traps like monitoring that dies with the region it watches, and get a prioritized resilience backlog. The audit every outage post-mortem says to do first.
by PromptWagon
Checks digital products before upload, including file completeness, folder structure, README quality, licence notes, buyer instructions, previews, thumbnail, ZIP readiness, product copy, pricing notes, platform fit, safety risks, rights risks, and final publishing checklist for creators and digital product sellers.