giang6283623

giang6283623/cursor-tip

Cursor rule Cursor

Visual process map for VAN QA mode (Technical Validation Entry Point).

giang6283623/cursor-tip

Cursor rule Cursor

Utility for VAN QA common validation fixes.

giang6283623/cursor-tip

Cursor rule Cursor

Utility for VAN QA mode transitions.

giang6283623/cursor-tip

Cursor rule Cursor

Utility for VAN QA validation reports.

giang6283623/cursor-tip

Cursor rule Cursor

Comprehensive guide for calling VAN QA rules.

giang6283623/cursor-tip

Cursor rule Cursor

Utility for remembering how to call VAN QA rules.

giang6283623/minimal-vibe-coding-kit

Skill Codex

Coordinate complex coding work through one verified controller and bounded native or cross-provider workers. Use when a user wants an active Codex, Claude, Cursor, OpenCode, Grok, Kimi, or other capable host to coordinate work through a native, automatically selected, or explicitly selected provider controller; choose…

giang6283623/minimal-vibe-coding-kit

Skill Codex

Use this skill to run an AgentShield-style review for Claude Code, Cursor, Codex, OpenCode, Grok, and Kimi repositories. Treat the repo root as the source of truth, then inspect agent surfaces before normal code review.

giang6283623/minimal-vibe-coding-kit

Skill Claude Code needs its repo

Run a metric-driven coding experiment loop. Use when improving a repo through repeated hypotheses, benchmark-guided changes, validation, keep/discard decisions, or safe workflow enhancement. Requires a goal, metric command, direction, editable paths, protected paths, and budget.

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Vet a request to bring something new into the repo - validate every URL and reference against official sources, check fit with existing rules, conventions, and skills, confirm anything unclear with the user, then integrate it and document how to use it.

giang6283623/minimal-vibe-coding-kit

Skill Claude CodeCodex

Deliver one observable behavior slice through Specify, Code, Clean, Architect, Harden, and Verify gates with proportional rigor and reproducible proof. Use when the user asks for extreme craftsmanship, clean-code delivery, TDD, architecture boundaries, or a high-confidence implementation workflow.

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Structured reasoning for complex coding work. Use when requirements are ambiguous, a design/debugging decision has multiple valid paths, or a large request needs to be split into safe implementable tasks.

giang6283623/minimal-vibe-coding-kit

Skill Codex

Plan, build, and verify an authorized website clone or migration through one front-loaded requirements session and an optional autonomous A-to-Z run. Use for small marketing or content sites, corporate sites, web applications, and small, medium, or large ecommerce projects from local screenshots, mock JSON, owner…

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Set the coding-explanation register. /coding-level N (0=ELI5, 1=Junior, 2=Mid, 3=Senior, 4=Tech Lead, 5=God); active until reinvoked. A project default may be recorded in backbone.yml conventions.customrules.

giang6283623/minimal-vibe-coding-kit

Skill Claude Code needs its repo

Propose daily improvements to project AI rules, skills, workflows, prompts, AgentShield posture, and backbone.yml. Use when the user asks to auto-enhance, update workflow, improve rules, or keep the vibe coding kit current. Propose diffs only; do not silently write.

giang6283623/minimal-vibe-coding-kit

Skill Codex

Design and run bounded dependency graphs for complex engineering work, with explicit artifacts, isolation, objective verification, resource budgets, retries, rollback, merge ownership, and human gates. Use when a task has at least three bounded work items, two or more genuinely independent branches, and plausible…

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Leave yourself a note before closing a multi-day task, then read it back at the start of the next session - it's the only memory that survives the gap.

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Generate styled Mermaid diagrams (31 types) from requirements - flowcharts, sequence, class, ER, state, Gantt, kanban, timeline, XY charts, architecture, and more. Also use when writing documentation (offer to include diagrams), when debugging or explaining a workflow (offer a visual flow map with risky zones…

giang6283623/minimal-vibe-coding-kit

Skill Codex

Safely inspect, plan, and update model, provider, reasoning, context, and compaction settings for Codex, Claude Code, Cursor, OpenCode, Grok Build, and Kimi Code from current official documentation. Use when setting up, comparing, migrating, or repairing provider configuration. Do not use for controller or worker…

giang6283623/minimal-vibe-coding-kit

Skill Claude Code needs its repo

Fan out 2-5 independent read-only analysis lanes across the repo using provider-ready native subagents or configured adapters, then merge the lane reports and verify them with a refutation pass. Use for repo-wide questions, large uncommitted-diff reviews, multi-doc reading, impact analysis, or consistency audits.…

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Guardrail workflow for shell changes that use path variables, remote base directories, repo folders, checkout repair, or destructive filesystem commands such as rm, mv, cp, rsync, find -delete, git clean, or git reset.

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

Sharpen a rough prompt into a precise one - same intent, sharper not longer - then execute the sharpened version immediately in the same turn.

giang6283623/minimal-vibe-coding-kit

Skill Codex

Govern complex agent work with an original four-role contract, independent challenge, explicit escalation signals, evidence-bound handbacks, and optional provider adapters. Use when the user asks for Proofline, role-separated orchestration, an empowered dissenting reviewer, multi-agent governance, or a…

giang6283623/minimal-vibe-coding-kit

Skill Claude Code

P0-P4 issue and task triage for vibe coding. Use when reviewing bugs, risks, feature requests, agent-surface changes, or deciding which work must happen first.