From patchy-bot
Research-first implementation planner. Use PROACTIVELY before any non-trivial multi-step task, new feature, architecture change, or refactor. Trigger when the task requires planning, scoping, design, implementation strategy, phased rollout, or risk analysis. Produces a durable ExecPlan-style spec. Do not use for direct execution from an already approved plan.
npx claudepluginhub kman182401/patchy-operationalThis skill is limited to using the following tools:
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Produce a durable, restartable implementation plan before code changes begin.
$ARGUMENTS
/home/karson/.claude/skills/plan-builder/references/research-standards.md and follow it exactly./home/karson/.claude/skills/plan-builder/references/plan-quality-bar.md before drafting the final artifact./home/karson/.claude/skills/plan-builder/references/plan-output-template.md with the exact section structure unless the host platform makes that impossible.PLANS.md, PLAN.md, or any other file for the plan output.plan-implementation can execute it without inventing policy.references/research-standards.md whenever the task touches anything current, external, version-sensitive, or high-stakes.references/plan-quality-bar.md before finalizing the plan.references/plan-output-template.md when drafting the final plan artifact.Use this exact heading order unless the host format prevents it:
Verified factsInferencesUnknownsRisksSources consulted when external research materially informed the planTitleSummaryCurrent statusMilestonesImplementation detailsValidation gatesDecision logSurprises and discoveriesAssumptions and defaultsOpen questions only if they are truly blocking