X-isdoingreat

validate

Interactive technical design quality review and validation. Use when reviewing design before implementation.

new-feature

Quick spec generation with interactive or automatic mode

Install / inspect / pause / change / delete Canvas Pilot cron instances via Windows Task Scheduler. The skill is a **course-agnostic interactive builder** — it lists the student's courses from courses.yaml, asks which course they want a cron for, which action template (email reminder vs autonomous submit), when (schedule), and which template-specific knobs to tune. Autonomous templates require the student to type `授权` to authorize auto-submit. Then walks 5 install gates end-to-end (yaml + render XML → schtasks /create → dry-run classifier → force-fire 60s OS trigger proof → enable schedule). Cookie health is checked at real fire time (not in dry-run); if Canvas session is dead the cron sends a wake-up email instead of silently launching Chromium. Triggered by "装个 cron" / "加个 cron" / "改 cron 时间" / "停掉 cron" / "看 cron 状态" / "删掉 cron" / "install a cron" / "set up a cron" / "/canvas-cron". The skill **zero-hardcodes** course names, template names, instance names, course IDs — every enumeration comes from the CLI'

canvas-awkward-syntax

Use when a short local academic draft needs role-aware syntax diversification while preserving meaning, locks, source grounding, rubric-critical openings, and document structure. Produce a reviewable local variant and never submit.

canvas-essay

Use for an approved long academic-writing assignment routed by canvas-execute after the deterministic writing router selects essay. Build, audit, humanize when configured, and return a verified local draft without submitting.

canvas-execute

Use after canvas-scan wrote a current plan and the student selected items. Records approval, hands approved work sequentially to native Codex course skills, validates results, updates ledger/report/delivery, and finalizes the marker. Canvas submission and quiz mutations require separate scoped authorization.

canvas-generic

Use for an approved Canvas assignment that no specialized course skill can handle. Investigate the real specification, build and verify a local draft artifact, and stop without submitting.

canvas-humanizer-loop

Use when a local draft needs repeated canvas-humanizer passes with independent meaning, structure, citation, voice, and rubric-damage checks. Converge conservatively, return the safest local artifact, and never submit.

canvas-humanizer-surgical

Use after canvas-humanizer when a local draft has specific meaning, grammar, citation, fluency, voice, or rubric defects. Repair only named segments, preserve safe text, and return a verified local artifact without submitting.

canvas-humanizer

Use when a local academic draft needs a meaning-preserving humanizing pass with less uniform syntax while retaining rubric, source, lock, voice, and length constraints. Operates on local files only and returns a reviewable transformed draft plus diagnostics.

canvas-ics33

Use for an approved programming assignment routed by canvas-execute. Resolve the private overlay and real spec from course pages, PDFs, or starter code; implement test-first, audit and package a draft, and submit only through a separately authorized exact-target Canvas workflow.

canvas-inside

Use for an approved Canvas Classic Quiz routed by canvas-execute. Build source-grounded study notes, run four independent native Codex answer passes, and perform only the exact quiz mutations authorized by a signed receipt; fail closed for New Quizzes, locks, missing sources, or incomplete authority.

canvas-reading-annotation

Use for an approved short academic-reading assignment routed by canvas-execute, including in-place PDF annotation, answer blanks, video worksheets, or short reflection drafts. Verify sources and artifacts locally and stop without submitting.

canvas-scan

Use when the student asks what Canvas work is pending or wants a homework plan. It performs one enriched read-only scan, writes the atomic assignment snapshot and approval plan, renders the plan, and stops without drafting or submitting anything.

canvas-setup

Use for first-run Canvas Pilot configuration or recovery when the Canvas host, local runtime, authentication, or route setup is incomplete. It performs the mechanical setup, verifies authentication, then hands empty-route installs to canvas-skill-opportunity and stops.

canvas-skip

Use when an approved Canvas plan item is manual, unsupported, explicitly deferred, or blocked by missing scoped mutation authority. It records one honest canonical skipped result and an idempotent manual todo, with no solving or Canvas mutation.

canvas-bootstrap

Use after the student selects one Canvas skill-opportunity candidate, or when they explicitly redesign one route. It validates the real recurring workflow, creates one public-safe Codex course skill plus a private local overlay, calibrates it when authorized, and writes a route only after the viability gate passes.

canvas-skill-opportunity

Use after first-run Canvas setup or when the user asks which recurring Canvas work should become the first durable course skill. Inspect representative real specifications and Canvas feedback policy, make a qualitative Agent judgment, write a private opportunity report, and stop for the user's choice.

canvas-submit

Use only for a separate exact later-message Canvas command (`submit N`, `take quiz N`, or `retake quiz N`) for one current approved item. Create one scoped receipt, perform only that mutation, verify Canvas read-back, and write the canonical result. Reject broad, automatic, ambiguous, or hypothetical requests.

canvas-zybooks

Generic zyBook-backed math/discrete course handler — written homework, take-home exams, reading-completion. Invoked by canvas-execute when an assignment's routing skill is `zybooks`. Before doing anything, this skill loads `_private/canvas-zybooks-app.md` which encodes your school/instructor-specific behavior (zyBook course code, JWT cookie path, course-context primer, instructor's grading rule). Without the overlay the skill stops and asks the user to author one.

cc-sync-execute-loop

Use only after a reviewed CC-to-Codex sync plan has been approved for execution. It runs the guarded implementation loop, updates durable plan state, and avoids raw planning or unapproved Canvas work.

cc-sync-runner

Use when Claude Code drift needs a public-safe Codex replacement plan or skill batch proposal. It audits capability gaps and writes reviewed planning artifacts; execution requires a separate explicit approval.

daily-work-tweet

Use when verified work from today or another day should become an X/Twitter post, build-in-public update, ship log, or bilingual draft. Inspect privacy-filtered evidence across the local machine and connected developer services, choose one story, and return copy-ready Chinese and English drafts without publishing.