config-contracts
Provides structural schema and validation rules for critical TOML configuration files used by the system.
Install
mkdir -p .claude/skills/config-contracts && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15951" && unzip -o skill.zip -d .claude/skills/config-contracts && rm skill.zipInstalls to .claude/skills/config-contracts
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.
TOML config structure and validation rules. Use when creating or modifying config files (global_rubric.toml, role_archetypes.toml, settings.toml), updating config validation, or loading config in the indexer.Key capabilities
- →Validate the structure of `global_rubric.toml`
- →Validate the structure of `role_archetypes.toml`
- →Validate the structure of `settings.toml`
- →Report actionable errors for missing or malformed TOML files
- →Apply default values for missing settings like `negative_weight`
- →Check if `global_rubric_path` exists
How it works
This skill validates TOML config files against predefined rules, checking for file existence, correct TOML syntax, and specific field constraints.
Inputs & outputs
When to use config-contracts
- →Modifying configuration files
- →Updating validation logic
- →Validating TOML structure
About this skill
Config Contracts — TOML Structure & Validation Rules
When This Skill Applies
When creating or modifying config files (global_rubric.toml, role_archetypes.toml,
settings.toml), updating config validation in config.py, or loading config in
the indexer.
Config File Overview
Three TOML config files with full structure examples in toml-schemas.md:
config/global_rubric.toml— 8 dimensions (altitude,humane_culture, etc.) withdescription,signals_positive,signals_negativeconfig/role_archetypes.toml—[[archetypes]]array withname,description,signals_positive,signals_negativeconfig/settings.toml—[scoring]section with weights,base_salary, thresholds
Validation Rules
global_rubric.toml
| Check | Error |
|---|---|
| File missing | ActionableError naming path + "create the file with at least one dimension" |
| Malformed TOML | ActionableError with syntax error details + file path |
role_archetypes.toml
| Check | Error |
|---|---|
| File missing | ActionableError naming path + recovery steps |
| Malformed TOML | ActionableError with syntax error + file path |
| Empty archetypes list | ActionableError advising to add entries before search |
Archetype without signals_positive | Graceful — embed description only |
Archetype without signals_negative | Graceful — no negative document for this archetype |
settings.toml — negative_weight
| Check | Error |
|---|---|
| Missing | Default to 0.4 |
| Out of range (< 0.0 or > 1.0) | ActionableError naming field + valid range |
settings.toml — culture_weight
| Check | Error |
|---|---|
| Missing | Default to 0.2 |
| Out of range (< 0.0 or > 1.0) | ActionableError naming field + valid range |
settings.toml — global_rubric_path
| Check | Error |
|---|---|
| Missing from settings | Default to "config/global_rubric.toml" |
| Path does not exist | ActionableError naming path + creation guidance |
When not to use it
- →When the user wants to modify config files that are not `global_rubric.toml`, `role_archetypes.toml`, or `settings.toml`
Limitations
- →It only applies to `global_rubric.toml`, `role_archetypes.toml`, and `settings.toml`
- →It defaults `negative_weight` to 0.4 if missing
- →It defaults `culture_weight` to 0.2 if missing
How it compares
This skill provides structured validation and error reporting for specific TOML configuration files, unlike a generic TOML parser that might not enforce domain-specific rules or provide actionable feedback.
Compared to similar skills
config-contracts side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| config-contracts (this skill) | 0 | 5mo | No flags | Beginner |
| common-technical-practices | 2 | 3mo | No flags | Intermediate |
| graceful-degradation | 1 | 7mo | No flags | Intermediate |
| domain-cloud-native | 1 | 6mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
common-technical-practices
TencentBlueKing
通用技术实践指南，涵盖 AOP 切面、分布式锁、重试机制、参数校验、性能监控、定时任务、审计日志等后端开发中的常见技术实践。当用户需要实现横切关注点、处理并发控制、配置重试策略、添加性能监控或实现审计功能时使用。
graceful-degradation
parcadei
Graceful Degradation with Helpful Messages
domain-cloud-native
actionbook
Use when building cloud-native apps. Keywords: kubernetes, k8s, docker, container, grpc, tonic, microservice, service mesh, observability, tracing, metrics, health check, cloud, deployment, 云原生, 微服务, 容器
review-quality
Lurek2D
Load this skill when auditing overall repo quality, hotspots, contract drift, and tool-reported quality findings. Skip it for narrow module implementation tasks with clear requested edits.
agent-gossip-coordinator
ruvnet
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator
dream-state
fabioc-aloha
Architecture maintenance, connection validation, automated health diagnostics, and unconscious processing