skills_sync
Align Codex-native skills with documented skills safely.
trust_layer_tdd
Enforce test-first changes and debug based on failing tests.
update_architecture
Refresh architecture maps after structural changes.
update_kit
Update this documentation kit safely from upstream.
write_adr
Document architectural decisions with context and consequences.
debug-fix-first-run-resolution
Root-cause debugging and first-run bug fixes with reproduction-first workflow, explicit hypotheses, disciplined instrumentation, minimal changes, and validated fixes (repro + tests + feature verification). Use when diagnosing a bug and delivering a verified fix instead of shotgun debugging.
Create Backend Service
Use this skill when adding new backend functionality (API endpoints + business logic).
Create Interactive Menu
Use this skill when creating dropdowns, context menus, or overlays that need a polished UX (open/close animation, click-outside, Escape, etc.).
Create New Indicator
Use this skill when you need to add a new Python indicator to AERA.
ast_injection
Use AST-aware edits to reduce syntax errors and maintain structure.
archaeologist
Detect legacy patterns and guide compatibility decisions.
action_logger
Keep an audit trail of changes, commands, and verification.
agent_manager
Automatically manage agent lifecycle, proposals, and registry.
analyze_repo_capabilities
Detect repo tooling and patterns, then record a dynamic manifest.
autonomy_kickoff
Run the full autonomy bootstrap with minimal questions.
backlog_curator
Maintain a lightweight backlog of high-value tasks discovered during work.
cartographer
Maintain living architecture maps and interaction flows.
clarify_first
Ask clarifying questions and get approval before implementation.
command_guard
Enforce .agentpolicy rules before executing commands.
context_compactor
Compress long-run context into handoff, backlog, and action logs.
detect_commands
Infer and verify install/test/lint/build commands for the repo.
execplan
Create and maintain PLANS.md for long-running or risky tasks.
full_auth
When explicitly authorized, execute end-to-end with a phased plan in one run until Definition of Done is met.
handoff_writer
Write a compact HANDOFF.md snapshot to restore context after session resets.
impact_analyzer
Analyze and document the impact of planned changes.
non_destructive_bootstrap
Install agent docs without overwriting or deleting existing content.
pattern_miner
Extract recurring patterns from action logs and propose automations.
quality_gates
Enforce Definition of Done checks from QUALITY_GATES.md.
refactor_gate
Ask whether to proceed with refactoring after architecture mapping.
repo_indexer
Build and maintain a fast navigation index of the repo.
response_style_selector
Ask the user to pick a response style and persist the preference.
safe_refactor_migration
Plan and execute large refactors with shadow mode and rollback.
safety_validation
Validate changes against .agentignore before commit.
shadow_coder
Build parallel architectures safely without breaking current behavior.
size_guard
Enforce line budgets and rotate or split large context files.
skills_auditor
Detect incorrectly installed skills and report issues.
Create Strategy (LEAN)
Use this skill when you need to add a new LEAN QCAlgorithm strategy in Python.
Create UI Component
Use this skill when creating a new React UI component. It provides a consistent Lumina-style template.
cupertino-ui-consistency
Maintain Cupertino + Lumina visual consistency for the AERA frontend. Use when creating or modifying UI, CSS/tokens, layouts, components, menus/overlays, tables, charts, or interaction states in this repo.
frontend-design-lumina
Design or redesign frontend interfaces in quant-lab with high-quality, production-ready UI/UX while preserving Lumina identity. Use when the user asks for UI polish, visual redesign, page/layout revamp, dashboard/chart UX improvements, interaction quality upgrades, or anti-generic "AI-looking" frontend output.
Plan Task (Architectural)
Use when the user asks for a plan or the task is complex/ambiguous. Enforces AGENTS.md workflow and encourages loading other relevant skills.
Refactor/Slice File
Use this skill when a file exceeds ~350 lines (target) / approaches the 500-line hard cap, or has mixed responsibilities (UI + Logic + Types).
Sync Documentation
Use this skill at the end of a task to ensure documentation matches the code.
verify-debug-mode
Confirm a requested feature change via AERA Debug mode (Debug view, console, logs). Use when validation must happen through Debug UI or when you need to add debug-only probes/commands to make a change observable.
Verify Changes
Use this skill after implementing code to verify correctness before notifying the user.