skills-collections

Use when bootstrapping or managing VPS agent environments: fresh install, add project, hex-relay redeploy, diagnostics, or fleet plan/apply.

Use when installing, verifying, or updating the shared VPS host runtime for Claude Code, Codex, MCP, and marketplace plugins.

Use when creating or verifying one project runtime on a prepared VPS, including god-session, provider credentials, and local dispatcher setup.

Use when deploying, redeploying, verifying, migrating, or syncing users for the hex-relay Telegram/API control plane on a VPS.

Use when inspecting health, drift, logs, auth, ports, systemd, tmux, or safe repair needs for one VPS project environment.

Reviews skills (D1-D11 + M1-M6 criteria) or .claude/commands for quality. Use when validating skill correctness before release.

Use when validating Stories, plans, or tasks through the evaluation platform with mandatory research, parallel evidence lanes, sequential merge, and bounded refinement. Modes: story | plan_review.

Use when an evaluation coordinator needs normalized findings from target artifacts and research evidence.

Use when an evaluation run needs review-driven documentation updates and a structured documentation summary.

Use when accepted findings require bounded repair changes and a structured repair summary.

Use when coordinating story quality evaluation with mandatory research, worker summaries, agent review, regression evidence, and bounded refinement.

Use when validating optimization plans through the evaluation platform with mandatory research, parallel agent evidence, sequential merge, and bounded refinement.

Drives a Story through full pipeline (tasks, validation, execution, quality). Use when executing a Story end-to-end from kanban board.

Creates slash commands from procedural doc sections. Use when transforming documentation prose into executable commands.

Executes Story tasks in priority order (To Review, To Rework, Todo). Use when Story has planned tasks ready for implementation.

Story-level quality gate with 4-level verdict (PASS/CONCERNS/FAIL/WAIVED) and Quality Score. Use when Story is ready for quality assessment.

Analyzes current or recent session for errors, inefficiencies, and improvement opportunities across skills, tools, hooks, and communication. Use after completing a task or periodically.

Installs agents, configures MCP servers, aligns marketplace plugins, creates and audits instructions. Use after setup or when agents/MCP/plugins need alignment.

Installs or updates Codex CLI and Claude Code. Use when CLI agents need installation or update.

Use when installing MCP packages and configuring Claude-side MCP registration, hooks, permissions, IDE extension mode, and migrations.

Use when installing or verifying this marketplace in Claude and Codex, aligning selected plugins, MCP settings, and Codex execution defaults.

Creates complete project documentation system (project docs, reference, tasks, tests). Use when bootstrapping docs from scratch or regenerating all.

Coordinates project documentation creation with single context gathering and project type detection. Use when generating project docs subset.

Creates root documentation files (AGENTS.md, CLAUDE.md, docs/README.md, standards, principles). Use for initial project doc setup.

Creates backend docs (api_spec.md, database_schema.md). Use when project has backend API or database.

RICE-scores Stories with market research and generates prioritization table. Use when Stories need business priority ranking for sprint planning.

Analyzes Story and builds optimal task plan (1-8 tasks), then routes to create or replan. Use when Story needs task breakdown or replanning.

Use when an evaluation run requires bounded iterative refinement with trace and cleanup evidence.

Reviews task implementation for quality, code standards, and test coverage. Use when task is in To Review. Sets task Done or To Rework.

Checks DRY/KISS/YAGNI/architecture compliance with quantitative Code Quality Score. Use when implementation tasks are Done and need quality scoring.

Auto-fixes low-risk tech debt (unused imports, dead code, commented-out code) with >=90% confidence. Use when audit findings need safe automated cleanup.

Analyzes application logs: classifies errors, checks log quality, maps stack traces to source. Use when logs need review after test runs or during development.

Plans automated tests (E2E/Integration/Unit) using Risk-Based Testing after manual testing. Use when Story needs a test task with prioritized scenarios.

Checks hierarchy, links, SSOT, compression, requirements compliance, freshness, legacy cleanup. Use when auditing documentation structure.

Checks document semantic content against SCOPE and project goals, coverage gaps, off-topic content, SSOT. Use when auditing documentation relevance.

Checks inline code documentation quality: WHY-not-WHAT, density, forbidden content, docstrings quality, actuality, legacy cleanup. Use when auditing comments and docstrings.

Verifies claims in .md files (paths, versions, counts, configs, endpoints) against codebase, cross-checks contradictions. Use when auditing docs accuracy.

Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Use when auditing build health.

Checks unreachable code, unused imports/variables/functions, commented-out code, unsupported patterns. Use when auditing dead code.

Bootstraps projects to production-ready structure. Use when creating new or transforming existing projects.