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".
74
70%
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
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable TypeScript code for Deepgram RBAC implementation, which is its primary strength. However, it is excessively verbose—most of the code is boilerplate that Claude could generate from a concise specification of roles, scopes, and patterns. The workflow lacks validation checkpoints for destructive operations like key revocation, and the entire implementation is inlined rather than being split across reference files.
Suggestions
Drastically reduce code volume: replace full class implementations with the role/scope mapping table, key API patterns (createScopedKey, revokeKey), and middleware signatures—Claude can generate the rest.
Add explicit validation checkpoints: before revoking old keys during rotation, verify the new key works; add a 'test key' step after provisioning.
Split detailed implementations (TeamManager, rotation logic, middleware) into separate reference files and link from the main skill with brief descriptions.
Remove the Output section which just restates what the skill covers—it adds no actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines of code. Much of this is boilerplate TypeScript that Claude could generate from a brief specification. The full Express middleware, TeamManager class, and rotation function could be condensed to interface descriptions and key patterns rather than complete implementations. | 1 / 3 |
Actionability | The code is fully executable TypeScript with concrete API calls, proper error handling, specific Deepgram SDK usage, and copy-paste ready implementations. Every step includes complete, runnable code with real method signatures. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced (define roles → provision keys → middleware → team management → rotation), but there are no explicit validation checkpoints. Key rotation involves destructive operations (revoking keys) without verification steps to confirm the new key works before revoking the old one. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of code with no references to separate files. The scope reference table, access control matrix, middleware, team management, and key rotation could each be split into separate reference files. The Resources section at the end links to external docs but the skill itself has no internal progressive disclosure. | 2 / 3 |
Total | 8 / 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
3e83543
- 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.