Agent skill

Tlaplus Model Reduction

by ArabelaTso in ArabelaTso/Skills-4-SE

Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties.

Apache-2.0Auto-check passed

Install Tlaplus Model Reduction

skills CLI
$ npx skills add ArabelaTso/Skills-4-SE --skill tlaplus-model-reduction -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ArabelaTso/Skills-4-SE tlaplus-model-reduction --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tlaplus-model-reduction .claude/skills/tlaplus-model-reduction && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tlaplus-model-reduction
GitHub stars
253
Token cost
~1.6k tokens
SKILL.md length
676 words
Files
2 (incl. references)
Skills in repo
170
Repo updated
First seen
Licence
Apache-2.0

At a glance

Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties.

  • Works in 6 steps: Input Analysis → Dependency Analysis → Identify Reduction Opportunities → …
  • Working with TLA+ specifications that need optimization
  • SKILL.md covers Overview, Workflow, Example Usage and Important Notes, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tlaplus Model Reduction is an agent skill from ArabelaTso/Skills-4-SE. Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties. Use when working with TLA+ specifications that need optimization, simplification, or reduction. Triggers when users ask to minimize, reduce, simplify, or optimize TLA+ specs, or when they want to remove redundancy from formal specifications while maintaining semantic equivalence.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/reduction_techniques.md`).

The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.

When your agent uses it

  • Working with TLA+ specifications that need optimization
  • Users ask to minimize
  • Optimize TLA+ specs
  • They want to remove redundancy from formal specifications while maintaining semantic equivalence

Example prompts

  • “/tlaplus-model-reduction”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Input Analysis
  2. Dependency Analysis
  3. Identify Reduction Opportunities
  4. Apply Reductions Incrementally
  5. Verify Semantic Equivalence
  6. Generate Output

What it can do on your machine

Read from SKILL.md and the folder at commit 4f38503. 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

Tlaplus Model Reduction loads about 1.6k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 123 tokens; SKILL.md has 676 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~123
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.2k

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 ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 676 words, ~1,574 tokens.

Download SKILL.mdSave it as .claude/skills/tlaplus-model-reduction/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
tlaplus-model-reduction
description
Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties. Use when working with TLA+ specifications that need optimization, simplification, or reduction. Triggers when users ask to minimize, reduce, simplify, or optimize TLA+ specs, or when they want to remove redundancy from formal specifications while maintaining semantic equivalence.

TLA+ Model Reduction (Spec Minimizer)

Overview

This skill analyzes TLA+ specifications and produces minimized versions by eliminating redundancies while preserving all specified properties. The reduction process analyzes reachability, dependency relations, and property relevance to ensure semantic equivalence between the original and reduced specifications.

Workflow

Step 1: Input Analysis

Parse and understand the input TLA+ specification:

  1. Identify components:

    • State variables (VARIABLES declaration)
    • Initial state predicate (Init)
    • Next-state relation (Next)
    • Invariants (INVARIANT declarations)
    • Temporal properties (PROPERTY declarations)
    • Type invariants and constraints
  2. Extract structure:

    • List all actions (disjuncts in Next)
    • Identify action guards (enabling conditions)
    • Map variable dependencies
    • Note fairness constraints if present
  3. Understand properties:

    • Safety properties to preserve
    • Liveness properties to maintain
    • User-specified invariants
Step 2: Dependency Analysis

Build comprehensive dependency graphs:

  1. Variable dependency graph:

    • For each variable, identify which actions read/write it
    • Determine which variables are used in property specifications
    • Find derived variables (computed from others)
    • Identify unused variables
  2. Action dependency graph:

    • Map which actions enable/disable other actions
    • Identify independent vs. dependent action sequences
    • Find actions with identical effects
  3. Property dependency graph:

    • Determine which variables each property depends on
    • Identify which actions affect property satisfaction
Step 3: Identify Reduction Opportunities

Systematically find redundancies using the techniques in reduction_techniques.md:

  1. Redundant state variables:

    • Variables never referenced in actions or properties
    • Variables whose values are always derivable from others
    • Variables that remain constant after initialization
  2. Equivalent actions:

