pica-ui-designer

pica product manager: the brief as a contract, the scope boundary and its exclusions, and the proof of delivery against the brief that was agreed.

3 skills · 3 commands · 1 agent

pica UX engineer: the interactive demo in code — tokens as structured data, the component library, every screen at every viewport in every state, measured before anyone sees it.

4 skills · 1 command · 1 agent

pica design ops: the approved build ported to Figma and verified frame by frame by measurement, the prototype wired, and a file a developer who was in no meeting can build from.

1 skill · 3 commands · 1 agent

pica business analyst: elicitation, the problem, the glossary, business rules, use cases and the requirements the business signs.

2 skills · 1 command · 1 agent

pica core: the state schema, the gates, the check runner and the orchestration every other package is built on.

1 skill · 2 commands · hooks

pica design QA: heuristic evaluation fanned out to independent evaluators, cognitive walkthrough, and the build-versus-design comparison nobody owns.

2 skills · 1 command · 1 agent

Carta Investors plugin — skills for querying investor data, performance benchmarks, regulatory reporting, AGM deck generation, brand extraction, and more via the Carta MCP Server.

29 skills · hooks

Carta Investors plugin — skills for querying investors data, performance benchmarks, regulatory reporting, AGM deck generation, brand extraction, and more via the Carta MCP server

29 skills · hooks

Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).

6 skills · 1 agent · hooks

Comprehensive context engineering and harness engineering skills for production-grade AI agent systems: fundamentals, degradation patterns, compression, optimization, self-managed context (model-controlled live context editing), multi-agent coordination, long-horizon prompting (pseudo-formal task briefs for long-running and parallel agents), memory systems, tool design, filesystem context, hosted agents, evaluation, autonomous harnesses, self-improvement loops (RSI, meta-harnesses, evolutionary scaffold search), latent briefing (KV cache sharing between agents), project development, and cognitive architecture. Ships with a researcher operating system (rubrics, mechanism registry, claim provenance, run state machine, adversarial benchmarks, continuous loop).

19 skills

LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

98 skills

用五重过滤法寻找值得模仿的对标，并排除主体差异造成的噪音。用户要求找对标、选择模仿对象或分析竞争参照时使用。

1 skill