Prompts
Prompt engineering and templates
implementing-as-tachikoma
by sumik5
Operates as Tachikoma Agent (Implementation Worker) performing actual code implementation. Use when receiving task assignments from Claude Code for implementation work, test creation, or documentation. Adapts to frontend, backend, or testing roles based on task assignment.
pan-code-review
by eltmon
Orchestrated parallel code review with automatic synthesis
pan-memory
by eltmon
"pan memory <subcommand> — search and inspect Overdeck memory observations, status, reset markers, summaries, and health"
starlight-si
by frankxai
Codex-native Starlight Intelligence /si router for choosing local agent lanes, building handoff packets, and running explicit read-only fanout or council dispatch across Codex, Claude, Grok, Antigravity, OpenCode, DeepAgent, and image tools. Use when prompts mention /si, the installed /si prompt shortcut, mobile alias si:, starlight si, route, dispatch, fanout, council, which agent/tool, local CLI lanes, or Starlight multi-agent orchestration.
real-mecha
by ShinChven
Converts 2D/anime mecha art into photorealistic 3D/real-world visualizations with high-fidelity material textures.
video-prompting
by Square-Zero-Labs
Draft and refine prompts for video generation models (text-to-video and image-to-video). Use when a user asks for a "video prompt" or a model-specific prompt such as Ovi, Sora, Veo 3, Wan 2.2, or LTX-2, including requests like "text-to-video prompt", "image-to-video prompt", or "write a prompt for [model]".
savethetokens
by Redclawww
Reduce Claude Code token burn with proactive compacting, task-scoped sessions, checkpoint files, tiered docs, and relevance-based context pruning. Use when a user explicitly asks to reduce context usage/cost, run token benchmarks, or optimize CLAUDE.md. Do not use to expand product scope or skip correctness checks.
photo-restoration
by ShinChven
Restores vintage and blurry photos to high-definition 8k images while preserving identity.
agent-task-splitter
by WenyuChiou
Use when the user asks to split a goal across Claude, Codex, or Gemini (gemini requests are rerouted - lane deprecated); plan a multi-agent run; break work into parallel agent tasks; or decompose a large task that needs bounded context handoffs. This is the generic multi-agent task splitter — writes .coord/plan.yml (a DAG) plus per-agent task files. NOT for research-domain routing that touches .research/, .paper/, or Zotero/Obsidian/NotebookLM ingest pipelines — for those, use research-hub-multi-ai instead (different artifact .coord/multi_ai_plan.md, research-hub-aware reconciliation).
baoyu-danger-gemini-web
by xuanxuan1983
Image generation skill using Gemini Web. Generates images from text prompts via Google Gemini. Also supports text generation. Use as the image generation backend for other skills like cover-image, xhs-images, article-illustrator.
daily
by ballred
Create daily notes and manage morning, midday, and evening routines. Structure daily planning, task review, and end-of-day reflection. Use for daily productivity routines or when asked to create today's note.
project
by ballred
Create, track, and archive projects linked to goals. The bridge between goals and daily tasks. Use for project creation, status dashboards, and archiving completed work.
skill-forge
by WilliamSaysX
Automated skill creation workshop with intelligent source detection, smart path management, and end-to-end workflow automation. This skill should be used when users want to create a new skill or convert external resources (GitHub repositories, online documentation, or local directories) into a skill. Automatically fetches, organizes, and packages skills with proactive cleanup management.
onboard
by ballred
Interactive vault setup and context loading. On first run, personalizes your vault. On subsequent runs, loads full context. Use at start of session or when Claude needs full vault context.
adopt
by ballred
Scaffold the PKM system onto an existing Obsidian vault. Scans your vault structure, maps folders interactively, and generates configuration — no template required.
weekly
by ballred
Facilitate weekly review process with reflection, goal alignment, and planning. Create review notes, analyze past week, plan next week. Use on Sundays or whenever doing weekly planning.
upgrade
by ballred
Update vault to the latest version of obsidian-claude-pkm. Creates backup, shows diffs, preserves your content. Use when a new version is available.
obsidian-vault-ops
by ballred
Read and write Obsidian vault files, manage wiki-links, process markdown with YAML frontmatter. Use when working with vault file operations, creating notes, or managing links.
solo-founder-gtm
by chadboyda
"When the user is a solo founder building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions 'solo founder,' 'one-person startup,' 'solopreneur,' 'bootstrapped,' 'no team,' 'AI agents as team,' 'scaling without hiring,' 'founder-led sales,' 'lean GTM,' 'one-person company,' or 'no employees.' This skill covers the complete solo founder GTM playbook from stack selection through agent team design, revenue-stage transitions, time allocation, and when to finally hire."
status
by IgorGanapolsky
Show the latest Codex bridge artifact metadata from Claude Code. Use when the user asks whether the bridge already ran, what mode it used, or where the result was saved.
setup
by IgorGanapolsky
Validate that the Codex bridge plugin is ready inside Claude Code. Use when the user asks to install, configure, or sanity-check Codex review from Claude.
adversarial-review
by IgorGanapolsky
Run a skeptical Codex review from Claude Code that hunts for hidden regressions, unsafe assumptions, and release risk. Use before merges, deploys, migrations, or other risky changes.
second-pass
by IgorGanapolsky
Hand the current task or repo state to Codex for an independent second pass from inside Claude Code. Use when the user explicitly wants another agent to take a shot after Claude's first pass.
thumbgate-feedback
by IgorGanapolsky
Capture thumbs up/down feedback into structured memories and prevention rules. Require one sentence of why before claiming memory promotion. Use when user gives explicit quality signals about agent work (e.g. "that worked", "that failed", "thumbs up/down"). Do NOT use for general questions, code generation, file operations, or any task that is not explicit feedback on prior agent output.