Explorar skills

Run the probe-driven validation rounds for the agentic ontology — Type 4 (adversarial — capability-negation / cross-product-fabrication / synonym-swap-with-negation, ≥2 of 3 PASS) and Type 6 (implicit-ADR confirmation — maintainer writes 5 ADRs they know are followed; ≥3 of 5 must surface in implicit-adrs.md top-10). Both rounds are MAINTAINER-AUTHORED; this skill is the protocol mechanics, not th

Process status/needs-triage items through the full pipeline: sort (reject/dedup), spec (brainstorming + writing-plans for M/L/XL items), score against the agent-ready checklist, and promote to status/ready (with owner/ai or owner/human) or reject to out-of-scope. Interactive — you confirm every decision. Trigger: "triage", "process backlog", "review incoming items", "spec items", or /pm:triage.

Show current progress of the audit and implementation system — scanner completion, backlog counts, blockers.

Otimiza o conteúdo para a descoberta por LLMs e o consumo por agentes de IA.

Produce a work plan and stub implementations from the brief and domain analysis

Pull the latest headsup release from GitHub and apply it in-place. Use when the user types /headsup-update, asks to "update headsup", or wants to pull the newest version of the tab-color/status hooks.

Turn raw insights into well-structured opportunity statements ready for prioritization or experiment design. Use this skill when a team has research insights and needs to frame them as actionable product opportunities.

Esta skill realiza revisões de código aprofundadas e baseadas em evidências para mudanças críticas em pull requests, branches ou diffs, especialmente para segurança, infraestrutura ou pagamentos, visando evitar perda de tempo ou bugs. Não deve ser usada para verificações rápidas ou feedback informal.

Automates headless Chrome via MCP for web scraping, screenshots, testing, and browser interactions. Handles multi-instance server selection to avoid lock conflicts between parallel agents. Triggers when browsing a website, taking a screenshot, scraping a page, testing a web app, automating browser interactions, or when chrome-devtools MCP tools are needed.

QA testing for Streamlit applications — locally or on Hugging Face Spaces. Covers app startup, UI rendering, Streamlit-specific checks (session state, widgets, forms, caching), clinical content accuracy, HF Spaces compatibility, and accessibility. Produces a structured QA report with PASS/FAIL/PARTIAL status.

Impõe uma disciplina de pesquisa baseada em fontes e com citação prioritária. Utilize esta habilidade para pesquisar, verificar fatos, resumir descobertas ou qualquer resultado factual que exija precisão e verificabilidade, mesmo com frases conversacionais.

Use when choosing the FORMAT of an output, not just its verbosity — match the medium (text, markdown, HTML dashboard, PPTX, DOCX) to the consumer's actual use mode. Operator-specific extension: also covers length calibration for different contexts. Outside scope is video (requires autovideo pipeline — too heavy to be native capability). The chengyu is about teaching with the right material, where