    • Actions with identical guards and effects
    • Actions that differ only syntactically
    • Actions that can be merged without changing behavior
  3. Redundant invariants:

    • Invariants implied by other invariants
    • Invariants that are always trivially true
    • Invariants not needed for property verification
Step 4: Apply Reductions Incrementally

Perform reductions one at a time, verifying correctness after each:

  1. Remove redundant variables:

    • Eliminate unused variables first (safest)
    • Remove derived variables and update references
    • Simplify expressions after variable removal
  2. Merge equivalent actions:

    • Combine actions with identical effects
    • Simplify the Next-state relation
    • Preserve action names in comments for traceability
  3. Minimize invariants:

    • Remove implied invariants
    • Keep minimal set that ensures all properties
    • Document which invariants were removed and why
  4. Simplify expressions:

    • Reduce complex boolean expressions
    • Eliminate dead code in action definitions
    • Simplify guards when possible
Step 5: Verify Semantic Equivalence

Ensure the reduced specification is equivalent to the original:

  1. Reachability preservation:

    • Verify the reduced spec reaches the same states (modulo removed variables)
    • Check that no new behaviors are introduced
    • Confirm all original behaviors are preserved
  2. Property preservation:

    • Verify all safety properties still hold
    • Confirm liveness properties are maintained
    • Check that fairness constraints are preserved
  3. Refinement relationship:

    • Establish that reduced spec refines the original
    • Define refinement mapping if variables were removed
    • Explain the correspondence between states
Show full SKILL.md (231 more words)Show less
Step 6: Generate Output

Produce the minimized specification and justification:

  1. Minimized TLA+ specification:

    • Write the complete reduced spec
    • Use clear formatting and structure
    • Add comments explaining major changes
  2. Reduction summary:

    • List all reductions performed:
      • Variables removed (with reasons)
      • Actions merged (with justification)
      • Invariants eliminated (with explanation)
    • Quantify the reduction (e.g., "Reduced from 8 to 5 variables")
  3. Correctness justification:

    • Explain why each reduction preserves semantics
    • Describe the refinement mapping if applicable
    • Reference dependency analysis results
    • Note any assumptions made

Example Usage

User request: "Minimize this TLA+ spec while preserving the safety property"

Process:

  1. Parse the spec and identify 3 state variables, 4 actions, 2 invariants
  2. Build dependency graphs showing variable temp is only used internally
  3. Identify that Action1 and Action2 have identical effects
  4. Determine that Inv2 is implied by Inv1
  5. Remove temp, merge actions, eliminate Inv2
  6. Output reduced spec with 2 variables, 3 actions, 1 invariant
  7. Provide justification: "temp removed (derived from x and y), actions merged (identical guards and effects), Inv2 removed (implied by Inv1)"

Important Notes

  • Always preserve the original specification's semantics
  • Document all assumptions made during reduction
  • If uncertain about a reduction's correctness, keep the original form
  • Prioritize safety: when in doubt, don't reduce
  • For complex specs, consider using TLC model checker to verify equivalence
  • Maintain traceability between original and reduced specifications

References

© ArabelaTso, Apache-2.0. 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 1 other file (references) in skills/tlaplus-model-reduction of ArabelaTso/Skills-4-SE.

  • SKILL.md
  • references/reduction_techniques.md

Open the folder on GitHubat commit 4f38503

Compare with similar skills

Tlaplus Model Reduction 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.

Tlaplus Model Reduction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tlaplus Model Reduction this skillArabelaTso/Skills-4-SE253—~1.6kAutomated safety check: PassApache-2.0
Minimalismsickn33/agentic-awesome-skills47k1 repos~2.2kAutomated safety check: PassMIT
Simplifycodewhale-hq/Codewhale41k—~155Automated safety check: PassMIT
Simplifyasgeirtj/system_prompts_leaks69k—~759Automated safety check: PassCC0-1.0
Agent Specificationruvnet/ruflo74k2 repos~1.8kAutomated safety check: PassMIT
RTK Rust Code Simplifierrtk-ai/rtk83k—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Minimalism

    sickn33/agentic-awesome-skills

    Web and App implementation guide for the Minimalism design style.

