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
515 skills found
Run structural QA on your translation files across locales. Flags missing keys, placeholder mismatches ({name}, %s, {{var}}), strings left untranslated and identical to the source, length-overflow risk that breaks UI, terminology drift against a glossary, empty targets, and plural-category gaps. Works on JSON, gettext .po/.pot, and .properties. It checks form, not meaning, so you do not need to speak the target language to use it.
The default MCP server is an API wrapper that dumps forty endpoint-shaped tools on the model and hopes — and the model gets confused, picks the wrong tool, and produces garbage that looks like a tool call
Build a complete printable cookbook / recipe book spec for ANY cuisine or theme — recipe page system, layouts, SEO, 13 tags, and image prompts.
Build a complete KDP sudoku puzzle book spec for ANY audience & theme — difficulty mix, page list, SEO, 13 tags, and cover/image prompts.
Build a complete, coordinated printable wall-art set for ANY theme — 9-print list, style guide, all 5 ratios, SEO, 13 tags, and image prompts.
by Liam Romanis
Deep audit and detection of the Dirty Frag (CVE-2026-43284/43500) Linux privilege escalation exploit chain.
by Nex AI
Generate and validate Factur-X/ZUGFeRD hybrid e-invoices compliant with the French EN16931 mandate.
Instant high-performance WordPress FSE block themes from brand briefs with WCAG-compliant design systems.
Write competitor comparison pages that convert — honest, specific, and built for the searcher who already knows your competitor's name.
Flag every em-dash and AI transition cliché in a draft and get a plain replacement suggestion for each. Catches em-dashes (the "ChatGPT dash"), overused transition words and phrases (moreover, furthermore, "in today's digital age," delve), and dash-like punctuation doing vague connective work. It flags and suggests; you decide what to change.
Paste any AI output. Get the production-ready prompt that made it.
Schema mistakes are the most expensive kind — code refactors in days, but a wrong table design holds your data hostage for years
Most launches are a tweet, a spike, and silence by Thursday — because they were planned around the ship date, not the audience.
by Arensight
Most AR teams track DSO. Almost none of them know why it moved. Upload your AR export. Get DSO, Collection Gap, CEI, aging breakdowns, and a prioritized follow-up queue — delivered as a clean six-tab Excel workbook, every week, without a data analyst in sight. Works with QuickBooks, Sage Intacct, NetSuite, Xero, Dynamics, FreshBooks, or any custom CSV. One setup conversation. Hands-free from there.
Catch the dangerous migration before it locks or wrecks your production database. Scans SQL migration files for destructive and risky operations: DROP and TRUNCATE, drops without IF EXISTS, lossy column-type changes, NOT NULL added without a default, DELETE or UPDATE with no WHERE, non-concurrent index builds, dropped constraints, renames, and data backfills mixed into schema changes. Each finding is ranked by severity with a safer rewrite. Postgres, MySQL, and SQLite.
by Matthew King
A risk-first QA agent that hunts bugs via personas, extracts BDD requirements, and drives TDD fixes.
by Nex AI
Scaffold legal entity formation, VAT validation, and compliance documentation for the Netherlands, Belgium, and Luxembourg.
Production prompts grow by accretion — every failure gets another appended rule until the prompt is two thousand words of contradictions that the model navigates unpredictably
Professional-grade design refinement for the final 10% of your UI.
An adversarial gate that audits an MCP server or agent tool definition — schemas, descriptions, scopes, auth — for tool poisoning, excessive agency, injectable descriptions, and missing access controls, then returns one SAFE/REVIEW/BLOCK verdict.
An adversarial gate that audits a resume or cover letter for overclaims, unverifiable metrics, vague impact, and ATS keyword gaps, then returns one PASS/REVISE/FAIL verdict.
Point it at an unfamiliar or inherited repo and quickly understand it. Maps the architecture, identifies the key modules and entry points, traces the core end-to-end flows, surfaces the conventions and gotchas, and assembles a clean ONBOARDING.md — turning a strange codebase into a clear mental model fast. Built for the moment you join a project, take one over, or have to explain a repo before changing it.
Jumping straight to code works until step seven, where the change you didn't anticipate meets the four files you already modified
An adversarial reviewer for social posts, ads, and marketing copy. It flags off-brand tone, unsupported claims, weak or missing calls-to-action, platform mismatches, and compliance risks, then returns a PUBLISH / REVISE / HOLD verdict — before you hit publish.