← all publishers

conn-castle

@conn-castle source repo

15 published skills

  1. Ship Pr · conn-castle bundle
    Ship one pull request, monitor hosted CI and review feedback, follow PR policy, and request authorization before merging and cleaning up.
    0
    installs
  2. Find Docs · conn-castle
    Use globally installed `ctx7` for API/library docs when local docs or CLI help are insufficient. Trigger for API syntax, config, setup, migrations, version-sensitive, or post-cutoff questions. Do not use for web research, local files, browser automation, or installs.
    0
    installs
  3. Implement · conn-castle
    Implement a large, substantive code change directly or through a planned cross-agent workflow, adding plan or code review only when warranted.
    0
    installs
  4. Playwright · conn-castle bundle
    Use globally installed `playwright-cli` for browser automation, UI inspection, screenshots, Playwright test debugging, or test generation. Trigger when a task needs browser interaction or test repair. Do not use for generic tests, web search, non-browser docs, or API-only work.
    0
    installs
  5. Skill Sync · conn-castle
    Manage local skills backed by known remote Git repositories. Use when the user wants to import, inspect, diff, pull, resolve, push, reset, or remove them, or project current local skills to enabled clients with `al sync`. Do not use to discover new skills or create user-owned skills.
    0
    installs
  6. Tavily Web · conn-castle
    Use Tavily CLI for web search, URL extraction, site mapping, and cited research. Trigger when the user needs current web info, asks to search/read a page, provides URLs, or wants a sourced report. Do not use for browser automation, local docs, or Tavily setup.
    0
    installs
  7. Audit Tests · conn-castle
    Audit the existing test suite once for redundancy, misleading coverage, organization, and material behavioral gaps, directly fixing safe findings.
    0
    installs
  8. Audit Memory · conn-castle
    Audit agent memory files (ISSUES, BACKLOG, DECISIONS, COMMANDS, CONTEXT) for structure, staleness, placement, consistency, and DECISIONS.md bloat; fix accepted findings.
    0
    installs
  9. Release Prep · conn-castle bundle
    Prepare or ship an Agent Outbox numbered release. Handles fresh and resumed preparation, mandatory human review of marketing captures with substantive differences, verification, the release commit, an explicitly requested push to main, production workflow dispatch, monitoring, and final tag/release proof.
    0
    installs
  10. Dispatch Agent · conn-castle
    Use Agent Dispatch MCP tools only when the user names an external dispatch target or another skill explicitly requires dispatch. Do not use it for generic subagent, second-agent, or fresh-context requests; use the built-in subagent instead.
    0
    installs
  11. Auto Skill Loop · conn-castle bundle
    Run an autonomous loop intended to result in merged PRs.
    0
    installs
  12. Interface Audit · conn-castle bundle
    Audit product interfaces as component boundaries, score complexity, over-engineering, and debt, maintain .agent-layer/tmp interface-audit reports, and finish at the final recommendation gate. Use for fresh interface cleanup audits or --update refreshes; not for implementation.
    0
    installs
  13. Audit Documentation · conn-castle
    Audit Markdown docs for static accuracy and cross-document consistency against the repo, fixing what is safe. Excludes memory files by default.
    0
    installs
  14. Apple Design · conn-castle bundle
    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
    0
    installs
  15. Request HTML Comments · conn-castle bundle
    Request and return element- or text-linked comments on a local HTML file or loopback-served page through an interactive browser overlay. Use when the user wants to annotate local HTML; do not use for remote URLs, browser automation, or code review.
    0
    installs