    47k GitHub starsUsed in 1 repo~2.2k tokens
    MobileAuto-check passed
  • Simplify

    codewhale-hq/Codewhale

    Improve clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.

    41k GitHub stars~155 tokensUpdated today
    Auto-check passed
  • Simplify

    asgeirtj/system_prompts_leaks

    Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes.

    69k GitHub stars~759 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Agent skill for specification - invoke with $agent-specification

    74k GitHub starsUsed in 2 repos~1.8k tokens
    Product & Project ManagementAuto-check passed
  • Reviews RTK's Rust code for over-engineering and verbose patterns, applying idioms like iterator chains and early returns while protecting a specific list of constraints from being simplified away.

    83k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Simplified English

    paperclipai/paperclip

    Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the…

    99k GitHub stars~392 tokensUpdated today
    Auto-check passed

More from ArabelaTso/Skills-4-SE

All 170 skills in this repo
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Metamorphic Test Generator

    ArabelaTso/Skills-4-SE

    Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.

    253 GitHub stars~798 tokensUpdated 1 mo ago
    Auto-check passed
  • Reproduction Trace Instrumenter

    ArabelaTso/Skills-4-SE

    Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.

    253 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Spring Mvc To Boot Migrator

    ArabelaTso/Skills-4-SE

    Automatically migrate Spring MVC applications to Spring Boot.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • State Snapshot Instrumenter

    ArabelaTso/Skills-4-SE

    Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Tlaplus Model Reduction

What does Tlaplus Model Reduction do?

Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties. Tlaplus Model Reduction is an agent skill from ArabelaTso/Skills-4-SE. Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties.

When should I use Tlaplus Model Reduction?

Tlaplus Model Reduction fits situations like: working with TLA+ specifications that need optimization; users ask to minimize; optimize TLA+ specs; they want to remove redundancy from formal specifications while maintaining semantic equivalence.

How do I install Tlaplus Model Reduction in Claude Code?

Run `npx skills add ArabelaTso/Skills-4-SE --skill tlaplus-model-reduction -a claude-code`. Or copy the skill folder (skills/tlaplus-model-reduction in ArabelaTso/Skills-4-SE) into .claude/skills/tlaplus-model-reduction in your project. Claude Code loads it when a task matches its description.

How do I install Tlaplus Model Reduction in Codex?

Run `npx skills add ArabelaTso/Skills-4-SE --skill tlaplus-model-reduction -a codex`. Or copy the skill folder (skills/tlaplus-model-reduction in ArabelaTso/Skills-4-SE) into .agents/skills/tlaplus-model-reduction in your project. Codex loads it when a task matches its description.

Can I use Tlaplus Model Reduction 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 ArabelaTso/Skills-4-SE --skill tlaplus-model-reduction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tlaplus-model-reduction, .gemini/skills/tlaplus-model-reduction, .github/skills/tlaplus-model-reduction and .opencode/skills/tlaplus-model-reduction in your project.

What does Tlaplus Model Reduction need to run?

SKILL.md names no scripts, command-line tools or credentials: Tlaplus Model Reduction is instructions for the agent only.

Does Tlaplus Model Reduction 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 Tlaplus Model Reduction 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 Tlaplus Model Reduction use?

Tlaplus Model Reduction is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tlaplus Model Reduction use?

About 1.6k tokens (SKILL.md is roughly 6.3k 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 635 tokens, read only when the agent opens those files.

What are the alternatives to Tlaplus Model Reduction?

Skills that share tags, products or a category with Tlaplus Model Reduction: Minimalism (sickn33/agentic-awesome-skills, 47k stars), Simplify (codewhale-hq/Codewhale, 41k stars), Simplify (asgeirtj/system_prompts_leaks, 69k stars) and Agent Specification (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tlaplus Model Reduction?

ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 170 skills in this directory. The repository was last updated on August 21, 2026.

Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.