comet-design
25Skill Claude CodeCodex
A writing workflow for creating or restoring a detailed technical design document. It is used only during the specified Comet design workflow.
not rated 2
changed 1mo ago A 44 tokens
comet-hotfix
26Skill Claude CodeCodex
A restricted Comet workflow for fixing an existing behavior bug.
not rated 2 1mo ago A 48 tokens
comet-native
27Skill Claude CodeCodex
A workflow helper for Native changes, guiding work through shaping the change, building it, checking it, and archiving it.
not rated 2 1mo ago A 47 tokens
comet-open
28Skill Claude CodeCodex
A skill for creating or resuming an OpenSpec change, where OpenSpec is a structured way to describe proposed software work. It fills in the proposal, design, tasks, and configuration files.
not rated 2
changed 1mo ago A 49 tokens
comet-tweak
29Skill Claude CodeCodex
A lightweight change workflow for Comet that handles a small or medium change described by one OpenSpec change.
not rated 2 1mo ago A 52 tokens
comet-verify
30Skill Claude CodeCodex
A Comet-specific verification step, where Comet refers to the surrounding change-management system. It is used only when the user or Comet routes work to this stage.
not rated 2
changed 1mo ago A 48 tokens
comet
31Skill Claude CodeCodex
A project-specific route for opening or restoring an active Comet change. Comet appears to be a project feature with two possible entry points: Native and Classic.
not rated 2
changed 1mo ago A 36 tokens
Skill Claude CodeCodex
When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep dive,' 'who are my competitors,'…
not rated 2 1mo ago A 128 tokens
Skill Claude CodeCodex
Use when analyzing popular articles or reference materials to extract reusable topics, titles, structures, arguments, cases, and remix directions for original content creation.
not rated 2 1mo ago A 32 tokens
Skill Claude CodeCodex
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content…
not rated 2 1mo ago A 143 tokens
Skill Claude Code
Restore working context saved earlier by /context-save. Loads the most recent saved state (across all branches by default) so you can pick up where you left off — even across Conductor workspace handoffs. Use when asked to "resume", "restore context", "where was I", or "pick up where I left off". Pair with…
not rated 2 1mo ago A 107 tokens
context-save
36Skill Claude Code
Save working context. Captures git state, decisions made, and remaining work so any future session can pick up without losing a beat. Use when asked to "save progress", "save state", "context save", or "save my work". Pair with /context-restore to resume later. Formerly /checkpoint — renamed because Claude Code treats…
not rated 2 1mo ago A 96 tokens
copy-editing
37Skill Claude CodeCodex
When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too…
not rated 2 1mo ago A 142 tokens
Skill Claude CodeCodex
When the user wants to conduct, analyze, or synthesize customer research. Use when the user mentions "customer research," "ICP research," "talk to customers," "analyze transcripts," "customer interviews," "survey analysis," "support ticket analysis," "voice of customer," "VOC," "build personas," "customer personas,"…
not rated 2 1mo ago A 179 tokens
Skill Claude CodeCodex
Read research outline, launch independent agent for each item for deep research. Disable task output.
not rated 2 1mo ago A 24 tokens
Skill Claude CodeCodex
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
not rated 2 1mo ago A 23 tokens
Skill Claude CodeCodex
Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
not rated 2 1mo ago A 27 tokens
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
not rated 2 1mo ago A 26 tokens
Skill Codex
Use when converting .docx files to Markdown, especially when the user wants heading levels, tables, figure captions, and embedded images preserved for Obsidian or other Markdown note systems. Trigger on requests like "docx to markdown", "save to Obsidian", "keep images", "keep heading levels", or when generic…
not rated 2 1mo ago A 85 tokens
docx
44Skill Claude CodeCodex
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
not rated 2
changed 1mo ago A 168 tokens
Skill Codex
Generate directly viewable Obsidian Excalidraw canvas files from structured content. Use when the user wants Codex or Claude Code to organize ideas, frameworks, maps, workflows, product diagrams, capability maps, architecture diagrams, or similar content into a final .excalidraw.md / .excalidraw canvas that opens as…
not rated 2 1mo ago A 85 tokens
Skill Claude CodeCodex
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
not rated 2
changed 1mo ago A 22 tokens
find-skills
47Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
not rated 2 1mo ago A 67 tokens
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
not rated 2 1mo ago A 27 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: