doc-detective/agent-tools/doc-detective-validate
Claude Code and agent skill by doc-detective/agent-tools
- community
- ext:[{"type":"config","description":"Configuration overrides"}]
Checking that the SKILL.md file is still in the repository.
Validate Doc Detective test specifications or configuration files
Install
npx vskill@latest install doc-detective/agent-tools/doc-detective-validateSemi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard
SKILL.md
Validate Command
Skill: doc-detective:validate
Validate Doc Detective test specifications or configuration files to ensure they're correctly structured.
Usage
Validate a test specification file or inline JSON:
Validate a configuration file:
Entry Criteria
Confirm all of the following before starting. If any item is unavailable or non-discoverable, stop and ask the user to provide it.
| Criteria | How to find it | |
|---|---|---|
| Test spec or config content to validate | Provided as a file path or inline JSON — ask user if missing |
Exit Criteria
Before completing:
- [ ] Validation executed against the provided input
- [ ] Each error reported as:
[FIELD]: [ERROR REASON] - [ ] Final result stated as
Validation PASSEDorValidation FAILED
Workflow
Validate Test Specification
Preferred: If a tool named validate_spec (or mcp__doc-detective__validate_spec) is registered in this session, call it instead of shelling out:
The MCP tool returns {valid, errors[], normalizedObject, schemaKey, schemaVersion}. Report each entry of errors[] as [instancePath]: [message]. Treat valid: true as Validation PASSED.
Fallback: If the MCP tool is not available, run the validator (try in order; stop and tell the user if none are available):
See _shared/MCP-USAGE.md for tool-naming conventions across hosts and log_observation guidance when validation friction is unrecoverable.
Only report `Validation PASSED` when the output confirms no errors. On failure, report each error as [FIELD]: [ERROR REASON].
Test spec checks:
testsarray must exist and be non-empty- Each test must have a non-empty
stepsarray - Each step must contain exactly one recognized Doc Detective action
- Action parameters must match expected types
Validate Configuration File
Preferred: Call validate_spec({object: <config>, schemaKey: "config_v3", addDefaults: true}) via MCP if available. Report each errors[] entry as [instancePath]: [message].
Fallback: Check the provided JSON against the doc-detective-common config schema. Report every field that fails as [FIELD]: [ERROR REASON].
Config checks:
input: must be a string or string array of valid glob patterns or file pathsrecursive: must be a booleanoutput: must be a valid directory path stringlogLevel: must be one ofsilent,error,warning,info,debugbrowser: must be an object (not a string)env: must be an object or.envfile path stringdefaultCommandTimeout: must be a number (milliseconds)
Valid config:
Invalid config:
Errors: browser must be object, logLevel value invalid.
See doc-detective-common for the full configuration schema.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/doc-detective-validate/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Extension points
configConfiguration overrides
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/doc-detective/agent-tools/doc-detective-validate)