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.
-
Generate XML sitemaps and robots.txt from route inventories before SEO launch
Use sitemap when an agent already knows the site routes or content URLs and needs valid sitemap XML, sitemap indexes, or robots.txt references before launch. This is a publishing-artifact skill, not a crawler or SEO platform.
-
Turn ICS calendar invites and feeds into structured events for scheduling automations
Use node-ical when an agent is handed a raw .ics file or subscription URL and needs normalized event objects, recurrence-aware dates, and timezone-safe fields it can reason over. The skill stops at parsing and structuring calendar data, not acting as a full calendar product.
-
Convert HTML emails and web fragments into clean plain text for downstream agents
Use html-to-text when an agent receives raw HTML from inboxes, support systems, or scraped pages and needs readable plain text before classification, summarization, or indexing. The skill is deliberately bounded to deterministic HTML-to-text conversion, not crawling or summarization.
-
Extract schema.org, Open Graph, and JSON-LD metadata from web pages for indexing
Uses extruct to pull machine-readable metadata from raw HTML so an agent can classify, deduplicate, or enrich pages without brittle full-page parsing. It is best for metadata harvesting workflows, not for crawling an entire site or rendering JavaScript-heavy pages.
-
Normalize loudness across podcast, lesson, or video batches before publishing
Uses ffmpeg-normalize to batch-normalize audio levels so an agent can hand off consistent output without opening a DAW or touching every file by hand. It fits pipelines that need EBU R128, RMS, or peak targets across mixed media before delivery.
-
Orchestrate stacked Git branches, sync safely, and ship pull requests in order
Uses Git Town to keep a branch stack healthy by syncing with the main branch, rebasing dependent branches in order, opening or updating pull requests, and cleaning up after merge. Best when an agent needs repeatable multi-branch workflow control instead of improvising long git command chains.
-
Validate CI and app config files against upstream JSON schemas before merge
Use check-jsonschema when an agent needs to catch broken GitHub Actions, Renovate, Azure Pipelines, and other schema-backed config files before they hit CI. The agent picks the right schema hook, validates the changed files, and reports the exact key or structure that drifted from the contract.
-
Rewrite Git history to purge secrets, binaries, or accidental paths before sharing a repo
Use git-filter-repo when an agent needs to surgically rewrite repository history after a leaked secret, a huge binary commit, or a bad subtree split. The agent analyzes the problem, builds the rewrite command, and leaves a clean follow-up checklist for force-push, clone reset, and downstream cleanup.
-
Audit and normalize SPDX license headers before releasing or open-sourcing a repository
Use REUSE when an agent needs file-level licensing clarity instead of guessing from a single top-level LICENSE file. The agent checks compliance, adds or verifies SPDX headers, pulls missing license texts into LICENSES/, and produces a concrete remediation list or SPDX export.
-
Load-test gRPC services from proto files and reusable request fixtures
This ASE skill uses ghz to run repeatable gRPC load tests from proto files, protosets, or server reflection. An agent can replay request fixtures at controlled concurrency, capture latency and error rates, and export machine-readable reports for regression checks or performance investigations.