apigee/devrel/apigee-policy-top10
Claude Code and agent skill by apigee/devrel
- community
Checking that the SKILL.md file is still in the repository.
Reports the top 10 Apigee policy types currently in use
Install
npx vskill@latest install apigee/devrel/apigee-policy-top10Semi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard
SKILL.md
apigee-policy-top10
Use this skill when the user asks "what are the top N policies in use in my Apigee org" or any close paraphrase.
Runtime dispatch
This skill ships ONE behavioural contract that runs on two runtimes. Choose the invocation path that matches the runtime you are running in. The downstream behaviour and output contract are identical.
| Runtime | How you invoke top10.py | |
|---|---|---|
| OpenCode | Use the !bash`` injection below. OpenCode auto-executes the bash on SKILL.md load. | |
| Gemini CLI / Claude Code / other agents | (install location varies; consult the agent's documentation) | |
| Any other runtime | Invoke top10.py via whatever bash mechanism the runtime provides, substituting ${SKILL_DIR} with the install path and ${APIGEE_ORG} with the value from the shell environment. |
Steps
- Resolve the target organization from the environment variable
APIGEE_ORG. If unset, ask the user once for the org id and then proceed.
- Invoke the bundled enumerator using the runtime path from the
table above. The exact command is:
Command (this is what OpenCode runs automatically; in other agent runtimes you run it yourself via the bash tool):
!python3 ${SKILL_DIR}/scripts/top10.py --org "${APIGEE_ORG}"
- The enumerator's FIRST line of stdout is a customer-facing
announcement that begins Querying your Apigee org now —. Surface this line verbatim to the user as it appears, before anything else. Do not paraphrase it. (The script is the source of truth for the announcement string; the SKILL.md does NOT contain a verbatim copy that the agent must remember.)
- After the announcement, the script prints a markdown table with
two columns (policy_type, count) sorted descending. Reproduce the table verbatim as the answer. Add a brief preface ("Here are the top 10 policy types in use…") and stop.
- Lines beginning
[apigee-policy-top10]are log lines for
operator debugging; do NOT surface them in the answer unless they say FAILED. On any FAILED line, surface the verbatim error to the user; do not retry.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingreferences/apigee-skills-serving/skills/apigee-policy-top10/SKILL.md
Popularity
- Repository stars
- 220
- Repository forks
- 173
- 7-day trend score
- 27
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/apigee/devrel/apigee-policy-top10)