PostHog CLI Queries
debugtheworldbot/keyStats
Runs HogQL queries against this project's PostHog data from the terminal using posthog-cli, with bundled scripts for dashboard metadata the CLI itself has no command for.
The six-section MiniMax H3 full-reference (Ref2VA) contract the APNext H3 Reference Prompt Writer nodes emit - subjectdefinitions, summary, retentionanalysis, detaileddescription, overallsoundscape…
Install H3 Ref2va
$ npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dagthomas/comfyui_dagthomas h3-ref2va --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dagthomas/comfyui_dagthomas.git skills-src && mkdir -p .claude/skills && cp -r skills-src/data/h3/skills/h3-ref2va .claude/skills/h3-ref2va && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "h3-ref2va" agent skill from https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2va into .claude/skills/h3-ref2va/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h3-ref2va", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2vaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dagthomas/comfyui_dagthomas h3-ref2va --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dagthomas/comfyui_dagthomas.git skills-src && mkdir -p .agents/skills && cp -r skills-src/data/h3/skills/h3-ref2va .agents/skills/h3-ref2va && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "h3-ref2va" agent skill from https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2va into .agents/skills/h3-ref2va/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h3-ref2va", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dagthomas/comfyui_dagthomas h3-ref2va --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dagthomas/comfyui_dagthomas.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/data/h3/skills/h3-ref2va .cursor/skills/h3-ref2va && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "h3-ref2va" agent skill from https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2va into .cursor/skills/h3-ref2va/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h3-ref2va", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dagthomas/comfyui_dagthomas.git --path data/h3/skills/h3-ref2va--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dagthomas/comfyui_dagthomas h3-ref2va --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dagthomas/comfyui_dagthomas.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/data/h3/skills/h3-ref2va .gemini/skills/h3-ref2va && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "h3-ref2va" agent skill from https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2va into .gemini/skills/h3-ref2va/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h3-ref2va", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dagthomas/comfyui_dagthomas h3-ref2vaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dagthomas/comfyui_dagthomas.git skills-src && mkdir -p .github/skills && cp -r skills-src/data/h3/skills/h3-ref2va .github/skills/h3-ref2va && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "h3-ref2va" agent skill from https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2va into .github/skills/h3-ref2va/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h3-ref2va", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dagthomas/comfyui_dagthomas h3-ref2va --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dagthomas/comfyui_dagthomas.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/data/h3/skills/h3-ref2va .opencode/skills/h3-ref2va && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "h3-ref2va" agent skill from https://github.com/dagthomas/comfyui_dagthomas/tree/master/data/h3/skills/h3-ref2va into .opencode/skills/h3-ref2va/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "h3-ref2va", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
h3-ref2va- GitHub stars
- 290
- Token cost
- ~1.2k tokens
- SKILL.md length
- 564 words
- Files
- 4 (incl. references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
The six-section MiniMax H3 full-reference (Ref2VA) contract the APNext H3 Reference Prompt Writer nodes emit - subjectdefinitions, summary, retentionanalysis, detaileddescription, overallsoundscape…
- Tasks that involve Product analytics
- SKILL.md covers How the node's images map, The reference_role directive, Roles and Fields, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
H3 Ref2va is an agent skill from dagthomas/comfyui_dagthomas. The six-section MiniMax H3 full-reference (Ref2VA) contract the APNext H3 Reference Prompt Writer nodes emit - subjectdefinitions, summary, retentionanalysis, detaileddescription, overallsoundscape, nondiegeticmusic - with <Subject N/<Picture N/<Video N/<Audio N roles, the retention vocabulary, summary task types, how the node's image1..image9 sockets become <Picture 1..<Picture 9, what its referencerole dropdown means, and reference-controls-HOW / user-controls-WHAT style transfer. Load with h3-prompt-director…
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/07_REF2VA_FULL_REFERENCE_GUIDE.md`, `references/13_REF2VA_GOLD_EXAMPLES.md` and `references/16_H3_REF2VA_STYLE_TRANSFER_LAB.md`).
It sits in Data & Analytics, covering Product analytics. It works with MiniMax. The repository describes itself as: comfyuidagthomas - Advanced Prompt Generation and Image Analysis. The licence is MIT.
When your agent uses it
- Tasks that involve Product analytics
Example prompts
- “/h3-ref2va”
What it can do on your machine
Read from SKILL.md and the folder at commit 469fdd6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
H3 Ref2va loads about 1.2k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 157 tokens; SKILL.md has 564 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from dagthomas/comfyui_dagthomas at commit 469fdd6, republished under its MIT licence (© dagthomas). 564 words, ~1,232 tokens.
