critical-action-identification-and-ranking

critical-action-identification-and-ranking is a skill for Claude Code, Codex from UCSC-VLAA/VisualClaw. It costs 44 tokens per session (325 once invoked), scanned A, original, MIT.

A guide for identifying the most important actions in a video and ranking them by how directly they achieve the main goal. It separates goal-critical actions from preparatory or supporting actions.

In plain words
What is it for?
Use it to analyze activities such as planting, repairs, or woodworking, then select the actions that would prevent the goal from being completed if they were skipped.
Why use it?
It prevents analysis from focusing on steps such as picking up a tool when the meaningful action is using it to complete the task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze activities such as planting, repairs, or woodworking, then select the actions that would prevent the goal from being completed if they were skipped.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add UCSC-VLAA/VisualClaw --skill critical-action-identification-and-ranking
Clone the repo
git clone --depth 1 https://github.com/UCSC-VLAA/VisualClaw

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for critical-action-identification-and-ranking

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking/github.svg)](https://agentmods.dev/skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking)
Your own site
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for critical-action-identification-and-ranking

Your own site · 80×15
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/critical-action-identification-and-ranking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00325
Opus 5 $0.00022 $0.00162
Sonnet 5 $0.00009 $0.00065
Haiku 4.5 $0.00004 $0.00032

Measured 12d ago against content hash 0a10477d9558, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

critical-action-identification-and-ranking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

visualclaw/skills_seed/seed_universal_mc/critical-action-identification-and-ranking/SKILL.md · 20 lines

What it actually says

Identify and Rank Actions by Contribution to Main Goal

  1. Define the end goal: Determine what the person is ultimately trying to achieve (e.g., plant seedlings, fix a frame, complete a wood project).
  2. Map all visible actions: List every action performed in sequence.
  3. Classify each action:
    • Core actions: Directly move toward the end goal (e.g., picking up seedlings, dropping them in soil)
    • Support actions: Enable core actions but are not themselves the goal (e.g., picking up a trowel, holding a sack)
  4. Select critical actions: Choose the core actions that most directly achieve the objective, not the preparatory steps.
  5. Verify importance: Ask: "If this action were skipped, would the main goal still be accomplished?" Core actions fail this test; support actions pass it.

Example: In Failure 5, the assistant focused on "picking the trowel" and "holding the sack," which are preparatory. The critical actions were "picking up seedlings" and "dropping them in the container"—the actions that actually plant them.

Anti-pattern: Confusing preparatory or support actions with the core actions that achieve the primary objective.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 20 lines · 44 tokens per session scan A 0a10477d9558

Subscribe to this mod's changes

critical-action-identification-and-ranking is a skill published in the GitHub repository UCSC-VLAA/VisualClaw (55 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 325 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ppt-generation

Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

bytedance/deer-flow · 44 tokens

image-generation

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

bytedance/deer-flow · 42 tokens

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens

video-generation

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

bytedance/deer-flow · 29 tokens

youtube-full

Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, first looks, or…

ZeroPointRepo/youtube-skills · 112 tokens

vision-skills

Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/htmlshot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long…

Anionex/agent-vision-toolkit · 132 tokens