$ loading_
Generate test scenarios and measure how well agents follow skills and rules.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skill-comply" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/skill-comply/SKILL.md 2. Save it as ~/.claude/skills/skill-comply/SKILL.md 3. Reload skills and tell me it's ready
Run a compliance test for this customer support agent: generate loose, standard, and strict prompt scenarios around refunds, complaints, and escalations; execute the agent; detect whether it follows tone guidelines, escalation rules, and prohibited promises; then report compliance rates, failed examples, and full tool-call timelines.
A compliance report with results across three strictness levels, behavior classifications, violation reasons, compliance rates, and detailed tool-call logs.
For this agent with search and database tools, automatically generate test scenarios and verify whether it follows the defined order of searching before querying, whether it incorrectly skips tools, and whether it uses any unauthorized tools. Return behavior-sequence classifications, step-by-step timelines, and overall adherence rates.
A workflow compliance analysis showing tool-call order, abnormal paths, unauthorized usage, and overall adherence percentages.
Generate and run tasks for this agent under loose, standard, and strict prompt conditions, then compare differences in rule-following, output consistency, and tool usage. Return segmented statistics and a concise visualization-ready summary.
A tiered comparison showing performance changes across prompt strictness levels, key risk areas, and overall stability conclusions.
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.
Design composable Top-K recommendation, ranking, and feed pipelines for user-context decisions.
Build testable Swift code with protocol-based dependency injection and focused mocks.
Apply Laravel security best practices for auth, vulnerabilities, APIs, and deployment.
Provides systematic verification for Claude Code sessions to improve correctness and quality.
Coordinate multi-agent teamwork with ownership, Kanban flow, merge gates, and handoffs.
Review Solidity AMM, liquidity pool, and swap flow security risks.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Turn a repeated workflow into a reusable skill file from the current session.
Mine recurring coding-agent workflows and refine skills for reuse and publication.
Semantically search a local skill library and load only relevant skills on demand.