deepgram-python-management-api
Use when writing or reviewing Python code in this repo that calls Deepgram Management APIs - projects, API keys, members, invites, usage, billing, models, and reusable Voice Agent configurations. Covers `client.manage.v1.projects`, project-scoped resources under `client.manage.v1.projects.*` (keys, members, members.invites, usage, billing, models, requests), global `client.manage.v1.models`, think-model discovery at `client.agent.v1.settings.think.models`, and `client.voice_agent.configurations.*`. Use `deepgram-python-voice-agent` when you want to run an agent interactively, this skill to PERSIST/LIST agent configs. Triggers include "management API", "list projects", "API keys", "members", "usage stats", "billing", "list models", "agent configurations", "manage.v1".
71
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that is highly specific, includes comprehensive trigger terms, clearly answers both what and when, and proactively distinguishes itself from a related skill. The explicit SDK path references and the boundary clarification with the voice-agent skill are particularly strong. The description is dense but informative without unnecessary fluff.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and resources: projects, API keys, members, invites, usage, billing, models, voice agent configurations, with specific SDK paths like `client.manage.v1.projects`, `client.voice_agent.configurations.*`. | 3 / 3 |
Completeness | Clearly answers both 'what' (calling Deepgram Management APIs for projects, keys, members, usage, billing, models, voice agent configs) and 'when' (explicit 'Use when writing or reviewing Python code in this repo that calls Deepgram Management APIs' plus explicit trigger list). Also distinguishes from a related skill (`deepgram-python-voice-agent`). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms users would say: 'management API', 'list projects', 'API keys', 'members', 'usage stats', 'billing', 'list models', 'agent configurations', 'manage.v1'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Deepgram Management APIs in Python) and explicitly differentiates itself from the related `deepgram-python-voice-agent` skill, explaining the boundary ('this skill to PERSIST/LIST agent configs' vs running an agent interactively). | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, comprehensive management API skill with excellent actionability — nearly every API surface has executable, copy-paste-ready code. The progressive disclosure and organization are well done with clear section hierarchy and external references. Main weaknesses are minor verbosity from some repeated information (agent config constraints stated in both code comments and Gotchas) and the lack of validation/safety patterns around destructive operations.
Suggestions
Add a brief safe-delete pattern or validation checkpoint for destructive operations (delete project/key/config) rather than just commenting them out — e.g., a verify-before-delete snippet.
Consolidate the agent config constraints: remove the inline code comments about 'agent block only' since Gotchas #4 and #5 cover this thoroughly, reducing duplication.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but some sections are slightly verbose — e.g., the 'Central product skills' section and repeated explanations about agent config being 'agent block only' (mentioned in Quick start comments AND Gotchas #5). The Gotchas section, while valuable, is lengthy at 10 items and some overlap with inline comments in code. | 2 / 3 |
Actionability | Excellent executable code examples covering all major API surfaces — projects, keys, members, invites, usage, billing, models, voice agent configs, and async. Code is copy-paste ready with correct method signatures, and critical details like `request=` payload pattern and `config=json.dumps(...)` are explicitly shown. | 3 / 3 |
Workflow Clarity | The skill covers many independent API calls rather than a multi-step workflow, so sequencing is less critical. However, for destructive operations (delete project, delete key, delete agent config), there are no validation checkpoints or confirmation patterns — just commented-out lines. The Gotchas mention 'wire tests typically comment out destructive calls' but don't provide a safe pattern for production use. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from authentication → quick starts → async → API reference → gotchas. References to external resources are one level deep and clearly signaled (reference.md, OpenAPI, Context7, product docs, example files). The layered API reference section is particularly well organized. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-python-sdk
- Commit
e169f63
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.