deepgram-enterprise-rbac
Configure enterprise role-based access control for Deepgram integrations. Use when implementing team permissions, managing API key scopes, or setting up organization-level access controls. Trigger: "deepgram RBAC", "deepgram permissions", "deepgram access control", "deepgram team roles", "deepgram enterprise", "deepgram key scopes".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-enterprise-rbac/SKILL.mdQuality
Discovery
89%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 a well-structured skill description with strong completeness and distinctiveness. It clearly identifies its niche (Deepgram enterprise RBAC) and provides explicit trigger guidance. The main weakness is that the capability actions could be more granular and concrete rather than staying at a high level.
Suggestions
Add more specific concrete actions such as 'create and assign roles', 'configure API key permission scopes', 'set up organization and project hierarchies' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Deepgram enterprise RBAC) and some actions (implementing team permissions, managing API key scopes, setting up org-level access controls), but the actions are somewhat high-level and could be more concrete (e.g., 'create roles', 'assign permissions to API keys', 'configure org hierarchies'). | 2 / 3 |
Completeness | Clearly answers both 'what' (configure enterprise RBAC for Deepgram integrations) and 'when' (implementing team permissions, managing API key scopes, setting up org-level access controls) with an explicit 'Use when' clause and additional trigger terms. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms that cover natural variations users would say: 'deepgram RBAC', 'deepgram permissions', 'deepgram access control', 'deepgram team roles', 'deepgram enterprise', 'deepgram key scopes'. These are well-targeted and cover multiple ways a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of 'Deepgram' + 'RBAC/access control'. The trigger terms are all prefixed with 'deepgram', making it very unlikely to conflict with generic RBAC skills or other Deepgram skills focused on different functionality. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with complete, executable TypeScript code covering the full RBAC lifecycle for Deepgram integrations. Its main weaknesses are verbosity (the full implementations could be condensed or split into referenced files) and missing validation checkpoints in the key rotation workflow, where revoking old keys without verifying new ones is risky. The structure is logical but would benefit from progressive disclosure via bundle files.
Suggestions
Add a validation checkpoint in the key rotation workflow: verify the new key works (e.g., a test API call) before revoking the old key, and document a rollback path if creation fails mid-rotation.
Extract the full class implementations (DeepgramKeyManager, TeamManager, rotation function) into separate bundle files and reference them from SKILL.md, keeping only the role definitions, scope table, middleware patterns, and access matrix inline.
Condense the team management code to a brief interface description and key patterns rather than full CRUD implementations, since Claude can generate standard add/remove/change-role logic from a concise spec.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~250 lines of code) and could be tightened. Some code is straightforward enough that Claude could generate it from a briefer specification (e.g., the team management CRUD operations, the middleware patterns). However, it doesn't over-explain concepts and the scope reference table is efficient. | 2 / 3 |
Actionability | The code is fully executable TypeScript with concrete types, real Deepgram SDK calls, Express middleware patterns, and SQL queries. Every step provides copy-paste ready implementations with proper error handling and logging. | 3 / 3 |
Workflow Clarity | The six steps are logically sequenced (define roles → provision keys → middleware → team management → rotation → matrix), but there are no explicit validation checkpoints or feedback loops. For operations involving key creation/revocation (destructive), there's no verify-then-proceed pattern — e.g., no step to verify a newly created key works before revoking the old one during rotation. | 2 / 3 |
Progressive Disclosure | The content is a monolithic file with all implementation details inline. The scope reference table, access control matrix, and error handling table are well-structured, but the extensive code blocks for team management and key rotation could be split into separate reference files. No bundle files exist to offload detail. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.