gradient

Maintain Gradient's repo-local agent harness: skills, agents, settings, repo brief, and gate-aligned instructions. Trigger: /harness, /skill, /primitive.

Take one shaped Gradient docs/schema/profile task to merge-ready. Composes /shape, /implement, /code-review, /ci, /qa, /demo, and /refactor as needed. Stops before merge. Trigger: /deliver.

Assess Gradient's readiness for governed agent work across docs, schemas, profiles, harness, validation, evidence, and public-safe boundaries. Trigger: /agent-readiness, /readiness.

Dialectical premise-and-alternatives audit for a plan, spec, or context packet. Four moves: premise challenge (is this the right problem?), mandatory structurally-distinct alternatives, cross-model outside voice, user-ratified convergence. Named for Gary Tan's plan-ceo-review pattern; operationalizes the AGENTS.md "Diverge Before You Converge" doctrine at the plan-review stage. Use when: about to commit to a plan/spec/design, reviewing a ticket before shape, when "is this the right problem" would be useful, or any time a proposal smells like a symptom fix instead of a root-cause fix. Trigger: /ceo-review, /challenge, /premise-check.

Gradient gate audit and validation workflow. Use when checking whether a docs/profile/schema change is safe to ship in this scaffold. Trigger: /ci.

Review Gradient docs, profiles, schemas, and harness changes for public-safe boundaries, lifecycle consistency, and contract depth. Trigger: /code-review, /review, /critique.

Produce evidence that a Gradient docs/schema/profile change is understandable and reviewable. For this repo, demos are validation transcripts, synthetic fixtures, before/after contract walkthroughs, or release-note blurbs. Trigger: /demo.

Investigate failures in Gradient contracts, docs, schemas, profiles, harness wiring, and future validation commands. Trigger: /diagnose.

Outer-loop Gradient work cycle. Pick, shape, implement, settle, ship, monitor, and feed learnings back into docs, schemas, profiles, or harness. Trigger: /flywheel.

Change Gradient's module contracts, profile schema, profiles, and evidence artifacts without drifting from the public-safe lifecycle invariant. Use when editing docs/module-contracts.md, docs/architecture.md, schemas/gradient.schema.json, profiles/*.yaml, or evidence packet fixtures. Trigger: /gradient-contracts.

Use Gradient itself: discover install state, initialize or upgrade repositories, operate the Work/Fleet/Context/Evidence/Policy loop, and know when repository work should flow through Gradient. Trigger: /gradient.

Groom Gradient ideas and debt into public-safe, lifecycle-aware work. Trigger: /groom, /backlog, /rethink.

Build a shaped Gradient context packet into docs, YAML profiles, JSON Schema, synthetic fixtures, or harness files. Trigger: /implement, /build.

Watch Gradient repo signals after a docs/schema/profile/harness change. Trigger: /monitor.

YC-partner-style interrogation of a raw idea. Six forcing questions before you shape anything: demand reality, status quo, desperate specificity, narrowest wedge, observation & surprise, future-fit. Named for Gary Tan's office-hours pattern; operationalizes the AGENTS.md "Diverge Before You Converge" doctrine at the ideation stage — problem-diamond, pre-/shape. Use when: user arrives with a rough idea, backlog item is fuzzy, you can't already write a one-sentence goal with a testable outcome, or the phrase "what should we build" would be useful. Trigger: /office-hours, /oh, /interrogate.

Verify Gradient docs, profiles, schemas, fixtures, and harness wiring by inspecting the changed artifact itself. Tests passing is not QA, and this repo has no app to drive. Trigger: /qa.

Simplify Gradient docs, schema, profile, or harness structure without changing semantics. Trigger: /refactor.

Session retrospective, operator coaching, harness postmortem, codification, and outer-loop cycle critique. Distills learnings into hooks/rules/skills, mutates the backlog from evidence, and emits harness-tuning suggestions to a branch. Learning engine of the outer loop. Use when: "done", "wrap up", "what did we learn", "retro", "reflect", "calibrate", "how could I have asked better", "prompt better", "teach me from this session", "what should I learn from this", "reflect on cycle", "cycle postmortem", post-/flywheel critique. Trigger: /reflect, /retro, /calibrate, /reflect cycle <cycle-ulid>.

Research Gradient product, architecture, model/provider, and reference-system questions with citations and public-safe boundaries. Trigger: /research.

Polish a Gradient branch until it is merge-ready. Runs review, gate, QA, and simplification loops, then stops before merge. Trigger: /settle, /pr-fix, /pr-polish.

Shape raw Gradient ideas into buildable context packets for docs, schemas, profiles, adapters, policy, context, or harness work. Trigger: /shape, /spec, /plan, /cp.

Final mile for a merge-ready Gradient branch: verify gate evidence, preserve work references, merge to master when authorized, and reflect. Trigger: /ship.

Turn local Gradient worktree changes into coherent commits and push when appropriate. Trigger: /yeet, /ship-local.

Rework a change as if the intended UX and architecture existed from day one, deleting compatibility cruft and accidental complexity. Trigger: /zero-tech-debt.