Claude Skills by juan294

Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.

Migrated source command `fix-ci`

Migrated source command `release`

Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.

Review and simplify recently changed code after implementation, covering reuse, quality and efficiency while preserving behavior and verification evidence.

Push accountability, CI monitoring after push, background agent CI verification, verification command sequencing.

Production deployment rules, rollback-first recovery, dependency batching, CI cost awareness, framework upgrade verification, fallback observability, and GitHub repo settings standardization.

Known agent error patterns -- debugging reference for tool failures, git errors, CI issues, and common mistakes. Consult when encountering unexpected behavior, tool errors, or CI failures.

Git recipes, worktree management, push sequences, branch verification, and conflict resolution patterns.

gh CLI patterns, JSON field discovery, PR check interpretation, label management, merge settings verification, CodeQL/GHAS gating.

macOS-specific patterns: launchd agent configuration, brew vs pip, zsh regex quirks, file descriptor limits.

Rules for sub-agents, Agent Teams, worktree agents, central commit pattern, and parallel work coordination.

Python-specific patterns: uv/poetry virtual environments, python -m imports, version pinning, pip restrictions on macOS.

Audit and safely migrate an existing project to shared RPI workflows while preserving custom instructions, settings, resources and conventions.

Evaluate the requested architecture, alternatives or current practices against repository evidence and primary sources, ending with a cited assessment artifact.

Set up a new project with shared RPI instructions, native workflows and relevant domain rules through an ownership-aware local installation plan.

Refine a vague or greenfield idea into a validated design brief through focused questions and explicit trade-offs.

Draft a reviewable change description from the complete local diff, commit history and valid verification evidence; publish text only when explicitly authorized.

Remove proven-owned RPI installation components while preserving project instructions, custom settings, skills and user work products.

Run independent fresh-context exploratory charters against a fixed authorized release candidate, preserving the eight-maneuver safety and evidence contract.

Diagnose existing CI failures and repair their root causes locally with regression evidence and complete verification before any authorized publication.

Execute an approved phased plan through implementation, review, repair, simplify and complete local verification before each acceptance boundary.

Create a cited phased implementation specification with behavioral oracles, explicit scope and measurable automated and manual acceptance criteria.

Audit launch readiness across architecture, frontend, backend, performance, operations, security, QA and UX, plus applicable agent surfaces, and produce validated findings.

Prepare and publish the explicitly requested version after complete local integration and release gates, exact-commit remote verification and publication authorization.

Validate and resolve every actionable pre-launch finding in ordered local waves with TDD, finding disposition and preservation of strategic exceptions.

Document how an existing codebase works to answer the requested research question, producing a cited research artifact without implementation or evaluative recommendations.

Report concise project orientation and read-only RPI installation diagnostics, including instruction size, model evidence, drift and native hook trust.

Derive an agent-facing tool contract and seed evaluations from clean and vague role-play transcripts grounded in the actual initial state.

Discover every relevant operational report and existing GitHub security or dependency finding, resolve authorized actionable items locally and record complete disposition.

Refresh documentation, diagrams, version references and existing inline documentation from verified changes since the last release.

Reconcile an installed RPI project with an explicit local source using recoverable ownership baselines, preserving local changes and reporting conflicts.

Verify each implementation phase against its approved plan, deviation notes, actual changes and valid automated acceptance evidence.

Shell and tool-call environment facts: escaping inside single-quoted zsh/jq/Python strings, complex regex in zsh, explicit paths and per-call working directories, linter invocation, curl and JSON output handling, and choosing a built-in tool over a shell one-liner.

Supabase migration safety, local testing workflow, grant requirements, fallback observability, and health endpoint patterns.

A disciplined procedure for finding root causes -- reproduce, isolate, hypothesize, bisect, fix, verify. Consult when a bug is non-obvious, a fix didn't hold, or you've tried the same thing twice without progress.

WebMCP tool design and the agent-facing tool contract: registering tools with document.modelContext, scoping one function per tool, naming tools by effect, schema and validation split, error messages as recovery instructions, and registering tools against page state.

Known agent error patterns -- debugging reference for tool failures, git errors, CI issues, and common mistakes. Consult when encountering unexpected behavior, tool errors, or CI failures.

Audit and safely migrate an existing project to shared RPI workflows while preserving custom instructions, settings, resources and conventions.

Evaluate the requested architecture, alternatives or current practices against repository evidence and primary sources, ending with a cited assessment artifact.

Set up a new project with shared RPI instructions, native workflows and relevant domain rules through an ownership-aware local installation plan.

Refine a vague or greenfield idea into a validated design brief through focused questions and explicit trade-offs.

Draft a reviewable change description from the complete local diff, commit history and valid verification evidence; publish text only when explicitly authorized.

Remove proven-owned RPI installation components while preserving project instructions, custom settings, skills and user work products.

Run independent fresh-context exploratory charters against a fixed authorized release candidate, preserving the eight-maneuver safety and evidence contract.

Diagnose existing CI failures and repair their root causes locally with regression evidence and complete verification before any authorized publication.

Execute an approved phased plan through implementation, review, repair, simplify and complete local verification before each acceptance boundary.

Create a cited phased implementation specification with behavioral oracles, explicit scope and measurable automated and manual acceptance criteria.

Audit launch readiness across architecture, frontend, backend, performance, operations, security, QA and UX, plus applicable agent surfaces, and produce validated findings.

Prepare and publish the explicitly requested version after complete local integration and release gates, exact-commit remote verification and publication authorization.