PROJECT ZERO

Advanced OSINT and social engineering orchestration. Focuses on target research, profile building, and the creation of highly convincing manipulation vectors.

中文简介正在准备中。当前显示原文说明。

Use when the user types [SWARM] to activate a multi-agent parallel workflow. Dispatches specialized subagents to work on independent tasks simultaneously, with progress tracking and result aggregation.

中文简介正在准备中。当前显示原文说明。

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

中文简介正在准备中。当前显示原文说明。

Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements. Runs quick_validate.py, checks line limits, verifies cross-references, and tests hook scripts. Use when skills have been added or modified and you want to verify everything passes before committing or submitting.

中文简介正在准备中。当前显示原文说明。

Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.

中文简介正在准备中。当前显示原文说明。

Use when Codex needs a spec-first TDD software workflow for feature builds, debugging, subagent development, code review, or finishing a development branch.

中文简介正在准备中。当前显示原文说明。

Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a `HEAL-` entry to `.learnings/HEALS.md` with proof. Use whenever a command, test, build, or lint fails or exits non-zero; on missing tooling, dependency/lockfile mismatch, wrong runtime version, venv or permission errors, port conflicts, dirty git state, or a missing `.env`; when the agent needs a helper or one-off script that doesn't exist yet; when an external API, tool, or MCP errors or rate-limits; or when a test flakes. Search `HEALS.md` by `Pattern-Key` first — most heals are recurrences, so increment `Recurrence-Count` instead of duplicating. Verify is mandatory: mark `pending-verify` honestly if sandboxed, `abandoned` if the fix can't be made to work. Pairs with `self-improvement` (which promotes recurring heals to durable memory) but owns the verify-before-persist discipline self-improvement doesn't.

中文简介正在准备中。当前显示原文说明。

Use when Codex needs self-reflection, correction logging, proactive follow-up, or persistent self-improvement memory after errors, user corrections, outdated knowledge, or better approaches.

中文简介正在准备中。当前显示原文说明。

Shell scripting reference — Bash syntax, redirections, process substitution, signal handling, debugging techniques. Use when writing shell scripts, troubleshooting Bash behavior, or automating system tasks.

中文简介正在准备中。当前显示原文说明。

Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Implements two feedback loops: the inner loop (detect, verify, recover) runs within a session via plan-interview, intent-framed-agent, context-surfing, verify-gate, self-healing (active recovery on failure), simplify-and-harden, and self-improvement. The outer loop (inspect, encode, regress-test) runs across sessions via learning-aggregator, harness-updater, and eval-creator. pre-flight-check bridges the two by surfacing accumulated knowledge — past heals and learnings — at session start. Handles standard, team-based, CI, and outer-loop pipeline variants. Does not replace individual skills; dispatches to them.

中文简介正在准备中。当前显示原文说明。

Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

中文简介正在准备中。当前显示原文说明。

Advanced identity and location fabrication. Supports spoofing of SMS, Messenger, Signal, WhatsApp, Snapchat, Twitter, Discord, Emails, and GPS coordinates.

中文简介正在准备中。当前显示原文说明。

Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern

中文简介正在准备中。当前显示原文说明。

Summarizes an agent session transcript into a concise briefing: goals, decisions, code changes, open questions. Use when starting a new session after a previous one, or when the user asks 'what did we work on?' or 'summarize the session'.

中文简介正在准备中。当前显示原文说明。

Autonomous system health monitoring, self-healing, resource optimization, and self-improvement workflows. Use when the user wants to implement automatic system health checks, auto-fix issues, optimize resources, reduce costs, schedule daily maintenance, or create a self-managing application. Triggers on: "self-healing", "auto-fix", "system health", "resource optimization", "cost reduction", "automated maintenance", "system monitoring", "self-improving", "auto-optimization", "daily workflow", "resource analysis", "load balancing".

中文简介正在准备中。当前显示原文说明。

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

中文简介正在准备中。当前显示原文说明。

Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is outdated or incorrect, (4) A better approach is discovered for a recurring task, (5) Receiving a Handoff block from self-healing (a recurring verified heal at Recurrence-Count >= 3) to distill into a memory file or new skill. For ACTIVE runtime failures where the agent needs to apply and verify a fix mid-task, use `self-healing` instead (it files HEAL- entries with proof; self-improvement promotes accumulated patterns). Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.

中文简介正在准备中。当前显示原文说明。

Use when Codex needs to capture learnings, errors, feature requests, or user corrections into .learnings so recurring workflows improve across sessions.

中文简介正在准备中。当前显示原文说明。

Complete setup and deployment workflow for Next.js applications with Prisma, Capacitor mobile apps, and production hosting. Use when the user wants to set up a new project, deploy to production, configure environments, run database migrations, or prepare an app for release. Triggers on: "setup the app", "deploy the app", "install dependencies", "run migrations", "configure environment", "build for production", "capacitor sync", "prepare for release", "run the setup script".

中文简介正在准备中。当前显示原文说明。

Shell scripting for automation, Bash/PowerShell one-liners, file manipulation, text processing, and system administration. Use when the user asks about writing shell scripts, Bash commands, text processing with awk/sed/grep, automation scripts, or system administration tasks.

中文简介正在准备中。当前显示原文说明。

Post-completion self-review for coding agents that runs simplify, harden, and micro-documentation passes on non-trivial code changes. Use when: a coding task is complete in a general agent session and you want a bounded quality and security sweep before signaling done. For CI pipeline execution, use simplify-and-harden-ci.

中文简介正在准备中。当前显示原文说明。

Meta-skill for creating new skills within the Quantum C2 project. Use when the user asks to create a skill, add a new skill, build a skill template, generate skill scaffolding, or extend the agent's capabilities with modular knowledge packages. Triggers on "create skill", "new skill", "build skill", "add skill", "skill template", "scaffold skill".

中文简介正在准备中。当前显示原文说明。

Use when Codex needs to select, spawn, and coordinate specialized agents across research, content, development, QA, analysis, documentation, personalization, or meta-agent workflows.

中文简介正在准备中。当前显示原文说明。

Periodically harden systems against zero-click and zero-day exploits. Triggers when user types "harden my system". Detects OS, applies comprehensive security hardening, configures defenses, and generates verification report. Supports Windows, macOS, and Linux with network and browser hardening. Use when hardening systems, applying security configurations, or defending against zero-click/zero-day exploits.

中文简介正在准备中。当前显示原文说明。