Download SKILL.mdSave it as
.claude/skills/h3-ref2va/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- h3-ref2va
- description
- The six-section MiniMax H3 full-reference (Ref2VA) contract the APNext H3 Reference Prompt Writer nodes emit - subject_definitions, summary, retention_analysis, detailed_description, overall_soundscape, non_diegetic_music - with <Subject N>/<Picture N>/<Video N>/<Audio N> roles, the retention vocabulary, summary task types, how the node's image_1..image_9 sockets become <Picture 1>..<Picture 9>, what its reference_role dropdown means, and reference-controls-HOW / user-controls-WHAT style transfer. Load with h3-prompt-director whenever reference media drives identity, style, motion, camera, performance or voice.
H3 Ref2VA (full-reference mode)
This is what the APNext H3 Reference Prompt Writer and APNext H3 Claude Code Reference Writer nodes expect back. No alignment line. Six labels, exactly once, in this order,
each followed by one blank line - the node splits on them:
subject_definitions:
summary:
retention_analysis:
detailed_description:
overall_soundscape:
non_diegetic_music:How the node's images map
The node has sockets image_1 ... image_9, mirrors ComfyUI's MiniMax H3 Reference to
Video node, and passes each image back out on the same-numbered output. So:
- Attached image k IS
<Picture k>. Never renumber, skip or merge pictures; the video model will receive them in that order. - Videos and audio cannot be attached to the writer node. When
reference_notesdescribe them ("Video 1 is the dance clip", "Audio 1 is her voice"), define<Video N>/<Audio N>from the notes in the order given, and treat those notes as fact. - Only the first frame of a batched input counts as that reference.
The reference_role directive
The node states how to treat the images:
- Auto - decide per image: a
<Subject N>for reusable visible content, a standalone<Picture N>for a concrete frame or composition anchor, or only a source cited inside another item's definition. - Subject - one
<Subject N>per image, citing<Picture k>inside the definition; no standalone picture entries. - Picture - one standalone
<Picture N>per image, stating which shot and position (first frame, keyframe, last frame) it anchors. - Style reference only - no standalone
<Picture N>entries; fold the style provenance into the relevant<Subject N>definitions and the style sentence before[Shot 1]. - Storyboard - standalone
<Picture N>entries stating which shots they map to and what planning information they carry.
Roles
<Subject N>= reusable visible reference content, or reusable visual / performance / style attributes. One line per subject, sourced from the pictures, videos or audio it draws on.- Standalone
<Picture N>= frame, keyframe or composition anchor only. <Video N>= editing, continuation, camera, cuts, rhythm or temporal structure.<Audio N>= copied or referenced audio.
Reference controls HOW; the user's idea controls WHAT. Protect the user's identity, anatomy, clothing, props, setting, composition, action, dialogue, visible text and story from leaking in from the source. When only a style is wanted, do not import recognizable IP characters, costumes, logos, products, vehicles or franchise silhouettes.
For a concept-only still with maximum freedom, define a <Subject N> sourced from the
picture, mark it weak_reference, retain only the stated premise, and explicitly release
composition, palette, design, lighting and animation treatment.
Show full SKILL.md (162 more words)Show less
Fields
subject_definitions:one line per tracked item.summary:a short paragraph that begins with the applicable task types in square brackets, joined by+:keyframe completion,reference generation,video editing,video continuation,audio reuse,audio reference. The node'stask_typedirective fixes this prefix when it is not Auto.retention_analysis:one line per item, using only visual -fully_preserved,partially_preserved,attribute_transfer,weak_referenceaudio -fully_copy,partially_copy,reference,weak_referenceand saying what is kept and what is released.detailed_description:one or two style sentences, then[Shot 1]and one continuous audiovisual timeline. Aim for the node'sword_target(350-500 words is the norm for generation tasks); go longer only when the references demand it.overall_soundscape:andnon_diegetic_music:as in the core skill.
Reference library
| Read this | When |
|---|---|
13_REF2VA_GOLD_EXAMPLES.md | Always for a first Ref2VA prompt in a session: full six-section examples with retention markers. |
07_REF2VA_FULL_REFERENCE_GUIDE.md | Roles, retention vocabulary and section contracts in detail. |
16_H3_REF2VA_STYLE_TRANSFER_LAB.md | A video reference supplies style, motion, editing rhythm or technique - keep WHAT separate from HOW. |
© dagthomas, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in data/h3/skills/h3-ref2va of dagthomas/comfyui_dagthomas.
