Runs a scheduled audit of existing tool, MCP, skill, and news entries to identify and address stale pricing, broken documentation links, outdated capabilities, and weakened prose that quietly degrades directory quality. This maintenance rhythm prevents the directory from accumulating digital rot as tools evolve and entries grow outdated.
Use cases
- Monthly or quarterly sweep of all directory entries to catch tools that have changed pricing or deprecated features
- After a major AI model release, refreshing entries for tools affected by the new model landscape
- Running a link audit to identify documentation URLs that have returned 404 or moved permanently
- Reviewing entries flagged by users or search console data for outdated information
- Auditing entries that have not been reviewed in over six months as a proactive maintenance step
Key features
- Pull the current inventory of entries and sort by last-verified date, prioritizing entries older than your maintenance threshold
- Recheck each source URL for the entry—verify the page loads, the content matches the entry, and the date is still accurate
- Assess whether the entry should be promoted (the tool is actively maintained and relevant), demoted (the tool is declining or less relevant), or archived (the tool is deprecated or shut down)
- Document the review action and date for each entry so the next audit cycle can pick up where this one left off
- Update the published date signal for search engines when substantive changes are made to an entry
When to Use This Skill
- When directory entries have not been reviewed in over 90 days and quality signals may be degrading
- When search console data shows declining impressions for a category of entries
- When a major ecosystem event (new model release, deprecation notice) affects multiple entries at once
Expected Output
A content audit report with each entry classified as current, needs-update, demoted, or archived, and a documented review date for each.
Frequently Asked Questions
- How do I prioritize which entries to refresh first?
- Start with entries that have the highest traffic (from search console data), the oldest verification dates, and those in categories that are actively changing (new model releases, new tool categories).
- What if a tool's official page has been completely removed?
- Archive the entry and note that the tool has been discontinued or the URL is no longer available. Do not delete the entry—keeping it with an archive note preserves the historical record and avoids broken internal links.
- How do I handle entry decisions when the tool is in a gray area between active and declining?
- Apply a default-to-transparency rule: note the uncertainty in the entry (e.g., 'last update unclear, verification pending') rather than removing it or keeping it unmarked. This is more honest and gives readers the context to decide for themselves.
Related
Related
3 Indexed items
Agentic coding vendor readiness review
Turns platform reliability and multi-vendor coding-agent guidance into a checklist before standardizing on a single AI coding stack. Teams inventory host-platform SLAs (for example GitHub availability incidents documented on githubstatus.com), compare primary and backup agents (GitHub Copilot, Cursor, Claude Code, Codex, etc.), verify observability hooks through Braintrust or similar tracing, and rehearse workflows when the code host or agent API is degraded. The skill cites public status pages and vendor billing changes—such as usage-based Copilot pricing announced on github.blog—so procurement and engineering sign off with eyes open about downtime, leadership churn, and feature parity gaps reported in trade media.
Incident response
Structured process for handling production incidents from detection to resolution and post-mortem. Covers severity assessment using P0-P3 grading, team coordination with a designated incident commander, communication templates for stakeholders and users, and structured post-mortem requirements to drive organizational learning from every significant outage.
LiteLLM Router fallback readiness review
Translates LiteLLM routing documentation into a pre-flight checklist before promoting multi-deployment LLM routes to production. Teams verify Router configuration covers primary and fallback model lists, retry policies, and load-balancing strategy documented at docs.litellm.ai/docs/routing, confirm proxy virtual keys and spend limits if traffic flows through LiteLLM Proxy, and rehearse provider outage drills using OpenAI-mapped exceptions (AuthenticationError, RateLimitError, APIError). The skill also points operators to enable `store_model_in_db` when MCP tools must persist alongside router definitions and to validate MCP server names comply with SEP-986 guidance referenced in LiteLLM v1.80.18 release notes.