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
42 skills found
by loreto
Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.
by Kevin Cline
Deep project analysis to generate professional README.md files with API references, scripts, and stack detection.
Run a complete pre-publish readiness check on your skills — version consistency, marketplace reference audit, internal path cleanup, and clear 0.0.1 vs 0.1.0 publishing decision.
Turn complex system documentation into structured, agent-accessible knowledge bases optimized for MCP and AI tools.
by Shandra
Transforms undocumented repositories into professional README files, setup guides, command maps, architecture notes, environment references, testing docs, and AI agent handoff files.
Design and evaluate production-grade observability systems using the 12-layer Full Stack Observatory reference model.
Lint your AGENTS.md (or CLAUDE.md and .cursorrules) for the problems that make a coding agent misbehave. Flags contradictory rules, references to files and commands that no longer exist, overly broad or unsafe instructions, missing sections (build, test, run, conventions), duplicate rules, and the case where you have competing rule files that should be consolidated into one AGENTS.md.
Free collection of 7 agent-ready monitoring tools. Price alerts, cost tracking, repo scanning, uptime checks, and more. Quick-reference guide with one-command install.
Audit, verify, and format academic citations across AMA, APA, and Vancouver styles to eliminate AI hallucinations.
Scan a SKILL.md package for prompt injection and secret exfiltration before you install or publish an agent skill. Flags env-variable-to-URL exfiltration wording, conditional triggers with hidden side effects, imperative instructions buried in HTML comments, zero-width characters, base64 and long-token blobs, remote content treated as instructions, pipe-to-shell and recursive force-delete references, and overbroad tool requests (network plus browser plus file-write with no scope).
by LocoLoboZ
A technical reference and troubleshooting expert for connecting Make.com scenarios to MCP-compatible AI agents.
by Joker
Data analysis engine with 4D decision matrix, 15-min quick analysis template, statistics reference, A/B testing playbook, user behavior analysis, SQL templates.
Audit local dbt SQL and YAML for missing model tests, source freshness and test gaps, likely-key coverage, missing model descriptions, SELECT *, and raw table references. Get severity-ranked findings plus starter tests YAML for model/key gaps without running dbt or querying a warehouse.
Generate an llms.txt for your site and validate an existing one against the spec. The generator turns your sitemap.xml or docs folder into a clean, sectioned llms.txt with one-line descriptions. The validator flags a missing H1 title, a missing summary blockquote, malformed link entries, links with no description, relative URLs that should be absolute, and a referenced llms-full.txt that is not present.
Catch documentation that drifted from your code. Flags functions and methods named in your docs that are gone from the source, CLI flags documented but missing from the arg parser, env vars the docs mention but the code never reads, example imports of modules that no longer exist, and npm scripts or Make targets your docs reference but the project does not define. Cross-references your README and docs against Python and JS/TS source.
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 Roy Yuen
Turn any website into a structured design system reference with CSS tokens and automated screenshots.
Inventory every LLM model and provider your code depends on, the AI bill of materials, and flag the dependency risk. It lists each provider, model, and where it's used, then flags hardcoded model ids, single-provider dependency with no alternative, the same model referenced by different ids, model ids with no config or env indirection, and providers pinned in your manifests. Recognizes OpenAI, Anthropic, Google Gemini, and more from an editable list.
Stop your agent citing papers that don't exist. Verifies every reference against live PubMed & Crossref — flags fabricated, mismatched, and retracted citations.
Audit AI-assisted medical and pharma content for compliance-readiness before it enters formal MLR review or journal submission. It checks claim substantiation and on-label scope, reference integrity (the acute AI risk: fabricated or misrepresented citations), fair balance and safety, AI-use disclosure, ICMJE authorship and GPP, COI and funding, data integrity and patient privacy, and adverse-event flags — then returns a PASS / REVISE / BLOCK verdict with the must-fix list. A readiness pre-check built for the regulated reality of medical communications — not a replacement for formal review.
by Shandra
Recommends electronics products and checks compatibility based on customer use case, budget, existing devices, technical level, preferences, required specs, and useful accessories.
Generate consistent API reference docs from your code, OpenAPI spec, or route handlers — per-endpoint parameters, real request and response examples, error codes, auth, and copy-pasteable curl, written for the developer calling the API.
by Y_Y_ai
Generates high-quality English patent specification drafts, proposes drawing compositions, maintains reference numeral consistency, and structures hierarchical claims.