decision-critic
Executes a python-based orchestration script to perform multi-step stress-testing of a decision.
Install
mkdir -p .claude/skills/decision-critic && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7775" && unzip -o skill.zip -d .claude/skills/decision-critic && rm skill.zipInstalls to .claude/skills/decision-critic
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Invoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.Key capabilities
- →Execute systematic evaluation steps for reasoning validation
- →Identify logical fallacies in architectural proposals
- →Stress-test decisions against pre-defined failure modes
- →Orchestrate script-driven critique flows
- →Automate boundary checking for design assumptions
How it works
Bypasses conversational AI reasoning to run a hardcoded Python script that applies a rigid critique framework to the input.
Inputs & outputs
When to use decision-critic
- →Critique a proposed technical architecture
- →Identify flaws in reasoning
- →Stress-test a design decision
About this skill
Decision Critic
When this skill activates, IMMEDIATELY invoke the script. The script IS the workflow.
Invocation
<invoke working-dir=".claude/skills/scripts" cmd="python3 -m skills.decision_critic.decision_critic --step 1 --decision '<decision text>'" />| Argument | Required | Description |
|---|---|---|
--step | Yes | Current step (1-7) |
--decision | Step 1 | The decision statement being criticized |
Do NOT analyze or critique first. Run the script and follow its output.
When not to use it
- →When the decision is purely subjective or aesthetic
- →When the critique script is not present in the project directory
Prerequisites
Limitations
- →Limited to the specific critique logic defined in the source script
- →Strictly follows the 7-step critique process
How it compares
It provides a programmatic, repeatable critique process instead of a subjective conversational review.
Compared to similar skills
decision-critic side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| decision-critic (this skill) | 1 | 6mo | No flags | Advanced |
| ark-analysis | 0 | 4mo | Review | Beginner |
| llm-council | 4 | 6mo | Review | Advanced |
| adversarial-spec | 3 | 6mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by solatis
View all by solatis →You might also like
ark-analysis
mckinsey
Analyze the Ark codebase by cloning the repository to a temporary location. Use this skill when the user asks questions about how Ark works, wants to understand Ark's implementation, or needs to examine Ark source code.
llm-council
am-will
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
adversarial-spec
zscole
Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. Use when user wants to write or refine a specification document using adversarial development.
project-development
muratcankoylan
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
cc-skill-project-guidelines-example
davila7
Project Guidelines Skill (Example)
plenum-architecture-contract
dhruvb14
>-