qWaitCrypto

Run the Chapter Gate (PASS/WARN/FAIL) after drafting a chapter. Use to ensure chapter obeys its fine-outline results and doesn’t contradict upstream canon.

Run the Consistency Gate (PASS/WARN/FAIL) to catch cross-chapter contradictions (character traits/state, world/system rules, timeline, who-knows-what) and produce a prioritized fix list.

Run the Fine-outline Gate (PASS/WARN/FAIL) before drafting chapters. Enforces per-chapter structure and Han > 500 per chapter plan when measurable.

Run the Forgotten Elements Gate to find dropped characters, stalled plot threads, and uncollected foreshadowing in long-form fiction, then output a prioritized fix list.

Run the Outline Gate (PASS/WARN/FAIL) before moving from outline to fine-outline. Use to ensure outline obeys spec constraints and anchors key ambiguity points.

Run the Regression Gate at milestones. Use to scan written chapters for consistency (timeline, knowledge, character state, system boundaries) and produce a prioritized fix list.

Run the Spec Gate (PASS/WARN/FAIL) before moving from spec to outline. Use to verify premise/system/characters/timeline readiness and detect spec-level contradictions.

Define and maintain character canon under spec/characters/ (identity, motive, resources, behavioral boundaries, relationships, state variables). Use when designing main cast, or when outline/chapters show OOC risk.

Use whenever the task is to fetch, backfill, sync, repair, slice, inspect, or featureize AuraQuant CTA market data. Trigger on requests about OHLCV history, gap filling, data versions, data slices, feature slices, or local data storage layout.

Use whenever the task is to run CTA experiments, inspect eval reports, compare results, or turn structured backtest/evaluation output into the next research decision in AuraQuant.

Use whenever the task is to inspect archive lineage, write candidate records, request freeze transitions, resolve approvals, or advance CTA strategy lifecycle state in AuraQuant. Trigger on candidate, frozen, production, deprecated, archive, lineage, or approval requests.

Use whenever the user wants to advance CTA research in AuraQuant, asks what the next step is, wants the agent to take over the overall research loop, or needs a cross-stage decision spanning data, specs, runtime modules, experiments, evaluation, and archive governance.

Use whenever the task is to define or update CTA runtime modules or specs in AuraQuant, including baseline/filter/execution/risk code under cta_runtime, spec persistence, runtime validation, and first-run assembly with default modules.

Use for CTA research inside Aura when the task is to inspect archived runs, review evaluation artifacts, generate the next structured proposal, or advance approval-gated archive state. Do not use it for generic coding or to invent unsupported execution capability.

Microsoft Word / DOCX processing via a plan-driven pipeline (analyze → plan → apply → Gate A validate → report). Use this skill whenever the user mentions Word documents, .docx files, contracts, reports, proposals, templates, tracked changes, redlining, or comments — whether creating from scratch, reading, editing, filling placeholders, or performing legal-grade redlines. Always prefer this skill over ad-hoc python-docx scripts for any .docx task.

PDF operations via a plan-driven pipeline (analyze → plan → apply → Gate A validate → report). Use this skill whenever the user mentions PDF files, scanned documents, OCR, merging or splitting PDFs, extracting text or tables, filling PDF forms, adding watermarks, encrypting or decrypting, extracting images, rotating pages, or reading metadata. Always use this skill for any .pdf task rather than ad-hoc scripts.

Microsoft PowerPoint / PPTX processing via a plan-driven pipeline with OOXML structure validation (Gate A). Use this skill whenever the user mentions PowerPoint, PPTX, slide decks, presentations, pitch decks, template filling, or needs to create slides from scratch, edit existing decks, replace text, fill placeholders, reorder/delete slides, or generate thumbnails. Always use this skill for any .pptx task.

Microsoft Excel / XLSX processing via a plan-driven pipeline with Gate A (structure) and Gate B (formula correctness) validation. Use this skill whenever the user mentions Excel, XLSX, spreadsheets, workbooks, financial models, budgets, forecasts, data entry, template filling, named ranges, formulas, charts, pivot tables, or any .xlsx task. Always prefer this skill over ad-hoc openpyxl scripts.

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Use whenever the task involves project documentation, architecture, design decisions, implementation plans, specs, worklogs, project memory, or any durable knowledge that should live in the repo. This includes reading or writing docs, querying prior decisions, checking doc health, reviewing history, updating AGENTS.md / CLAUDE.md / ARCHITECTURE.md, or organizing project knowledge. If the repo has AGENTS.md, CLAUDE.md, or .harnesskit/, treat HarnessKit as the default documentation workflow: read the entrypoint first, then use the CLI when query, context, checks, indexing, or history are useful.