15five
15Five integration. Manage Persons, Organizations. Use when the user wants to interact with 15Five data.
72
66%
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 ./skills/15five/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description correctly identifies the integration target (15Five) and provides a 'Use when' clause, but the capabilities listed are vague ('Manage') and the entity names ('Persons', 'Organizations') are generic. The description would benefit from more specific actions and richer trigger terms that reflect how users naturally talk about 15Five functionality.
Suggestions
Replace 'Manage' with specific concrete actions like 'Create, update, list, and delete Persons and Organizations' to improve specificity.
Add natural trigger terms users might say, such as 'employees', 'team members', 'performance reviews', 'HR data', or '15Five API' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (15Five) and mentions 'Manage Persons, Organizations' which are some actions, but 'manage' is vague and doesn't specify concrete operations like create, update, delete, or list. | 2 / 3 |
Completeness | Answers both 'what' (manage Persons, Organizations in 15Five) and 'when' ('Use when the user wants to interact with 15Five data'), though the 'when' clause is somewhat generic. | 3 / 3 |
Trigger Term Quality | Includes '15Five' as a key trigger term and mentions 'Persons' and 'Organizations', but misses natural variations users might say like 'employees', 'people', 'companies', 'HR', or 'performance management'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Persons' and 'Organizations' are generic entity names that could overlap with CRM or HR tools. However, the specific mention of '15Five' provides some distinctiveness for users who explicitly reference that platform. | 2 / 3 |
Total | 9 / 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.
The skill provides solid, actionable CLI commands for integrating with 15Five via Membrane, covering the full lifecycle from setup to execution. Its main weaknesses are unnecessary introductory fluff, a popular actions table where every description is 'No description' (adding bulk without value), and a lack of explicit validation/error-recovery steps in the workflow. The content could be tightened significantly while preserving all useful guidance.
Suggestions
Remove or drastically shorten the introductory paragraph explaining what 15Five is — Claude already knows this, and the skill description covers it.
Either add meaningful descriptions to the popular actions table or remove it entirely, as 20 rows of 'No description' waste tokens without aiding discovery.
Add explicit validation checkpoints to the workflow, e.g., verifying connection success after `membrane connect` and checking action run output for errors before proceeding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary explanation (e.g., 'performance management platform that helps companies improve employee engagement...') and the overview bullet list adds no actionable value. The popular actions table has 'No description' for every entry, wasting tokens. However, the CLI commands themselves are reasonably lean. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready CLI commands for every step: installation, authentication, connecting, searching actions, creating actions, polling, and running actions with input parameters. The guidance is concrete and specific. | 3 / 3 |
Workflow Clarity | The steps are presented in a logical sequence (install → auth → connect → search → create/run), and the action creation flow includes polling with state checking. However, there are no explicit validation checkpoints or error recovery feedback loops for the overall workflow, and the headless auth flow could be more clearly sequenced. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and headers, but it's somewhat monolithic — the popular actions table and best practices could be separated or trimmed. There are no references to external detail files, though for a skill of this size (~100 lines) that's borderline acceptable. The overview section is a dead-end list with no links or elaboration. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- membranedev/application-skills
- Commit
56d7336
- 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.