Check whether coding agents follow their assigned skills and rules across three levels of prompt support. Generate test scenarios, inspect tool call sequences, and get reports showing compliance scores and the order of observed actions.
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines. Use when checking whether agents actually follow the skills, rules, and definitions they were given, rather than assuming they do.
This skill checks whether an AI agent follows its assigned skills or rules. It derives an expected sequence of actions from Markdown and generates scenarios at three levels: instructions that support the rule, neutral instructions, and competing instructions. An LLM classifies tool calls made during execution, and the skill checks their order. Reports show compliance scores and timelines for each scenario.
Use it after adding a rule, or when you want to know whether a procedure is followed without an explicit reminder. Reports include the expected steps and the actual prompts, so you can see which stages were missed. For steps with low compliance, it also suggests moving the action to a hook that starts it automatically.
testing.md is actually being followed.”SKILL.md without running them.”The execution examples use uv, Python, and claude -p. Normal verification calls models and incurs costs. With --dry-run, only specifications and scenarios are generated; the agent does not run. Verification of agent definitions only checks whether the agent is invoked. Checking its internal workflow is not yet supported.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Measures whether coding agents actually follow skills, rules, or agent definitions by:
claude -p and capturing tool call traces via stream-jsonskills/*/SKILL.md): Workflow skills like search-first, TDD guidesrules/common/*.md): Mandatory rules like testing.md, security.md, git-workflow.mdagents/*.md): Whether an agent gets invoked when expected (internal workflow verification not yet supported)/skill-comply <path># Full run
uv run python -m scripts.run ~/.claude/rules/common/testing.md
# Dry run (no cost, spec + scenarios only)
uv run python -m scripts.run --dry-run ~/.claude/skills/search-first/SKILL.md
# Custom models
uv run python -m scripts.run --gen-model haiku --model sonnet <path>
Measures whether a skill/rule is followed even when the prompt doesn't explicitly support it.
Reports are self-contained and include:
For users familiar with hooks, reports also include hook promotion recommendations for steps with low compliance. This is informational — the main value is the compliance visibility itself.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.
Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.