All authors
Claude Skills by ucsahinn
github.com/ucsahinn11 skills0 installs14 views
- Adaptive Agent RoutingSelect the narrowest useful agent, skill, MCP, and config route for non-trivial work. Use when delegation, context placement, specialist ownership, duplicate skill aliases, or routing visibility materially affects execution; avoid for trivial single-surface work.Votes: 0GitHub stars: 6
- Agentchef OperatorMaintain, audit, and improve AgentChef setup repositories. Use for README/docs/template/catalog/installer/validation updates, release-readiness work, and safe Codex starter maintenance without weakening security, leaking local state, or changing external systems.Votes: 0GitHub stars: 6
- Context Budget PlannerPlan token and context usage before broad agent work. Use for repo-wide, research-heavy, multi-agent, documentation-heavy, or long-running tasks that need a context budget, source priority map, compaction handoff, and verification gates.Votes: 0GitHub stars: 6
- Evidence ResearchDesign and execute source-traceable deep research for decisions, landscapes, comparisons, implementation questions, and evidence reviews. Use when the request needs a research charter, current primary sources, reproducible search and screening, source appraisal, claim-level citations, disagreement and uncertainty analysis, qualitative or quantitative methods, or a decision-ready evidence package.Votes: 0GitHub stars: 6
- External Review WorkflowPrepare a secret-safe, hash-pinned repository snapshot for manual review by an external model, generate a local handoff contract, and verify returned structured findings against the live repository without automatic upload or external execution.Votes: 0GitHub stars: 6
- FetchReconstruct an authorized reference website from a supplied URL with high visual, responsive, interaction, asset, and observable behavior fidelity. Use only when the user explicitly invokes $fetch or $agentchef:fetch for site reconstruction; do not use for JavaScript Fetch API help, generic scraping or archiving, credential capture, access bypass, or deployment.Votes: 0GitHub stars: 6
- Gptpro HandoffAuthor a high-signal, manifest-bound GPT Pro (ChatGPT Project) prompt and verify the returned report against the live repository before implementation. Use when asking GPT Pro for a deep architecture decision, hard bug investigation, security or optimization analysis, or research brief, or when a GPT Pro report came back and must be checked, triaged, or applied.Votes: 0GitHub stars: 6
- GptproPrepare a repository for a manual GPT Pro (ChatGPT Project) deep review as safe, architecture-aware, directly uploadable text bundles plus a convenience ZIP. Use to build or refresh GPT Pro Project context, upload a codebase to GPT Pro, split a monorepo into apps/packages/services/libs plus database and docs context, or create a safe external-model source snapshot.Votes: 0GitHub stars: 6
- Offline Diagram TripletCreate editable offline diagrams from an English description or Mermaid source. Use when the agent should emit a triplet: Mermaid source, an editable .excalidraw file for excalidraw.com, and rendered SVG/PNG assets with zero network access.Votes: 0GitHub stars: 6
- SeoAudit, implement, and verify evidence-backed search optimization for websites and web applications. Use for technical SEO, crawlability, indexing readiness, rendering, metadata, canonical and hreflang policy, structured data, content intent, internal linking, Core Web Vitals, local or international SEO, measurement design, and prioritized growth roadmaps.Votes: 0GitHub stars: 6
- Agent BriefWrite the task brief an orchestrator hands to another agent (subagent, Codex worker, or peer session) and check the handoff that comes back. Use before any delegation that has a goal, a write scope, or acceptance criteria; skip it for a one-line read-only question.Votes: 0GitHub stars: 6