claims
Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security requirements, single-agent local work.
91
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 97%
↑ 1.79xAgent success when using this skill
Validation for skill structure
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 explicit 'Use when' and 'Skip when' clauses that aid in skill selection. The trigger terms are natural and relevant. The main weakness is that the capability description could be more specific about what types of permissions, claims, or operations are supported.
Suggestions
Add more specific concrete actions beyond 'grant, revoke, verify' - e.g., 'create permission claims, validate agent credentials, audit access logs'
Specify what types of resources or operations can be protected (e.g., 'file access, API calls, tool execution')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (claims-based authorization) and lists some actions (grant, revoke, verify permissions), but lacks comprehensive detail about what specific operations or data types are involved. | 2 / 3 |
Completeness | Clearly answers both what (claims-based authorization, grant/revoke/verify permissions) and when (explicit 'Use when' clause with triggers, plus helpful 'Skip when' guidance for disambiguation). | 3 / 3 |
Trigger Term Quality | Includes good natural keywords users would say: 'permission management', 'access control', 'authorization checks', 'secure operations'. These are terms users naturally use when dealing with security concerns. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on claims-based authorization and multi-agent coordination. The 'Skip when' clause further reduces conflict risk by explicitly excluding single-agent and open-access scenarios. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides actionable CLI commands for claims-based authorization. The tables efficiently convey structured information and commands are copy-paste ready. The main weakness is the lack of workflow guidance showing how to verify operations succeeded or sequence multiple authorization steps together.
Suggestions
Add a brief workflow example showing the sequence: check existing claims → grant new claim → verify grant succeeded
Include verification commands or expected output after grant/revoke operations to confirm success
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables for structured data, no unnecessary explanations of what claims or authorization are. Every section adds value without padding. | 3 / 3 |
Actionability | Provides complete, copy-paste ready CLI commands with realistic examples including agent IDs and scope patterns. Commands are fully executable with clear flag syntax. | 3 / 3 |
Workflow Clarity | Commands are listed individually but there's no workflow showing how to sequence operations (e.g., check before grant, verify after grant). For security-sensitive operations, validation/verification steps after granting or revoking would strengthen this. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single focused purpose, the content is well-organized with clear sections (claim types, commands, scope patterns, security levels). No need for external references given the scope. | 3 / 3 |
Total | 11 / 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.
- 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.