8x8
8x8 integration. Manage Persons, Organizations, Deals, Leads, Activities, Notes and more. Use when the user wants to interact with 8x8 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/8x8/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 adequately identifies the platform (8x8) and lists the main entity types it can manage, with an explicit 'Use when' clause. However, it lacks specific action verbs beyond 'Manage', uses the vague catch-all 'and more', and misses natural trigger terms users might use like 'CRM', 'contacts', or 'sales pipeline'. The description would benefit from more concrete actions and richer trigger vocabulary.
Suggestions
Replace 'Manage' with specific actions like 'Create, update, search, and delete' to improve specificity.
Add natural trigger terms users might say, such as 'CRM', 'contacts', 'sales pipeline', 'customer data', or '8x8 CRM'.
Remove 'and more' and either list the additional capabilities or omit the phrase, as it adds no selection value.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (8x8) and lists entity types (Persons, Organizations, Deals, Leads, Activities, Notes), but 'Manage' and 'and more' are vague—no specific actions like 'create', 'update', 'delete', or 'search' are mentioned. | 2 / 3 |
Completeness | Answers both 'what' (manage Persons, Organizations, Deals, etc.) and 'when' ('Use when the user wants to interact with 8x8 data') with an explicit trigger clause, though the 'when' is somewhat generic. | 3 / 3 |
Trigger Term Quality | Includes '8x8' as a key trigger term and entity names like 'Persons', 'Deals', 'Leads', but misses natural user phrases like 'CRM', 'contacts', 'pipeline', or 'sales' that users might actually say when needing this skill. | 2 / 3 |
Distinctiveness Conflict Risk | The '8x8' brand name provides some distinctiveness, but terms like 'Persons', 'Organizations', 'Deals', 'Leads' overlap heavily with generic CRM skills (e.g., Pipedrive, HubSpot, Salesforce integrations). Without more specific 8x8 terminology, there's moderate conflict risk. | 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 interacting with 8x8 via Membrane, with good coverage of the full workflow from installation to running actions. However, it includes unnecessary introductory content about what 8x8 is, an unhelpful feature overview list, and a popular actions table with empty descriptions. The workflow could benefit from explicit validation checkpoints between steps.
Suggestions
Remove the introductory paragraph explaining what 8x8 is and the bullet-point feature overview — Claude already knows this and the list isn't tied to actionable commands.
Either add descriptions to the popular actions table or remove it; empty description columns waste tokens without providing value.
Add explicit validation checkpoints between workflow steps, e.g., verify connection succeeded before searching for actions, and verify action search results before running.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what 8x8 is (cloud-based communication platform, used by organizations of all sizes) is unnecessary context Claude already knows. The overview bullet list of features adds little value since it's not tied to actionable guidance. However, the CLI commands and workflow sections are reasonably efficient. | 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 commands include specific flags like --json and --wait with clear explanations. | 3 / 3 |
Workflow Clarity | The multi-step workflows (install → authenticate → connect → search → run) are present and sequenced, but there's no explicit validation or error handling at each step. The action creation flow has state checking (READY vs CONFIGURATION_ERROR) which is good, but the overall connection and action execution flow lacks verification checkpoints (e.g., confirming connection succeeded before searching actions). | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but the overview bullet list of 8x8 features is a wall of items with no actionable links or references. The popular actions table has empty description fields, wasting space. For a skill of this length, some content could be better organized or trimmed rather than inlined. | 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.