Skill Claude CodeCodex
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki".
Skill Claude CodeCodex
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".
Skill Claude CodeCodex
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow".
Skill Claude CodeCodex
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?".
Skill Claude CodeCodex
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".
Skill Claude CodeCodex
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file".
Skill Claude CodeCodex
Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes…
Hook Claude Code
Runs when a session starts on startup, resume, clear and compact, executing rule-context-hook.py via bash with --show-toplevel, --workspace and --platform. From buiphucminhtam/forgewright.
Hook Claude Code
Runs when a subagent starts, executing rule-context-hook.py via bash with --show-toplevel, --workspace and --platform. From buiphucminhtam/forgewright.
Hook Claude Code
Runs when the agent finishes a response, executing stop-gate.sh via bash with --platform. From buiphucminhtam/forgewright.
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, SubagentStart, Stop).
Agent Cursor
Translates natural language chat into structured pipeline requests. Use at the start of every conversation when the user describes what they want. Powered by prompt-master methodology.
Agent Cursor
Reviews code quality, architecture conformance, naming conventions, and error handling. Use after spec-reviewer passes. Requires full context to assess broad codebase patterns.
Agent Cursor
Security specialist for read-only OWASP audit. Use when implementing auth, payments, or handling sensitive data. Audits code for vulnerabilities without modifying anything.
Agent Cursor
Validates task delivery against CONTRACT.json acceptance criteria. Use after workers complete parallel tasks. Performs spec compliance check only — not quality review.
Agent Cursor
Validates completed work. Use after tasks are marked done to confirm implementations are functional. Runs mandatory checklist before any approval.
Instructions file CodexOpenCode
AGENTS.md instructions for buiphucminhtam/forgewright, covering forgewright kernel lite — antigravity / cursor, forgewright kernel lite — entry, hard rules (the only 6), senior delivery standard (always on) and boot sequence.
Instructions file
Claude Code instructions for buiphucminhtam/forgewright, covering forgewright kernel lite — claude code, forgewright kernel lite — entry, hard rules (the only 6), senior delivery standard (always on) and boot sequence.
Instructions file Gemini CLI
Gemini CLI instructions for buiphucminhtam/forgewright, covering forgewright kernel lite — gemini, forgewright kernel lite — entry, hard rules (the only 6), senior delivery standard (always on) and boot sequence.
Skill Claude CodeCodex
This framework guidance is immutable during the application task.
Skill Claude CodeCodex
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || echo "=== 3D Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat…
Skill Claude CodeCodex
Source: This skill is part of Phase 1 (Quick Wins) of the Forgewright improvement plan (v9). It ensures Forgewright tests itself systematically before shipping changes.
Skill Claude CodeCodex
You are the Accessibility Engineering Specialist. You ensure digital products are usable by everyone, including people with visual, auditory, motor, and cognitive disabilities. You audit against WCAG 2.2 standards (AA minimum, AAA preferred), implement ARIA patterns, ensure keyboard navigability, test with screen…
Skill Claude CodeCodex
You are the AI Behavior Engineer Specialist. You design and implement intelligent agent systems that make NPCs feel alive and responsive. You master behavior trees, GOAP, utility AI, pathfinding, perception systems, and group behaviors.