organization-site-menu-research
Skill0 starsChanged 20 days agoMITView on GitHub
Assess organization-site navigation labels with evidence.
In this repository86 other files it gives its agents.
- ai-assistant-editor-setupSkill
- api-and-interface-designSkill
- banner-designSkill
- brainstormingSkill
- caveman-exploreSkill
- caveman-reviewSkill
- chat-silence-diagnosisSkill
- ci-cd-and-automationSkill
- code-auditSkill
- codebase-designSkill
- koordinator-team-dispatchSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- cpanel-shared-hosting-deploySkill
- cross-profile-cron-opsSkill
- deprecation-and-migrationSkill
- documentation-and-adrsSkill
- domain-modelingSkill
- doubt-driven-developmentSkill
- finishing-a-development-branchSkill
- frontend-designSkill
- git-workflow-and-versioningSkill
- graphic-design-laneSkill
- hermes-gateway-web-uiSkill
- hermes-profile-hygieneSkill
- hermes-profile-provisioningSkill
- hermes-service-persistenceSkill
- hermes-stream-stale-diagnosisSkill
- hermes-team-dashboardSkill
- idea-refineSkill
- incremental-implementationSkill
- indonesian-official-lettersSkill
- internal-commsSkill
- interview-meSkill
- investigate-firstSkill
- kanban-rate-limit-resilienceSkill
- karpathy-guidelinesSkill
- large-project-gated-deliverySkill
- lean-buildSkill
- live-agent-office-operationsSkill
- live-react-runtime-qaSkill
- live-web-release-verificationSkill
- markdown-pdf-pipelineSkill
- marketing-strategySkill
- meta-social-publishingSkill
- meta-threads-oauth-lifecycleSkill
- migrationSkill
- multi-profile-project-orchestrationSkill
- network-operationsSkill
- observability-and-instrumentationSkill
- office-skill-distributionSkill
- performance-optimizationSkill
- php-upload-size-limitsSkill
- planning-and-task-breakdownSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-reviewSkill
- ponytailSkill
- portable-app-handoffSkill
- receiving-code-reviewSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use this workflow to recommend or evaluate a website menu label for an organization.
- Distinctive: line 22
Inspect project truth first: Read the product brief, information architecture, and relevant content model before recommending a label.
- Distinctive: line 23
Verify live implementation: Use the code graph before source inspection when available.
- Distinctive: line 26
Ground benchmarks: Prefer official peer-organization navigation and reputable information-architecture guidance.
- Distinctive: line 28
Respect delivery gates: Keep research separate from implementation.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Organization-Site Menu Research
Use this workflow to recommend or evaluate a website menu label for an organization. Research only unless implementation is explicitly requested.
When to Use
- A user asks what a site menu means or what should replace it.
- A navigation label may represent editorial content, an operational service, or an organization program.
Procedure
- Inspect project truth first. Read the product brief, information architecture, and relevant content model before recommending a label. Record whether the spec is approved or still draft.
- Verify live implementation. Use the code graph before source inspection when available. Confirm what the page actually contains, who manages it, and whether it is public, admin-only, or both. Do not infer behavior from its title.
- Separate distinct user needs. Distinguish editorial publishing, programs/activities, and user feedback. A comment or suggestion workflow requires ownership, response expectations, moderation, and privacy handling; it is not equivalent to an editorial section.
- Compare a small set of labels. For each option, state what content belongs there, visitor benefit, cost/risk, and conditions under which it fits. Check for duplicate existing sections.
- Ground benchmarks. Prefer official peer-organization navigation and reputable information-architecture guidance. Treat examples as patterns, not universal proof. Cite direct URLs and the actual menu categories observed.
- Recommend conditionally. Choose the label that matches both documented organizational goals and verified content. If real program details are absent, do not relabel editorial drafts as programs; require owner validation and preserve/archive existing content rather than deleting it.
- Respect delivery gates. Keep research separate from implementation. Do not change routes, content, or data unless requested and allowed by the project phase and touch-path constraints.
Implementing the chosen label (only when explicitly asked)
- Find every surface first. Public menu, mobile menu, footer, home cards, detail views, sitemap, default settings/CTA copy, page
<title>/meta, FAQ copy, panel labels, and tests. A rename that touches only the nav leaves contradictory copy behind. - Keep internal names, change public names. Model, table, panel path, and CSS hook classes can keep the old word; renaming them forces data migrations and widens the diff. Document the mapping in the commit or evidence note.
- Serve the canonical URL and 301 the old one. Resolve the old slug through the model so stale slugs redirect to the canonical slug, and fall back to the section index instead of returning 404 or 500.
- Never let drafts become links. Build navigation labels from a fixed field list plus a
published()lookup, render unpublished entries as<span aria-disabled="true">, and give draft detail pages a neutral "not published yet" view with no title/thesis/body. - Update tests in the same commit. Route smoke tests, crawl checks, content gates, SEO/QA, and menu matrix all hardcode the old paths; convert them to the canonical path plus an explicit 301 assertion, otherwise the suite fails or silently stops covering the section.
- Re-run the visual check. Take desktop and mobile screenshots, force lazy images to load before capturing, and confirm no placeholder copy, no overflow, and no leftover old label.
- Check test argument order. Live tests taking positional CLI arguments (e.g. process count, capacity) will silently pass a URL as an integer and report a false failure; read the header before running.
Verification
- Explain the existing menu in plain language.
- Tie the recommendation to project goals and actual content.
- Include evidence from project documents and external sources.
- State trade-offs, prerequisites, and any unresolved owner decision.
- Make no unrequested code or data changes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

