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
509 skills found
An adversarial security gate that audits untrusted content — web pages, tool outputs, documents, emails — for embedded instructions, exfiltration, and authority spoofing, then returns a SAFE/REVIEW/BLOCK verdict.
An adversarial gate that audits any chart, data summary, or statistic for misleading visuals and unsound inference, then returns one PASS/REVISE/FAIL verdict.
Runs an ordered evidence-integrity gate over any AI draft — grade sources, ground claims, verify technical assertions, stress-test — then returns one PASS/REVISE/FAIL ship decision.
Diagnoses and fixes LCP, INP, and CLS on WordPress sites with a scored, prioritized action plan and runnable before→after code — including the non-obvious insight that consent-gated analytics loading is a measured CWV improvement, not just a GDPR requirement.
A repo visitor decides in about ten seconds whether your project solves their problem — and most READMEs spend those ten seconds on installation instructions instead of answering 'what does this actually do'
You changed the prompt, tried four inputs, it looked better, you shipped — and three days later support tickets say outputs are worse for an entire class of inputs you didn't test
Professional-grade market intelligence and competitive strategy reports using the LPOG consulting framework.
Find the model-version coupling that breaks when you swap LLMs. Flags hardcoded model names and versions, deprecated or renamed parameters (the max_tokens to max_completion_tokens class of change), hardcoded token and context-window limits, response-format parsing tied to one model's output, tool-schema format coupling between providers, and hardcoded per-token cost constants. The patterns load from an editable model-rules table you update as new models ship.
Catch the Open Graph and Twitter Card problems that make a shared link preview blank or broken. Flags missing og:title, og:image, og:description, og:url, or twitter:card, a relative og:image URL (crawlers need an absolute one), an SVG og:image (no platform renders it), and image dimensions that miss the 1200x630 standard. Reads your HTML or pasted head markup; it does not fetch the page or refresh a platform's cache.
Generate a ready-to-use LICENSE file for your repo. Pick from MIT, Apache-2.0, GPL-3.0, MPL-2.0, BSD-2-Clause, BSD-3-Clause, or The Unlicense, fill in your name and year, and get the canonical license text. Prints to the screen by default and writes a LICENSE file only when you ask.
Diagnose why your Docker Compose stack won't come up: port conflicts, bad or missing env vars, absent healthchecks, volume and permission issues, depends_on that doesn't wait for readiness, networking gaps, platform mismatches, and databases that aren't ready. Reads your docker-compose.yml and logs and ranks the blockers with fixes.
Optimize your Etsy thumbnails using click psychology to stop the scroll and and earn more clicks.
Generate 30-page themed sight word product specs with Dolch/Fry lists, Etsy SEO, and Midjourney prompts.
Check ad copy for the editorial issues that get Google and Meta ads disapproved, before you submit. Flags all-caps words, gimmicky punctuation (!!, ??), prohibited and hype words, Meta's banned personal-attribute framing ("Are you over 40?"), absolute or unsubstantiated claims, ad-field length overflow, and trademark-term risk. The word lists and field limits are editable, so you can tune it to your accounts.
Audit a draft against your own voice spec and flag every line that breaks your house style. Checks banned words and phrases, em-dashes (when your spec bans them), sentences over your word-count cap, off-spec terms that have a preferred replacement, missing contractions, and forbidden clichés. Config-driven by a voice-spec.json you control, with a sensible default spec if you don't supply one.
Audit your SPF, DKIM, and DMARC records for the misconfigurations that get mail rejected or sent to spam. Flags a missing DMARC record or p=none, missing rua reporting, a missing or duplicated SPF record, SPF over the 10-lookup limit, permissive +all/?all, a missing DKIM selector, and SPF/DKIM domain-alignment mismatches. Paste a DNS zone file or dig/nslookup output.
Stuck with a “wip” or “fix stuff” commit? Get one clean, ready-to-paste rewrite. Bad commit message you already wrote — “wip”, “fix stuff”, a vague subject a reviewer flagged? Find the #1 reason it fails and get a finished rewrite: clean subject, a why-body only when it’s needed.
Turns Claude into a senior WordPress launch reviewer that audits a site, theme, or plugin against the entire pre-launch standard across 7 weighted domains and returns one objective go/no-go decision with a scored blocker list.
Before an agent acts on a plan, verify that the things it named actually exist. Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo, and flags the ones that do not resolve. Catches the hallucinated function and the phantom package before the edit, not after the build breaks. Resolves Python and JavaScript/TypeScript.
Audit a JavaScript or TypeScript frontend for missing translations and hardcoded UI strings before you ship a new locale. Flags hardcoded JSX text and UI props (title, placeholder, aria-label, label, alt) not wrapped in t(), i18n.t(), or <Trans>; keys present in the default locale but missing from other locale files; keys referenced in code but absent from the locales (the raw dotted keys that leak to users); unused locale keys; and unparseable locale JSON.
by Nex AI
Ship a Manifest V3 Chrome extension that applies a custom accent color theme across any website.
Convert existing HTML sections or plain descriptions into production-ready Gutenberg block patterns that inherit your theme's design system — no hardcoded colors, no inline styles, no editor validation errors.
Deploy a production-ready AI chat widget that qualifies web leads and syncs them to your CRM via n8n.
The hard part of multi-agent work isn't spawning agents — it's deciding what deserves parallelism, what each agent needs to not duplicate work, and how failures cascade