Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
Build scroll-linked animations with GSAP ScrollTrigger
Use Greensock’s official gsap-scrolltrigger skill to plan, implement, and debug scroll-linked animations, pinned sections, and scrubbed storytelling without guessing at plugin setup. The agent should reach for this when a user needs a bounded scroll-animation workflow, not when they just need the GSAP product page.
-
Improve Qdrant vector search relevance and retrieval quality
Use Qdrant’s official qdrant-search-quality skill when an agent needs to diagnose weak recall, irrelevant matches, or embedding and chunking mistakes in a live retrieval pipeline. It is a bounded search-quality tuning workflow, not a generic database listing.
-
Develop and harden WordPress plugins with lifecycle and security guardrails
Use Automattic’s official wp-plugin-development skill when an agent needs to build, refactor, secure, or package a WordPress plugin with correct activation hooks, settings handling, uninstall behavior, and data hygiene. This is a plugin engineering playbook, not a generic WordPress listing.
-
Regression-test prompts, agents, and RAG outputs before shipping changes
Use promptfoo when an agent needs to evaluate prompt, agent, or RAG behavior against saved assertions before a change goes live. The value here is the repeatable evaluation workflow, not a generic AI tooling catalog entry.
-
Generate release PRs and changelog updates from Conventional Commits
Use release-please when an agent should turn merged Conventional Commits into structured release PRs, version bumps, and changelog updates before a human reviews and merges. This is a release-management workflow, not a generic package or CI listing.
-
Automate repository triage and recurring repo maintenance with guarded GitHub agent workflows
Use GitHub Agentic Workflows to let an agent triage issues, inspect CI failures, or deliver scheduled repository upkeep inside GitHub Actions with explicit workflow definitions and reviewable runs. This is for bounded, repeatable repository operations, not for listing GitHub as a general coding platform.
-
Diagnose WordPress repo structure and route follow-up work safely
This skill inspects a WordPress codebase, identifies what kind of project it is, and returns the signals an agent needs before touching files or running tools. Use it when you need a deterministic first pass instead of guessing whether a repo is a plugin, block theme, site, core checkout, or mixed workspace.
-
Investigate backend-only WordPress performance bottlenecks
This skill guides an agent through measuring, profiling, and narrowing slow WordPress behavior without relying on browser clicks. Use it when the job is to diagnose slow pages, REST endpoints, cron activity, autoload bloat, or query-heavy requests from the backend outward.
-
Build and debug interactive WordPress frontends with data-wp directives
This skill helps an agent create or troubleshoot WordPress Interactivity API behavior, from store wiring to server-rendered state and hydration checks. Use it when a block, theme, or plugin needs directive-driven interactivity rather than ad hoc frontend glue.
-
publint Package Export Validation Skill for npm Release Checks
Use this skill when an agent needs to lint a package before publish, catch broken exports or manifest issues, and explain exactly what will fail for consumers. It is a pre-publish validation workflow centered on publint, not a generic listing for the tool itself.