skills.rest
yeaboi-ai
yeaboi-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

mode-blueprints

Documents internal architecture blueprints for yeaboi's standup, retro, performance, and reporting modes.

4|Updated Mar 17, 2026
Search Tags:#architecture#sqlite#blueprints#pipelines#tui#standup#retro
One-click install
npx skills add https://github.com/yeaboi-ai/yeaboi.ai --skill mode-blueprints-yeaboi-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mode-blueprints
Source: https://github.com/yeaboi-ai/yeaboi.ai/tree/main/.claude/skills/mode-blueprints
Command: npx skills add https://github.com/yeaboi-ai/yeaboi.ai --skill mode-blueprints-yeaboi-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When modifying or extending yeaboi's standalone modes (Daily Standup, Retro, Performance, Reporting, Roadmap Intake), developers need to understand each mode's pipeline structure, SQLite schema versions, persistence stores, delivery channels, and export formats. This Skill provides the internal blueprints so changes stay consistent with the shared architectural conventions. ## Core Features & Use Cases - Mode Pipeline Documentation: Details each mode's engine, store, render/export structure, including the parse → fallback → format LLM convention and deterministic aggregation stages. - Schema & Persistence Reference: Records SQLite schema versions, frozen-dataclass artifacts in agent/state.py, and per-mode store tables. - Integration Checklists: Explains required additions when creating a new mode, such as FeatureTip discoverability entries and saved-sessions hub registration, including the tests that enforce them. - Use Case: When adding a new mode to yeaboi or modifying src/yeaboi/standup/, retro/, performance/, reporting/, or roadmap/, consult this Skill to follow the established blueprint and avoid failing surface-parity or saved-sessions tests. ## Quick Start Ask the AI to explain the standup mode pipeline or to guide you through adding a new mode following the mode-blueprints conventions.

Frequently Asked Questions about mode-blueprints

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add a new mode to yeaboi?▼

Create a self-contained package with engine, store, and render/export modules, define frozen-dataclass artifacts in agent/state.py, bump the SQLite schema in sessions.py, register a FeatureTip in _tips.py, and add a saved-sessions hub via _run_mode_hub. Tests in test_surface_parity.py fail until these exist.

What pipeline convention do yeaboi modes follow?▼

Modes are standalone pipelines, not LangGraph nodes, following the node parse → fallback → format convention with one get_llm()/track_usage() call. Deterministic logic like aggregation and confidence scoring stays in pure functions, with the LLM used only for prose synthesis.

How does the retro mode handle remote participants?▼

The retro mode runs a stdlib http.server bound to 127.0.0.1 and exposes it through a Cloudflare quick tunnel. Teammates join via a token-gated URL or join code, with per-visitor rate limiting keyed on the CF-Connecting-IP header.

Where are standup and retro runs persisted?▼

Each mode defines its own SQLite schema in sessions.py: standup uses schema v6 with standup_config, standup_history, and standup_updates tables, while retro uses schema v7 with a retro_history table. Exports are written as Markdown and HTML under ~/.yeaboi/exports/.

Why are yeaboi mode pipelines not LangGraph nodes?▼

Scheduled headless runs must be fast and checkpoint-free, so engines like run_standup() call get_llm() directly instead of compiling a graph. Activity gathering and confidence scoring remain deterministic function calls.

Related Skills

Explore More Software Engineering Skills→
KhaledMKhaledKhaledMKhaled

package-management

Install and manage language runtimes, packages, and Nix system dependencies.

Community
Intermediate
yusifengyusifeng
192

formax-semantics-parity-workflow

Enforce canonical cross-surface semantics across TUI, app-server, and Web surfaces.

Community
Advanced
matthew-johnsonmatthew-johnson

gitnexus-explorer

Index a codebase into a navigable knowledge graph with GitNexus.

Community
Intermediate
Jin9Jin9

developing-langgraph-workflows

Implement, refactor, and review LangGraph v1.x StateGraph workflows with typed state and safe persistence.

Community
Intermediate