Generate Chinese/Japanese speech with StepFun's contextual TTS, controlling emotion via natural-language instructions and inline () prosody cues.
Turns a single concept into a magazine-style feature: real problem → failed attempts → turning point → insight → naming, rendered as one long vertical HTML page.
Produces a statistically rigorous A/B test plan with hypothesis, sample size, duration, guardrails, and a results interpretation guide.
Plans trips for travelers with disabilities by verifying real accessibility, booking assistance in writing, and pre-writing contingency scripts.
Turns finished A/B test numbers into an honest readout with a ship/no-ship verdict, significance checks and segment cuts.
Locates babysitter processes and committed runs in an external public repo and writes an evidence-backed retrospective with concrete improvement suggestions.
Uses GitHub code search to find public repos importing a specific SDK and maintains a deduplicated, additive Markdown catalog.
Interviews you about a business process, then generates a complete multi-agent team configuration set.
Orchestrates a 2-layer parallel agent hierarchy for large refactors, multi-file migrations, and codebase-wide audits.
Splits huge data workloads into batches, runs them across parallel sub-agents, and merges everything back into one validated output.
Pulls financials, earnings and key metrics from Yahoo Finance and scores a company's financial strength with the Piotroski F-Score.
Look up the next earnings date, BMO/AMC timing and consensus EPS for any ticker or list of tickers.
A CSO persona skill for multi-year decisions: where to play, build vs. buy vs. partner, portfolio and capital allocation, and planning under uncertainty.
A corporate-development skill that disciplines M&A thinking from deal thesis and target screening through valuation, diligence, and integration planning.
Create, track, resume and close team goals and tasks as Markdown files in the Deeplake virtual filesystem under memory/goal/.
Teaches Claude to create, track, park and close team goals and tasks as Markdown files in the Deeplake virtual filesystem under ~/.deeplake/memory/goal/.
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 Activeloop Hivemind's org-wide session memory (index → summaries → raw JSONL) plus team skill sharing and semantic search controls.
Lets Claude Code search and manage org-wide shared session memory and team skills via Activeloop Hivemind.
Query an AST-derived code graph as virtual files to answer structural questions like "what calls X?" and "what breaks if I change this?".