score-guidance-adherence
This skill evaluates how well a theory in theory.md adheres to user guidance found in phenomenon.txt or GUIDANCE.txt.
Identity proven by GitHub's verified organisation badge (imbue-ai)
- Agents
- Claude Code
- License
- AGPL-3.0 (copyleft)
- Pin
- a2ee48cpinned Oct 9, 2026
- Context cost
- about 420 tokenswhen the skill loads
- GitHub stars
- 36on imbue-ai/catalyst
- Scripts
- None found
What it does
“Score how well the given theory adheres to the provided guidance.”
Generated summary from the skill's own text
This skill evaluates how well a theory in theory.md adheres to user guidance found in phenomenon.txt or GUIDANCE.txt. It checks for compliance with specified constraints and assigns a score between 0 and 1 based on how strictly the theory follows the provided requirements.
When to use it
- Validating theories against user-specified constraints or requirements
- Measuring theory quality relative to explicit guidance criteria
- Filtering or ranking theories based on adherence scores
- Quality assurance when generating multiple theory candidates
When not to
- No guidance files exist or guidance is purely descriptive rather than prescriptive
- Assessing theories on correctness or accuracy independent of user preferences
- Comparing theories without predefined user guidance to evaluate against
Install
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add imbue-ai/catalyst --skill score-guidance-adherenceInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install imbue-ai/catalyst score-guidance-adherence@a2ee48c34741df5d4549d97b22aa44589d9eaa6aInstalls the commit we checked (a2ee48c).
Copy by hand
Download the folder at a2ee48c and put it in .claude/skills/score-guidance-adherence for Claude Code and in .agents/skills/score-guidance-adherence for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "score-guidance-adherence" by Imbue. Source, pinned to commit a2ee48c34741df5d4549d97b22aa44589d9eaa6a: https://github.com/imbue-ai/catalyst/tree/a2ee48c34741df5d4549d97b22aa44589d9eaa6a/src/claude_skills/skills/score-guidance-adherence 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/score-guidance-adherence/ for Claude Code and .agents/skills/score-guidance-adherence/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Listing and checks: https://www.agentnative.dev/skills/imbue/score-guidance-adherence
SKILL.md at the pin
--- name: score-guidance-adherence description: "Score how well the given theory adheres to the provided guidance." argument-hint: "the theory ID to score (e.g. T_20260414_143100_d4e5f6)" user-invocable: false --- This skill explains how to assess and score how well a given theory adheres to the provided user guidance. ## Guidance Adherence Score Execution Steps 1. **Check Guidance**: User guidance can come from two places: a) the file `phenomenon.txt`, and/or b) the file `GUIDANCE.txt`, both in the current working directory. Zero, one, or both of the files might exist. Check which one(s) exists, and read them to determine whether the user has provided any specific guidance on what kind of theory they're looking for. - Note that `phenomenon.txt` (if it exists), will also contain a description of the phenomenon that is being investigated. Disregard that part, as we are only interested in any *additional* constraints that it imposes on the type of theory that the user is interested in, not on *what* the theory should explain. - If neither file exists, or neither contain any prescriptive guidance on what type of theory the user expects, you can skip the next step and just assign a score of 1 (trivially full adherence to guidance, since there is no guidance). 2. **Understand the Theory**: If you haven't yet, carefully read the `theory.md` file to understand the theory that you are scoring. 3. **Score Adherence**: Assign a Guidance Adherence Score between 0 and 1. Check if the theory in `theory.md` adheres to all user-provided guidance from the sources mentioned above. Assign a score of 1 if it strictly adheres to all guidance, 0.5 if it adheres to some but not all guidance or only partially adheres to some key guidance, and 0 if it doesn't adhere to any relevant guidance. Use your judgment to assign intermediate scores in other scenarios.
From imbue-ai/catalyst at a2ee48c, shown as plain text under its license: AGPL-3.0 (copyleft). The license text is in LICENSE.
View SKILL.md on GitHub at a2ee48cFiles
- SKILL.md1.9 KB · ab2953a008ed
1 file, 1.9 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at a2ee48cMore from Imbue
architect
Generates an architecture document for a feature by reading the existing spec, analyzing the codebase deeply, and conducting guided Q&A with the user to…
Claude Code · about 4K tokens · pinned 6 days ago
build
This skill executes a multi-step implementation plan by working through task files sequentially.
Claude Code · about 1.1K tokens · pinned 6 days ago
build-sculptor-extension
Build or modify Sculptor extensions, which are runtime ES modules that add panels, overlays, widgets, home views, or settings UI to the Sculptor frontend.
Contains scripts
Claude Code, Codex, Cursor +3 · about 3.3K tokens · pinned 6 days ago
fix-bug
Fixes bugs using test-driven development with an interactive or autonomous workflow.
Claude Code · about 9.8K tokens · pinned 6 days ago
handoff
This skill hands off ongoing work to a fresh agent, either in the same workspace or a new isolated workspace, while preserving context through a synthesized…
Claude Code · about 1.1K tokens · pinned 6 days ago
help
This skill fetches the latest Sculptor documentation from GitHub and answers user questions about how to use Sculptor's features, including workspaces…
Claude Code · about 880 tokens · pinned 6 days ago
Related in AI and agents
agent-builder
Agent Builder orchestrates the creation, modification, testing, and publishing of n8n Agents.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 2.3K tokens · pinned 6 days ago
intent-recognition
Classifies automation requests by determining which primitive owns the top-level control flow (workflow, agent, needs clarification, or out-of-scope) and…
by n8nOfficial publisher
Claude Code, Codex, Cursor +4 · about 6.9K tokens · pinned 6 days ago
planned-task-runtime
This skill manages follow-up interactions with a background task execution system, handling task completion synthesis, failure replanning, workflow building…
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 2.2K tokens · pinned 6 days ago
skill-creator
This skill guides agents through creating new skills that extend Gemini CLI with specialized knowledge, workflows, and tool integrations.
by GoogleOfficial publisher
Contains scripts
Gemini CLI · about 5K tokens · pinned 6 days ago
-21risk-automation
This skill automates 21risk operations by connecting to the 21risk toolkit through Composio's Rube MCP server.
by ComposioOfficial publisher
Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago
-2chat-automation
This skill automates 2chat tasks by integrating with Composio's 2chat toolkit through Rube MCP.
by ComposioOfficial publisher
Agents not labelled yet · about 680 tokens · pinned 6 days ago
Open roles at Imbue
No open roles at Imbue on the Agent Native jobs board right now.
Browse the jobs board