ce

Plugin ce from marketplace claude-essentials in rileyhilliard/claude-essentials. Commands read from the repo's manifest — 11 days ago.

Skills (11)

• architecting-systems

  Guides clean, scalable system architecture during the build phase. Use when designing modules, defining boundaries, structuring projects, managing dependencies, or preventing tight coupling and brittleness as systems grow.

• design

  Design direction and craft rules for product UIs (dashboards, admin tools, SaaS apps, data-heavy interfaces), with a list of AI-default styles to avoid and CSS or Tailwind implementation details. Use when building or restyling a page, component, layout, or theme, choosing color, type and spacing, or

• effect

  Writes and reviews Effect v4 TypeScript code against the installed release instead of remembered Effect 3 APIs. Use when changing Effect services, layers, errors, schemas, resources, fibers, retries, config, logging, HttpApi or HttpClient, SQL, effect/cli commands or @effect/vitest tests.

• executing-plans

  Executes an implementation plan or RFC end to end in a worktree, covering a devils-advocate review of the plan, grouped subagent implementation, the test gate, a code-reviewer pass with every finding fixed, a commit, and a local merge to main. Use when asked to execute, implement, or ship a plan, or

• handling-errors

  Prevents silent failures and context loss in error handling. Use when writing try-catch blocks, designing error propagation, reviewing catch blocks, or implementing Result patterns.

• managing-databases

  Database architecture and SQL guidance for PostgreSQL, DuckDB, Parquet, PGVector, and Neo4j. Use when designing schemas, choosing a storage engine, writing or reviewing non-trivial SQL, adding indexes, tuning slow queries, or configuring vector and graph workloads.

• planning-products

  Defines product features from a PM perspective (JTBD, competitive research, scope negotiation) before technical planning. Use when scoping features, writing product specs, defining user problems, or choosing what to build.

• post-mortem

  Reviews a completed session, or many sessions, to find what caused friction and turns each finding into a concrete change with a file path (docs, CLAUDE.md, skills, hooks, tests, architecture). Use when the user asks for a post-mortem, retro, or lessons learned, asks what went wrong or what keeps go

• structuring-articles

  Selects and applies journalistic story structures (WSJ Formula, Inverted Pyramid, Hourglass, Tick-Tock). Use when writing or outlining articles, blog posts, essays, or any narrative prose longer than a few paragraphs.

• writer

  Writing style guide for prose that sounds like a specific person wrote it, with personas per format and a catalog of AI rhetorical tells to avoid. Use when writing or editing documentation, READMEs, commit messages, PR descriptions, blog posts, LinkedIn or social posts, outreach emails, UI copy, or

• writing-tests

  Writes behavior-focused tests using the Testing Trophy model with real dependencies and minimal mocking. Use when writing or reviewing tests, choosing between unit, integration and E2E, deciding what to mock, replacing sleeps with proper waits, or fixing flaky tests that fail only alongside other te

Subagents (4)

• code-reviewer

  Reviews a branch's full diff against its base from correctness, security, product/UX, and developer-experience angles, and returns a flat list of fixes with file:line references and no optional tier. Use after finishing work on a branch or worktree and before merging, or when asked for a code review

• copywriter

  Writes articles, essays, and long-form content using professional journalistic frameworks. Takes a brief or topic, recommends the best story structure, asks clarifying questions, then drafts the piece section by section. Use when writing articles, blog posts, features, essays, opinion pieces, trend

• devils-advocate

  Pokes holes in a plan, RFC, spec, design, or decision before it is committed to, checking its claims against the real code and raising only genuine flaws, risks, unstated assumptions, and missing edge cases. Use when asked to DA, play devil's advocate, stress-test, or find what's missing in a plan,

• log-reader

  Investigates large or multi-file logs with grep-style filtering by time window, severity, and request ID, so the raw logs never land in the main context, and reports the likely cause with supporting snippets. Use when a bug or incident needs evidence from logs too big to read directly.

Similar plugins