qduc-claude-skills

Plugin qduc-claude-skills from marketplace cascade-code-general-misc-4 in joshuarweaver/cascade-code-general-misc-4. Commands read from the repo's manifest — 1 month ago.

Skills (5)

• cartographer

  Work that's too big to hold in one session, planned as a living map of unknowns — named destination, sharp questions, and fog — resolved one at a time, and kept open through implementation so unknowns found mid-build come back to the map instead of into the diff.

• coordinator

  Coordinate complex work by decomposing it, delegating bounded tasks to available workers, managing dependencies and parallelism, validating evidence, and integrating results. Use when the user asks to coordinate, orchestrate, delegate, use subagents or workers, fan work out, or manage work that bene

• grill-design

  Investigate and pressure-test the design of a non-trivial software feature before implementation. Use when requirements, architecture, integration points, edge cases, compatibility, migrations, rollout, or testing decisions remain uncertain, especially in an existing codebase.

• grill-visual

  Interrogate a plan or design in the browser — opens a local web page and pushes questions with hand-authored HTML diagrams (decision trees, comparison grids, flows) to it, then reads the answers back. Use when the user wants to be grilled visually or graphically, wants a visual/interactive grilling

• implement-feature

  Implement an approved software feature as thin end-to-end slices before hardening individual components. Use when a concrete feature design or implementation plan already exists and the task requires safe incremental implementation in an existing codebase.

Subagents (2)

• Explore

  Read-only search agent for broad fan-out searches — when answering means sweeping many files, directories, or naming conventions and you only need the conclusion, not the file dumps. It reads excerpts rather than whole files, so it locates code; it doesn't review or audit it. Specify search breadth:

• consultant

  A stronger reviewer for decision points. Consult this agent BEFORE substantive work — before writing code, before committing to an interpretation, before building on an assumption — and again when you believe a task is complete, when stuck (errors recurring, approach not converging, results that don

Similar plugins