代码评审
自动化代码审查与分析
bison-strategy
Senpi-ai
BISON v3.0.1 — Conviction Holder. Patient multi-asset (BTC/ETH/SOL) conviction trader. MIN_SCORE 11 across 9 components (4H/1H structure, momentum, SM alignment, funding, volume, OI proxy, RSI). Conviction- scaled margin tiers (25%/31%/37%) and 7-10× leverage. DSL is wide by design — time-cuts DISABLED — so a real directional thesis can run multiple days into the move. Few trades. Long holds. Big moves. v3.0.1 ships a race-window dedup cache that eliminates the ENGINE_FAILURE retry noise on already-held assets, plus a doubled DSL exit interval to throttle REDUCE_ONLY spam when runtime position-state lags HL.
reverse
AsiaOstrich
"[UDS] System archeology — reverse engineer code across Logic, Data, and Runtime dimensions"
coverage
AsiaOstrich
"[UDS] Analyze test coverage and provide recommendations"
Testing Guide
AsiaOstrich
Testing pyramid and test writing standards for UT/IT/ST/E2E. Supports ISTQB and Industry Pyramid frameworks. Use when: writing tests, discussing test coverage, test strategy, or test naming. Keywords: test, unit, integration, e2e, coverage, mock, ISTQB, SIT, 測試, 單元, 整合, 端對端.
release
AsiaOstrich
"[UDS] Guide release process and changelogs"
discover
AsiaOstrich
"[UDS] Assess project health, architecture, and risks before adding features"
review
AsiaOstrich
"[UDS] Perform systematic code review with checklist"
checkin
AsiaOstrich
"[UDS] Pre-commit quality gates verification"
sdd
AsiaOstrich
"[UDS] Create or review specification documents for Spec-Driven Development"
Project Structure Guide
AsiaOstrich
Guide for organizing project directories following language-specific best practices. Use when: creating projects, reorganizing structure, adding modules, setting up builds. Keywords: project, structure, directory, layout, gitignore, scaffold, 專案結構, 目錄.
upgrade-simple-icons
wei
Upgrade simple-icons to the latest version and preserve any removed icons by sourcing them from the previous version into common/icons/customIcons.ts and updating icon mappings. Use whenever bumping or upgrading simple-icons in this repo.
team-issue
catlog22
Unified team skill for issue resolution. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team issue".
review-cycle
catlog22
Unified multi-dimensional code review with automated fix orchestration. Supports session-based (git changes) and module-based (path patterns) review modes with 7-dimension parallel analysis, iterative deep-dive, and automated fix pipeline. Triggers on "workflow:review-cycle", "workflow:review-session-cycle", "workflow:review-module-cycle", "workflow:review-cycle-fix".
team-ultra-analyze
catlog22
Unified team skill for deep collaborative analysis. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team ultra-analyze", "team analyze".
review-code
catlog22
Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".
team-uidesign
catlog22
Unified team skill for UI design team. All roles invoke this skill with --role arg for role-specific execution. CP-9 Dual-Track design+implementation.
team-frontend
catlog22
Unified team skill for frontend development team. All roles invoke this skill with --role arg. Built-in ui-ux-pro-max design intelligence. Triggers on "team frontend".
review-cycle
catlog22
Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-based (path patterns), or fix mode. Triggers on "workflow:review-cycle", "workflow:review-session-cycle", "workflow:review-module-cycle", "workflow:review-cycle-fix".
ccw-cli-tools
catlog22
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes.
claude-md-management
giuseppe-trisciuoglio
Provides comprehensive CLAUDE.md file management capabilities including auditing, quality assessment, and targeted improvements. Use when user asks to check, audit, update, improve, fix, maintain, or validate CLAUDE.md files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when CLAUDE.md needs to be created from scratch. This skill scans all CLAUDE.md files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.
github-pr-fix
holon-run
"Fix pull requests based on review feedback and CI failures. Use when: (1) Addressing PR review comments, (2) Fixing CI/test failures, (3) Resolving merge conflicts, (4) Implementing requested changes."
github-controller
holon-run
Controller skill for proactive GitHub automation. Run as a long-lived controller session, continuously consume events from HOLON_CONTROLLER_EVENT_CHANNEL, decide whether to run issue solve, PR review, PR fix, or no-op, then execute using existing GitHub skills.
project-pulse
holon-run
"Automated PM sync skill for GitHub-first projects. Use it to sync issue state from GitHub, maintain a local cache cursor, and generate priority/risk reports plus next actions for controller planning."
github-issue-solve
holon-run
"Solve GitHub issues by implementing features or fixes and creating pull requests. Use when: (1) Implementing features described in issues, (2) Fixing bugs reported in issues, (3) Creating PRs from issue requirements."