Agent rules skill author
Skill ytvee-dev/webdev-agent-kit/skills/agent-rules-skill-author
A cross-platform frontend kit for Codex, Claude Code, Cursor, OpenCode, etc. It helps AI coding agents work predictably and safely with existing frontend projects.
npx -y skills add ytvee-dev/webdev-agent-kit --skill agent-rules-skill-authorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Create, evaluate, or edit this .agents WebDev Agent Kit, including AGENTS.md, common/**, project/**, skills/**, metadata, validators, and progressive-disclosure rules.
SKILL.md
7.5 KB, as published. Nobody here has run it
Agent Rules And Skill Author
Purpose
Create or revise repo-local agent rules and .agents-compatible skill packages without leaking project-specific instructions into the wrong layer.
When To Use
- The user asks to create, evaluate, rename, delete, or edit skills.
- The user asks to change
AGENTS.md, manifests, validators,common/**,project/**, orskills/**. - The user explicitly asks for user-facing README documentation changes.
- The screenshot-to-frontend pipeline rules, tool contracts, or skill routing need maintenance.
When Not To Use
- The user asks to write a design implementation spec from screenshots. Use
design-screenshot-spec. - The user asks to implement a frontend layout from a spec. Use
frontend-layout-implementer. - The user asks to visually verify rendered UI. Use
frontend-visual-qa. - The user asks to adapt a new project in Plan Mode. Use
project-onboarding-adapter.
Required Context
- Read
AGENTS.md. - Confirm the classified task is
skill-documentation-refactor,documentation, or another.agentsrule-maintenance task. - Read
common/documentation-maintenance.md. - Read affected
common/**,skills/**,project/**, manifests, validators, templates, examples, and root pointer files for the requested change. - Apply
common/readme-policy.md: read targeted README sections when the request concerns README, public setup guidance, or docs/implementation drift; verify technical claims through higher evidence. - Read relevant references from this skill only when their topic is in scope.
- Read current OpenAI Codex docs when native skill behavior,
AGENTS.md, MCP, plugins, oragents/openai.yamlbehavior may have changed.
Tool Contract
- Use filesystem reads and targeted search for local bundle facts.
- Activate
openai_platform_docswhen current OpenAI or Codex behavior affects the change; followcommon/codex-official-docs-policy.md. - Use
context7andmdnonly when authoring rules depend on current framework or web platform behavior. - Do not use Figma MCP for this bundle.
Workflow
- Classify the target layer:
AGENTS.md, manifests, validators,common/**,project/**,templates/**,examples/**, orskills/**. - Treat README as optional human-facing context, never runtime policy or validator truth. Do not edit it unless the current user explicitly requests that README change.
- Confirm whether a new skill is needed or an existing skill/reference/common rule should be edited.
- Define trigger surface, non-trigger cases, inputs, outputs, defaults, tool contract, failure modes, and validation gates.
- Keep skill packages in the standard section order used by this bundle.
- Keep graph frontmatter and Codex UI/invocation metadata synchronized; keep
capability declarations in
tool-capabilities-manifest.json. - Remove stale links after renames or deletions.
- Validate changed skill packages and run documentation checks.
Output Contract
Final response: return only facts that affect the user's understanding, confidence, or next action. Omit empty fields and workflow narration.
Report:
- files changed;
- skill routing or trigger changes;
- tool dependency changes;
- validation performed;
- unresolved risks or blocked checks.
Validation Gates
nameanddescriptionstay first inSKILL.mdfrontmatter.- Every skill has
Purpose,When To Use,When Not To Use,Required Context,Tool Contract,Workflow,Output Contract,Validation Gates,Trigger Evals, andReference Map. - New references are linked from the owning
SKILL.md. agents/openai.yamlmatches skill UI and invocation policy. Only true hard client-tool dependencies belong there; optional providers belong in the capability manifest.- No Figma MCP or Figma whiteboard workflow is introduced.
- README is not used as runtime policy, routing input, validator truth, or sole technical evidence, and is not edited without an explicit current user request.
Trigger Evals
Should trigger:
- "Create a new skill for visual QA."
- "Audit and rewrite the .agents skill routing."
- "Update AGENTS.md, manifests, and graph links for renamed skills."
Should not trigger:
- "Implement this Design Implementation Spec."
- "Compare the rendered page to the screenshot."
- "Write a layout spec from these screenshots."
Authoring Mode
Default to the source-bundle contract: native name and description plus local graph metadata. Use strict native-portable frontmatter only when the user explicitly requests a standalone skill outside this bundle.
Before material skill changes:
- Use
references/skill-design.mdto choose the smallest correct intervention and package shape. - Use
references/trigger-and-metadata.mdto align the description, invocation policy, andagents/openai.yaml. - Use
references/skill-quality-rubric.mdfor trigger and workflow evals. - Use
references/rules-writing.mdwhen policy scope or precedence changes. - Use
references/documentation-maintenance.mdfor graph, manifest, rename, or publication changes. - Use
references/validation-checklist.mdbefore final reporting.
For new skills, use the local scaffolder only after the workflow, resources, compatibility target, and trigger boundary are defined. Keep examples and scripts only when they implement repeatable behavior.
Reference Map
references/codex-native-skill-contract.mdreferences/rules-writing.mdreferences/skill-design.mdreferences/skill-quality-rubric.mdreferences/trigger-and-metadata.mdreferences/validation-checklist.mdcommon/readme-policy.mdcommon/codex-official-docs-policy.mdreferences/figma-derived-conventions.mdreferences/source-backed-prompting.mdreferences/documentation-maintenance.md