WGM and Companion Skills
Turn a rough request into working software and help its operator understand the result.
The complete author package contains wgm plus teach-me, quiz-me, and rugged companions. It joins request clarification, planning, implementation loops, code-backed teaching, knowledge checks, and stress testing.
Use cases
- Develop software from a rough request
- Learn and quiz yourself on a repository
- Stress-test the delivered result
How to use
Use the upstream installer to retain the main Skill and all companions. Supply the goal and acceptance conditions, then use the learning or rugged workflows against the resulting repository.
Skills
wgm
Autonomous build skill that turns a rough request into working software through a relentless requirements interview (grill), a persistent plan, and a Ralph-style build loop (analyze → implement → validate → review → record). Use when the user runs /wgm, or asks to build, implement, prototype, or ship a feature or app from rough intent; when a task is ambiguous and needs requirements interrogation before coding; or for multi-step feature work that benefits from a planned, test-validated iterative loop. Supports phase modes grill, analyze, plan, build, and review, with an optional "only" qualifier to run a single phase (e.g. "/wgm analyze only"). Not for trivial one-file edits, pure debugging, or research-only questions.
agent-frontier/wgmteach-me
Companion learning skill that makes a codebase legible fast. Surveys a repository, builds a cited map, runs a guided tour in dependency order, and finishes with a validated first change so the learner has actually moved the code. Use when the user runs /teach-me, or asks to learn, understand, onboard onto, get up to speed on, or be walked through a repository — including one wgm just built for them. Supports phase modes map, tour, deep, change, and recap, with an optional "only" qualifier to run a single phase (e.g. "/teach-me tour only"). Not for answering a single narrow code question, and not for making feature changes — that is wgm's job.
agent-frontier/wgmquiz-me
Companion assessment skill that grills a user on a codebase until their understanding is proven rather than assumed. Asks one question at a time, grades every answer against the real code with citations, scores 0-100 by difficulty tier, and drills the weak areas it finds. Use when the user runs /quiz-me, or asks to be quizzed, tested, grilled, or checked on a repository — including one wgm just built for them. Supports phase modes warmup, drill, exam, and review, with an optional "only" qualifier to run a single phase (e.g. "/quiz-me drill only"). Not for teaching or explaining the codebase — that is teach-me — and not for reviewing code changes.
agent-frontier/wgmrugged
Companion review skill that stress-tests a request, spec, plan, diff, or system against the operators and environment that will actually run it, not an idealized one. Runs a disciplined lifecycle (Triage -> Context -> Bottleneck decomposition -> Simplify -> Field test -> Verdict) and emits exactly one of three verdicts -- RUGGED, FRAGILE, UNKNOWN -- backed by exact pre-build validation design or deterministic field/stress evidence rather than confident claims. Use when the user runs /rugged, or asks whether a design will hold up in the real world, survive real operators, or is over-engineered for conditions that don't exist. Supports standalone modes plan, review, stress, and recap. Read-only -- never edits product code or docs. Not for building or fixing anything -- that is wgm -- and not for weapon, firearm, or tactical guidance of any kind.
agent-frontier/wgm