adk

In the author's own words, from each skill's SKILL.md.

• poly-adk-branching

  This skill should be used when the user wants to "resolve merge conflicts", "merge a branch", "fix conflict markers", "create a hotfix branch", "share changes for review", or manage branches in a PolyAI ADK project — or when poly pull or poly branch merge reports conflicts. Covers branch management, the three-way merge model, non-interactive conflict resolution, and review gists. Part of the Poly…

  skills/poly-adk-branching/SKILL.md on GitHub (opens in a new tab)

• poly-adk-conversations

  This skill should be used when the user wants to "see what happened on a call", "review real conversations", "download a call recording", "debug a production call", or "add logging/metrics" to a PolyAI agent. Covers poly conversations and instrumenting functions with conv.log and metrics. Part of the PolyAI ADK skills suite. Do NOT use for simulated test conversations (use poly-adk-testing).

  skills/poly-adk-conversations/SKILL.md on GitHub (opens in a new tab)

• poly-adk-rtc

  This skill should be used when the user wants to "change real-time configuration", "update RTC", "edit per-environment config", or work with the real_time_configuration/ directory of a PolyAI ADK project. Covers poly rtc pull/push/edit/diff/validate, drift protection, and the live-environment hazard. Part of the PolyAI ADK skills suite. Do NOT use for resources that deploy through branches (use p…

  skills/poly-adk-rtc/SKILL.md on GitHub (opens in a new tab)

• poly-adk-testing

  This skill should be used when the user wants to "test the agent", "chat with the agent", "call the agent", "run the test suite", "write a test case", "check why a test failed", or "run a function" built with the PolyAI ADK. Covers poly validate, scripted poly chat, the test_suite/ simulated conversation tests, and executing functions in isolation. Part of the PolyAI ADK skills suite. Do NOT use…

  skills/poly-adk-testing/SKILL.md on GitHub (opens in a new tab)

• poly-adk-workflow

  This skill should be used when the user wants to "build an agent", "update an agent", "create a PolyAI project", "push changes to Agent Studio", or work with the PolyAI ADK (`poly`) in any way. Entrypoint for the PolyAI ADK skills suite — covers setup, project structure, resource choice, and the core edit/validate/push/test/merge workflow, and routes to the task-specific skills (testing, branchin…

  skills/poly-adk-workflow/SKILL.md on GitHub (opens in a new tab)

• add-resource-type

  Add a new Agent Studio resource type to the ADK, covering the class, registration, projection parsing, tests, fixture and docs. Use when asked to support a new resource in the polyai-adk repo.

  .claude/skills/add-resource-type/SKILL.md on GitHub (opens in a new tab)

• ci-check

  Run the same checks as the ADK's GitHub CI (PR title, lint, format, licences, licenses.json, skill versions, tests) locally and report pass/fail. Use before pushing a branch or opening a pull request in the polyai-adk repo.

  .claude/skills/ci-check/SKILL.md on GitHub (opens in a new tab)

• open-pr

  Prepare and open a pull request on the polyai-adk repo, with checks run, the right conventional-commit title, the repo's PR template filled in and no internal references. Use when asked to open, create or raise a PR for ADK changes.

  .claude/skills/open-pr/SKILL.md on GitHub (opens in a new tab)

• review-pr

  Review an ADK pull request or local branch against the repo's review checklist (REVIEW.md) and report blocking issues and nits. Use when asked to review a PR in the polyai-adk repo, or to self-review a branch before opening one.

  .claude/skills/review-pr/SKILL.md on GitHub (opens in a new tab)

• write-tests

  Write readable tests for new or changed ADK code and show that coverage of the touched modules didn't drop. Use after implementing a feature or fix in the polyai-adk repo, or when asked to add test coverage.

  .claude/skills/write-tests/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• SkillSpectorby NVIDIA Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and… 20.3k stars · 27 skills
• openrigby mvschwarz Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work. 7.5k stars · 30 skills
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 107k stars · 25 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills