1crm
1CRM integration. Manage data, records, and automate workflows. Use when the user wants to interact with 1CRM data.
59
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/1crm/SKILL.mdQuality
Discovery
75%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 has a solid structure with an explicit 'Use when' clause and a distinctive product name (1CRM) that minimizes conflict risk. However, it falls short on specificity of capabilities and trigger term coverage — the actions described are generic ('manage data, records') rather than concrete, and it lacks natural keyword variations users might employ when seeking CRM-related help.
Suggestions
List specific concrete actions such as 'create and update contacts, manage deals, track sales pipeline, generate reports' instead of the generic 'manage data, records'.
Add natural trigger term variations like 'CRM', 'customer records', 'contacts', 'leads', 'sales data', or 'customer relationship management' to improve matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (1CRM) and some actions ('manage data, records, and automate workflows'), but these are fairly generic and not comprehensive — it doesn't list specific concrete actions like 'create contacts', 'update deals', 'generate reports', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (manage data, records, automate workflows in 1CRM) and 'when' (explicit 'Use when the user wants to interact with 1CRM data'), satisfying the requirement for an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes '1CRM' as a key trigger term and 'data', 'records', 'workflows', but misses natural variations users might say like 'CRM', 'contacts', 'leads', 'sales pipeline', 'customer management', or specific 1CRM entity names. | 2 / 3 |
Distinctiveness Conflict Risk | The specific mention of '1CRM' as a named product creates a clear niche that is unlikely to conflict with other skills — it would only trigger when users specifically reference 1CRM. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides strong, actionable CLI-based workflows for connecting to and interacting with 1CRM via Membrane, with clear state-machine logic for connection setup. However, it is significantly bloated by an unnecessary 45-item entity list and an introductory paragraph explaining what CRM software is — information Claude already possesses. Removing the filler content would make this a much stronger skill.
Suggestions
Remove the opening paragraph explaining what 1CRM is and the entire 45-item entity bullet list — these consume tokens without providing actionable guidance.
If the entity list is important for action discovery, condense it to a single line like 'Supports standard CRM entities: Accounts, Contacts, Leads, Opportunities, Cases, and 40+ others.'
Remove the 'Use action names and parameters as needed' line, which is vague and non-actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explains what CRM is, which Claude already knows. The massive 45-item bullet list of 1CRM entities adds no actionable value — it's just a feature list with no instructions. The 'Use action names and parameters as needed' line is vague filler. | 1 / 3 |
Actionability | The skill provides fully executable CLI commands for authentication, connection setup, action discovery, action execution, and proxy requests. Commands are copy-paste ready with clear flag descriptions and parameter examples. | 3 / 3 |
Workflow Clarity | The connection workflow is well-sequenced with explicit state checks (READY, BUILDING, CLIENT_ACTION_REQUIRED, errors), polling instructions, and clear branching logic for each state. The headless auth flow includes a feedback loop for code completion. | 3 / 3 |
Progressive Disclosure | Content is organized into logical sections with headers, but the massive entity list bloats the main file unnecessarily. There are no references to supporting files, and the overview section could be removed or condensed significantly. The skill is a single monolithic file when some content (e.g., proxy request options table) could be separated. | 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
f484c82
- 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.