mit einem Klick
skills
skills enthält 4 gesammelte Skills von 1broseidon, mit Repository-Berufsabdeckung und Skill-Detailseiten auf SkillsMP.
Skills in diesem Repository
Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.
Engineer system prompts, agent instructions, and other skills against how LLMs actually process text, instead of writing them by feel. Use when authoring or revising any prompt-like artifact: a system prompt, agent instruction set, SKILL.md, tool-use policy, CLAUDE.md, or long behavioral instruction block an LLM executes. Triggers: 'tighten/improve this prompt', a critique or rewrite request, a prompt that is ignored or unreliable, or porting a prompt to a new harness or model. The value is applying the mechanism behind each fix, not just the fix.
Backend craft skill for language-agnostic CLIs, REST APIs, gRPC services, package APIs, and backend repo structure. Use when building, auditing, reshaping, or studying backend boundaries: command trees, HTTP/gRPC contracts, error envelopes, config precedence, operability hooks, package boundaries, dead code, shared-package shape, and agent/script-friendly tools. Not for browser UI, ORM schema design, business domain modeling, Kubernetes/Terraform, or frontend design.
Documentation craft skill for project docs that match the code and read well. Use when writing, auditing, syncing, or extracting documentation: READMEs, API references, tutorials, how-to guides, explanations, architecture notes, changelogs, runbooks, and in-code API docs. Enforces evidence-level claims (no fabricated flags, endpoints, params, defaults, or return types), Diátaxis-aligned structure, audience fit, drift detection, and prose that earns its length.