revalidation
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: revalidation
description: Revalidate Codex project instructions, agents, skills, or migrated AI configuration. Use when th…
category: ai
runtime: no special runtime
---
# revalidation output preview
## PART A: Task fit
- Use case: Revalidate Codex project instructions, agents, skills, or migrated AI configuration. Use when the user asks for agent revalidation, skill revalidation, config revalidation, or to check that AGENTS.md and .codex/skills match the codebase. Use when this capability is needed..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Step 1: Structural Validation / Step 2: Logical Analysis” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Revalidate Codex project instructions, agents, skills, or migrated AI configuration. Use when the user asks for agent revalidation, skill revalidation, config revalidation, or to check that AGENTS.md and .codex/skills match the codebase. Use when this capability is needed.”.
- **02** When the source has headings, the agent prioritizes “Step 1: Structural Validation / Step 2: Logical Analysis” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Step 1: Structural Validation / Step 2: Logical Analysis”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: revalidation
description: Revalidate Codex project instructions, agents, skills, or migrated AI configuration. Use when th…
category: ai
source: tomevault-io/skills-registry
---
# revalidation
## When to use
- Revalidate Codex project instructions, agents, skills, or migrated AI configuration. Use when the user asks for agent…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Step 1: Structural Validation / Step 2: Logical Analysis” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "revalidation" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Step 1: Structural Validation / Step 2: Logical Analysis
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Agent And Skill Revalidation
Use this workflow to keep Codex configuration accurate and coherent with the actual codebase.
Step 1: Structural Validation
Re-read the target agent or skill configuration file in full. Validate every documented fact against the current codebase, including current-session changes:
- File and directory paths exist and match the documentation.
- Referenced tools, reference docs, and linked files exist.
- Named types, classes, dialogs, and namespaces are accurate.
- Documented conventions still match existing code.
Apply objective structural fixes automatically. These corrections do not need approval.
Step 2: Logical Analysis
Analyze the configuration beyond mechanical path checks:
- Responsibilities align with the available tools and reference files.
- Conventions still make sense for the current codebase.
- Sections do not overlap, contradict each other, or duplicate stale guidance.
- Commonly edited areas are covered.
- Self-maintenance rules catch likely side effects.
- Reference files are structured well enough to scale.
Present logical findings one at a time, ordered by importance. For each finding:
- Describe the issue and concrete suggestion.
- Ask the user to approve, reject, or modify the suggestion. Use a concise plain-text question when no structured question tool is available.
- Apply approved changes immediately before moving to the next finding.
Do not batch logical findings. Do not apply logical-analysis changes without user approval.
Source: BitzArt-VS/UI-Tweaks — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review