All skills

Scans a repo for nine kinds of technical debt and produces a prioritized, effort-estimated cleanup report with optional safe auto-fixes.

A seven-mode marketing skill that routes requests into SEO audits, campaign plans, content strategy, email sequences, competitive analysis, brand review, or performance reporting and runs each through a gated three-phase framework.

Uses GitHub code search to find public repos importing a specific SDK and maintains a deduplicated, additive Markdown catalog.

Scrapes BOSS直聘 (zhipin.com) job listings through Chrome CDP by keyword, city and filters, exporting plaintext-salary JSON/CSV plus summary reports.

Read an AST-derived code graph as plain files to instantly answer structural questions like "what calls X?" and "what breaks if I change this?".

Gives the agent a disciplined way to search org-wide persistent session memory and to sync skills mined from session logs.

Teaches Claude to create, track, park and close team goals and tasks as Markdown files in the Deeplake virtual filesystem under ~/.deeplake/memory/goal/.

Makes Claude always search both its built-in memory and Activeloop Hivemind's org-wide shared memory.

Query an AST-derived code graph as virtual files to answer structural questions like "what calls X?" and "what breaks if I change this?".

Create, track, resume and close team goals and tasks as Markdown files in the Deeplake virtual filesystem under memory/goal/.

Turns finished experiment results into an honest readout: lift, statistical and practical significance, risks, and a ship/no-ship call.

A zero-dependency playbook for modern CSS animation: scroll-driven timelines, View Transitions, @starting-style and anchor positioning.

A skill that transcribes Chinese/English audio up to ~30 minutes in a single call via StepFun's stepaudio-2.5-asr SSE endpoint.

Fetches a researcher's PubMed record, classifies study types and author position, then charts the patterns and writes a strategy report.

Generate Chinese/Japanese speech with StepFun's contextual TTS, controlling emotion via natural-language instructions and inline () prosody cues.

Turns one brief into several complete identity sets (logo, type, palette), measures them with scripts, and ships a guidelines kit for the set you pick.

Audit any website against 373 rules in 20 categories with the SEOmator CLI, and diff two audits to see what a deploy changed.

Audits any website against 373 SEO, technical, security and AI-readiness rules via the SEOmator CLI, and diffs two runs to show what a deploy changed.

Audits dependency manifests and server configs for known CVEs, scores them with CVSS/EPSS/KEV, and outputs a prioritized remediation report.

Audits a Markdown knowledge vault for broken links, orphans, stubs and schema violations, auto-fixing only the mechanical problems.