Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
- License 许可
- MIT
- 最近更新
- 2026-06-22
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- Validation Engine
- tags
- [ "validation", "quality", "review" ]
- author
- ForgeWeave Core
- version
- 1.0.0
- skill_id
- validation-engine
- description
- Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
- tui_compatibility
- [ "opencode", "claude", "gemini", "qwen" ]
02 资源文件 2
- 参考文档references/validation-rules.md889 B
- 脚本scripts/check_claims.py2.3 KB
03 SKILL.md 正文
Validation Engine
Purpose
Systematically inspect outputs from any skill or agent for correctness, consistency, completeness, and compliance with project rules defined in AGENTS.md. Acts as a quality gate before outputs are presented to the user or used by downstream skills.
When to Use
- After any skill produces output that needs quality assurance
- Before presenting research results to the user
- When cross-checking claims across multiple sources
- After code generation, before presenting the code
When Not to Use
- The output is trivial and doesn't need validation
- The user is iterating quickly and doesn't want validation overhead
- The output is an intermediate step that will be further processed
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
output |
string | Yes | The content to validate |
type |
enum | Yes | research, code, documentation, plan |
rules |
array | No | Specific rules to enforce (defaults from AGENTS.md) |
Expected Outputs
| Output | Description |
|---|---|
| Validation report | Pass/fail per rule, with details |
| Issues found | List of problems with severity and location |
| Suggestions | How to fix each issue |
Exact Workflow Steps
- Load validation rules from AGENTS.md and the specific skill's requirements
- For research: check every claim has a source URL, flag contradictions, check no blog sources
- For code: check syntax, check against project conventions, verify tests pass
- For documentation: check completeness, accuracy, clarity
- For plans: check steps are ordered, dependencies identified, risks documented
- Compile validation report with pass/fail per rule
Required Checks
- [ ] All required fields are present in the output
- [ ] No contradictions across the output
- [ ] Output follows applicable rules from AGENTS.md
- [ ] All claims are traceable to sources
Failure Modes
| Failure Condition | Response |
|---|---|
| Validation rules are ambiguous | Ask for clarification |
| Output fails critical rules | Reject and report specific failures |
| Output fails minor rules | Accept with warnings |
References
| Reference | Path |
|---|---|
| AGENTS.md | ./AGENTS.md |
| Internal validator component | Used by the deep-research skill pipeline |
04 同仓库更多 Skills
Workflow Orchestrator
Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)
Web Research
Browser-driven or scraping-based skill for real-time internet extraction using Playwright and HTTP-based fetching
Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
Tool Selector
Determines which tools, APIs, MCP actions, or system capabilities are required for a given task
Test Generator
Creates test plans and test cases (unit, integration, edge cases) based on existing or planned code
Skill Generator
Meta-skill that creates new SKILL.md files from research outputs and patterns discovered in execution