- SKILL.md
- references/07_REF2VA_FULL_REFERENCE_GUIDE.md
- references/13_REF2VA_GOLD_EXAMPLES.md
- references/16_H3_REF2VA_STYLE_TRANSFER_LAB.md
Open the folder on GitHubat commit 469fdd6
Compare with similar skills
H3 Ref2va next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| H3 Ref2va this skilldagthomas/comfyui_dagthomas | 290 | — | ~1.2k | Automated safety check: Pass | MIT | |
| PostHog CLI Queriesdebugtheworldbot/keyStats | 1.5k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Retentioneering Contributingretentioneering/retentioneering-tools | 920 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Retentioneering Product Analyticsretentioneering/retentioneering-tools | 920 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Retention Analysisliangdabiao/claude-data-analysis-ultra-main | 290 | 1 repos | ~1.3k | Automated safety check: Notes | None | |
| Feature Analytics Instrumentation Plannermistralai/mistral-vibe | 5.1k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Retentioneering Contributing
retentioneering/retentioneering-tools
Help the user turn their Retentioneering ideas, friction reports, bug findings, or feature needs into high-quality upstream contributions: from capturing and validating the idea, through minimal…
Retentioneering Product Analytics
retentioneering/retentioneering-tools
Analyze event logs, clickstreams, user paths, product funnels, retention, behavioral segments, transition graphs, step matrices, sequence patterns, and customer journeys using Retentioneering.
Retention Analysis
liangdabiao/claude-data-analysis-ultra-main
Analyze user retention and churn using survival analysis, cohort analysis, and machine learning.
- Official
Feature Analytics Instrumentation Planner
mistralai/mistral-vibe
Plans which analytics events and properties a new feature needs, checks them against the existing event registry, and verifies them per environment.
Funnel Analysis
liangdabiao/claude-data-analysis-ultra-main
Analyze user conversion funnels, calculate step-by-step conversion rates, create interactive visualizations, and identify optimization opportunities.
More from dagthomas/comfyui_dagthomas
H3 Base Format
dagthomas/comfyui_dagthomas
The three-field MiniMax H3 contract the APNext H3 Prompt Writer nodes emit for T2VA, I2VA, FL2VA and L2VA - integratedmultimodaldescription / overallsoundscape / nondiegeticmusic, the exact…
H3 Crossover
dagthomas/comfyui_dagthomas
The four-section MiniMax H3 crossover-scene contract the APNext H3 Crossover Writer node emits - subjectdefinitions / integratedmultimodaldescription / overallsoundscape / nondiegeticmusic per…
H3 Prompt Director
dagthomas/comfyui_dagthomas
Core craft for writing MiniMax H3 video prompts as the engine behind the APNext H3 nodes in ComfyUI - how to obey the node's directives (task type, duration, shot plan, camera, dialogue, wildness)…
H3 Style Craft
dagthomas/comfyui_dagthomas
Turning the APNext H3 node's visualstyle, camera and wildness settings into observable MiniMax H3 prompt language - one visual-medium pack plus at most one motion, finish and audio pack, translating…
Related
Works with
Categories
Questions about H3 Ref2va
What does H3 Ref2va do?
The six-section MiniMax H3 full-reference (Ref2VA) contract the APNext H3 Reference Prompt Writer nodes emit - subjectdefinitions, summary, retentionanalysis, detaileddescription, overallsoundscape…. H3 Ref2va is an agent skill from dagthomas/comfyui_dagthomas.<Picture 9, what its referencerole dropdown means, and reference-controls-HOW / user-controls-WHAT style transfer.
When should I use H3 Ref2va?
H3 Ref2va fits situations like: tasks that involve Product analytics.
How do I install H3 Ref2va in Claude Code?
Run `npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a claude-code`. Or copy the skill folder (data/h3/skills/h3-ref2va in dagthomas/comfyui_dagthomas) into .claude/skills/h3-ref2va in your project. Claude Code loads it when a task matches its description.
How do I install H3 Ref2va in Codex?
Run `npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a codex`. Or copy the skill folder (data/h3/skills/h3-ref2va in dagthomas/comfyui_dagthomas) into .agents/skills/h3-ref2va in your project. Codex loads it when a task matches its description.
Can I use H3 Ref2va in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dagthomas/comfyui_dagthomas --skill h3-ref2va -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/h3-ref2va, .gemini/skills/h3-ref2va, .github/skills/h3-ref2va and .opencode/skills/h3-ref2va in your project.
What does H3 Ref2va need to run?
SKILL.md names no scripts, command-line tools or credentials: H3 Ref2va is instructions for the agent only.
Does H3 Ref2va access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is H3 Ref2va safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does H3 Ref2va use?
H3 Ref2va is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does H3 Ref2va use?
About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.
What are the alternatives to H3 Ref2va?
Skills that share tags, products or a category with H3 Ref2va: PostHog CLI Queries (debugtheworldbot/keyStats, 1.5k stars), Retentioneering Contributing (retentioneering/retentioneering-tools, 920 stars), Retentioneering Product Analytics (retentioneering/retentioneering-tools, 920 stars) and Retention Analysis (liangdabiao/claude-data-analysis-ultra-main, 290 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains H3 Ref2va?
dagthomas (a GitHub user) maintains it in dagthomas/comfyui_dagthomas, which has 290 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 30, 2026.
Source: dagthomas/comfyui_dagthomas on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.