Skill Claude CodeCodex
Use when creating a Discord bot for ThisCodex, especially when the user wants Codex to drive the Discord Developer Portal through a connected browser-automation MCP, create the application, enable required intents, receive the token safely, and invite the bot. Also use when browser automation is missing and Playwright…
Skill Claude CodeCodex
Use when the user is stuck, confused, or asks what ThisCodex can do — friendly diagnosis of where they got stuck, step-by-step recovery in plain language (Korean or English, following the user's language), hands-on browser assistance via playwright MCP when available (computeruse/browseruse are not callable in codex…
Skill Claude CodeCodex
Use when writing, generating, refining, reviewing, or being asked for ANY prompt aimed at an LLM (Claude / GPT / Gemini / Codex), or when building GPTs / Gems system instructions, or when a task is fact-check / research / image-generation prompting. Produces structured, framework-grounded prompts instead of ad-hoc…
Skill Claude CodeCodex
Use when the user asks for /thiscodex setup, step-by-step ThisCodex onboarding, tmux-only Discord bot launch guidance, YOLO/safe-mode selection, or progress reporting cadence setup.
Skill Claude CodeCodex
Use when creating a Slack bot that bridges to local AI engines (Claude Code / Codex CLI). Covers Slack CLI authentication (near-full automation), app creation, engine-prefix routing, per-bot persona loading via CLAUDE.md/AGENTS.md, per-bot acknowledgement reactions, thread-scoped conversation continuity (claude…
Skill Claude CodeCodex
Use when running ThisCodex feature smoke tests through the /test dispatcher for memory, tmux, GraphRAG, meetings, rules, hooks, or installer behavior.
Skill Claude CodeCodex
Use when setting up an OpenAI Codex CLI agent as a persistent Discord bot with Claude-Code-equivalent persona/vault discipline, when porting Claude Code skills or rules to Codex, or when wiring multi-agent conventions (cross-bot addressing, meeting threads, SessionStart roster, progressive-disclosure rules) so Claude…
Plugin Claude Code
Plugin marketplace listing 15 plugins: prompt-engineering-skills, km, tofu-at, skills-2.0-upgrade, qwen3-tts-claude-skill.
Plugin Claude Code
Research pipeline that decides depth after the evidence: source-grade weighted scoring, worker-hidden thresholds, and type-driven investigation frames.
MCP server Claude CodeCodexCursor
MCP server "searchflow" as configured in treylom/deep-research. Runs ${CLAUDE_PLUGIN_ROOT}/skills/searchflow/scripts/mcp-server.mjs with node.
Instructions file
Repository instructions for deep-research, a project that provides a structured research process called SearchFlow. They cover installation, required tools, and how to copy the complete supporting files.
Agent
A deprecated research worker whose behaviour changes according to the role it receives, such as web searching, academic searching, cross-checking, synthesis, or quality review.
Command
A deprecated command that passes its arguments to SearchFlow, the replacement research workflow. The provided material does not describe the full SearchFlow process.
Command
A research workflow command that investigates a question, gathers sources, checks their quality, and produces a structured report. Its description is partly in Korean, so the exact user-facing process cannot be fully confirmed here.
Skill Claude CodeCodex
Use when a research question needs sourced, cross-checked findings — fact-checks, market/company/tech/policy research, comparisons, or open exploration. Routes the question to a research type, spawns per-frame investigators, grades sources, and re-investigates the weakest axis until a deadline or round cap. Replaces…