Grouped grilling session that wraps grill-with-docs semantics while discussing related questions in batches, with explicit convergence checks so it stops when docs already contain enough decision quality. Use when the user wants to stress-test a plan against docs and domain language faster than one-question-at-a-time grilling, especially when asking whether remaining questions exist.

Create and maintain an intuitive human documentation surface for AI-agent-developed repos. Use when humans should only need README.md, ARCHITECTURE.md, STATUS.md, and docs/human/** while planning logs, generated docs, retrospectives, ADR detail, and implementation evidence stay in AI-agent-only folders.

Orchestrate the intuitive idea-to-execution workflow: grill-me or office-hours for direct or auto-guided idea shaping, docs/plans as the pre-execution source of truth, autoplan for hard review, optional to-issues for vertical slices, GSD ingest/plan for committed execution, GSD execute/verify for implementation, simplify for changed-code cleanup, bounded scoping for architecture/refactor work, and tdd inside risky slices. Use when the user asks for normal development flow, durable planning, fuzzy idea to implementation, Matt Pocock skills + gstack + GSD together, improve-codebase-architecture via a pipeline, or one coherent source of truth from idea to verified work.

Initialize, audit, aggressively slim, merge, and refresh project-local AGENTS.md and CLAUDE.md files from existing repo guidance, agent /init suggestions, stdin-bundled Codex init-style discovery, and intuitive workflow defaults. Use when setting up a repo for Claude Code/Codex, replacing symlinked agent files with local guidance, rerunning agent init after weeks of drift, cleaning overgrown root agent files, or aligning a repo to intuitive-doc, intuitive-tests, intuitive-flow, intuitive-refactor, and intuitive-reduce-entropy without overwriting project-specific hints.

Port changes from one git worktree or checkout into the default repository folder's current branch. Use when the user asks to move, copy, transfer, transplant, cherry-pick, apply a patch, or port worktree changes into the main/default repo checkout without changing the target branch.

Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, main-session /goal wording, or skill-runner worker prompts for an intuitive-flow run. This skill does not execute; it produces the contract that $intuitive-flow or a main-session goal can execute after approval.

Periodically inspect a repository and recommend the highest-value entropy reduction slice across agent guidance, human docs, tests, repo layout, stale APIs, and cleanup gates. Use when the user says the repo feels messy, asks what to clean next, wants to make an old repo easier for humans and AI agents to work in, or wants maintenance suggestions without already knowing the target seam. This is the small public entrypoint for repo maintenance; it routes to specialist skills instead of making the user choose them upfront.

Set a bounded aggressive refactor goal before architecture or cleanup work starts. Use whenever the user wants to improve architecture, clean up aggressively, "fix all big issues", avoid endless refactors, decide what is in/out of scope, classify P0/P1/P2/Parked findings, remove stale APIs or compatibility shims, or define the tests and stop condition before changing code. This skill works standalone and can also be combined with architecture scanners, intuitive-flow, TDD, or diagnosis skills.

Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It turns broad testing advice into a practical, behavior-first cleanup workflow. For broad suite refactors, audit first, propose a recommended path across markers, folder layout, pruning, fixtures, and parameterization, then wait for user feedback before applying disruptive changes.

Run a daily development task through one or more named skills in an isolated tmux-backed Codex or Claude session. Use when the user asks to "impl X with $skill", "run X via $intuitive-flow", supervise a skill-driven task, keep the main session clean, evaluate the run, or improve custom skills after a real task reveals a reusable workflow defect.