phrimm136

Execute a planned multi-phase task — resume from /plan's committed artifacts and run each phase red→green→refactor inline in the main session under hook enforcement and script gates. Generation stays in one hot context; agents are spawned only to verify (spikes already done, review lanes, refuters, seam, provenance, drive). One final user gate over the whole task diff — for large tasks (15+ files), after /plan.

Archive an agreed design as a task specification — requirements with stable R-ids, a ratified tests.manifest.json (contract rows, decision rows with enforcement pointers, touch map, spike list), a slimmed mechanics doc for the prose residue, taste decisions drafted into meme, one tandem commit

Turn a ratified tests.manifest.json into an executable plan — scaffold phases, fill decision slots inline, run environment spikes as verification probes, lint, delta-review, bake baselines, and land one plan commit. The generation half of the build pipeline; everything it produces is a file, so /build resumes from disk. Run after /spec, before /build, for large multi-phase tasks.

Restore session context from the task checklist — add 'continue' to also resume execution from the first non-closed item

Code review via risk-routed judgment lanes — static tools first, then only the lanes the diff's surface warrants, blocker findings refuter-verified and fixed green-to-green

Dialectic architecture and design debate — argue until consensus, close every ambiguity, and land the agreement as falsifiable candidate rows (scenarios, decisions, spikes) ready for /spec to ratify

Close out a task — results generated from checklist and verification data plus a hand-written narrative delta, the amendment log drafted into meme, backlog reconciled, living docs swept for staleness

Write a teaching-grade, interactive learning report into ~/learning/ that distills what was worked on in the current conversation AND the related concepts behind it — both at full depth. Subagents author markdown in a typed-block convention (quiz and diagram code fences, skippable fenced divs, callout blockquotes, front-matter metadata); a bundled pandoc converter renders each file into a self-contained interactive HTML page with a TOC, validated multiple-choice quizzes with per-option feedback, HTML diagrams, and a computed reading-time footer. Splits a large or multi-concept report into a directory of numbered pieces with an index. Use when the user says "/learning-report", "write a learning report", "document what we learned", "turn this into a learning doc", or asks to teach-back the session. An optional arg focuses the report on a specific topic.

Add a selectable planner keyword end-to-end across FE, BE, and i18n with the proper in-game translation. Use when adding a plan keyword, synergy keyword, faction keyword, or a value to the planner keyword filter.

Synchronize patterns from docs/**/findings.md to CLAUDE.md and skill documentation. Use when updating specs, consolidating learnings, preventing outdated documentation, or running /findings-sync command.

Add a new announcement to all 5 JSON files with auto-translation, commit, and tag. Use when adding announcements, writing update notices, or posting new content.

Full commit workflow — pre-commit validation, branch creation, commit message writing, staging, and checkout. Use this skill whenever the user asks to commit, create a commit, write a commit message, stage changes, finalize work, or prepare code for a PR. Also triggers on phrases like "commit the change", "ready to commit", "let's commit this", "wrap this up", or any git commit-related request.

Create and manage Claude Code skills. Use when creating skills, modifying skill-rules.json, or debugging activation.

Interview simulator that tests understanding of architectural decisions. Asks "why" questions, gives hints instead of answers, probes deeper on correct responses. Supports topic-based and random code quiz modes.