modem-dev/ossrules / public/files/qwik/.ruler/skills/qwik-guidance-maintenance
qwik-guidance-maintenance
UnverifiedUse when editing Qwik's .ruler guidance, adding or changing rules or skills, keeping AI guidance from going stale, updating assistant setup docs, or answering how Ruler should generate assistant-native guidance, skills, config, or policy for this repo.
Qwik Guidance Maintenance
Use this skill for .ruler/**, README AI assistant setup, dedicated rules, generated
assistant-output boundaries, rule-vs-skill taxonomy work, and assistant-native config questions.
Also use it at the end of a code task when source inspection proves a loaded skill or reference is
stale.
Fast Path
- Follow the Guidance Source Of Truth rule (in
.ruler/AGENTS.md) for source layout, rule-vs-skill taxonomy, generated assistant outputs, AI config builder behavior, skill naming, and stale-guidance policy. - Follow the Generated Output Boundaries rule (in
.ruler/AGENTS.md) before editing, regenerating, or relying on generated output. - Edit committed source files in
.ruler/, not generated assistant outputs. - Keep new durable policy in the narrowest source:
.ruler/AGENTS.mdfor repo-wide context and always-on rules, and.ruler/skills/**for task-specific workflows. - For a target assistant, research the current native guidance, skill, config, and policy formats when the mapping is ambiguous.
- Verify Ruler behavior with a dry run when the CLI is available.
- Verify generated guidance by checking source markers in the target assistant's native guidance file and generated skills in the target assistant's native skills directory when supported.
Freshness Workflow
When an agent uses a skill and current source contradicts it:
- Finish the user's product-code task first unless the guidance defect blocks the task.
- Update the narrowest
.rulersource that was wrong. - Prefer replacing stale details over appending another long lesson.
- Keep history-derived guidance behavioral and durable.
- Mention the guidance update in the final response so reviewers know why
.rulerchanged.
Source Map
- Repo-wide guidance + always-on rules:
.ruler/AGENTS.md - Human setup guide:
.ruler/README.md - Ruler config:
.ruler/ruler.toml - Source skills:
.ruler/skills/**/SKILL.md - Generated outputs (committed): root
AGENTS.md, rootCLAUDE.md, and.claude/skills//.codex/skills/; other.claude//.codex//.cursor/files stay local
Rule And Skill Workflow
- For a new always-on policy, add or update a rule section in
.ruler/AGENTS.mdand its summary in the Source Rules index there. - For package-specific details, update the package skill or a directly linked reference.
- For long notes, add a
references/file only when progressive disclosure keeps the skill body smaller and clearer. - For assistant setup changes, keep human setup steps in
.ruler/README.mdand behavioral agent rules in.ruler/AGENTS.md. - For assistant output questions, use the
guidance-source-of-truthrule unless current Ruler or target-tool docs have changed. - Treat command execution policy as a separate native format from prose guidance. Do not translate
.ruler/AGENTS.mdguidance into command-policy files just because the target tool calls them "rules".
Verification
Use the target assistant for the change. For a Codex example:
npx @intellectronica/ruler apply --agents codex --dry-run --no-mcp --no-gitignore
ruler apply --agents codex
rg -n 'Source: .ruler/AGENTS.md' AGENTS.md
find .codex/skills -name SKILL.md
pnpm prettier --check .ruler README.md .gitignore
git diff --check
If npx cannot reach the registry, retry only when network approval is appropriate; otherwise
record the blocker and still run local formatting/diff checks.
Stop Conditions
- Stop before editing generated assistant outputs directly.
- Stop if a proposed rule duplicates detailed skill content instead of summarizing durable policy.
- Stop if current Ruler or target-tool docs contradict the Guidance Source Of Truth rule in
.ruler/AGENTS.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |