pipedrive-automation
Automate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube MCP (Composio). Always search tools first for current schemas.
75
66%
Does it follow best practices?
Impact
91%
1.13xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/pipedrive-automation/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 is strong in specificity and distinctiveness, clearly identifying Pipedrive CRM as the domain and listing concrete entity types it manages. However, it lacks an explicit 'Use when...' clause which hurts completeness, and the trigger terms could be expanded to include more natural user language like 'sales', 'leads', or 'customers'.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Pipedrive, CRM deals, sales pipelines, or managing contacts and organizations in Pipedrive.'
Include more natural user-facing trigger terms like 'sales', 'leads', 'customers', 'follow-ups', and 'CRM' variations that users would naturally say when needing this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: deals, contacts, organizations, activities, notes, and pipeline management. Also specifies the mechanism (Rube MCP/Composio) and includes a concrete procedural instruction to search tools first for current schemas. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate Pipedrive CRM operations across multiple entity types), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes good domain keywords like 'Pipedrive', 'CRM', 'deals', 'contacts', 'organizations', 'activities', 'notes', 'pipeline', but misses common user variations like 'lead', 'sales', 'follow-up', 'customer', or 'opportunity'. The term 'Rube MCP (Composio)' is technical jargon unlikely to appear in user requests. | 2 / 3 |
Distinctiveness Conflict Risk | Very clearly scoped to Pipedrive CRM specifically, with distinct entity types and a named integration platform (Rube MCP/Composio). Unlikely to conflict with other skills unless there are multiple Pipedrive-related skills. | 3 / 3 |
Total | 10 / 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.
This is a solid, highly actionable skill with clear tool sequences and specific parameter guidance for Pipedrive CRM automation. Its main weaknesses are redundancy across sections (pitfalls repeated in both per-workflow and summary sections), lack of validation/error-handling checkpoints in workflows, and a monolithic structure that could benefit from splitting detailed reference material into separate files.
Suggestions
Add explicit validation steps after key operations (e.g., check response status/data after PIPEDRIVE_ADD_A_DEAL before proceeding to add products) to improve workflow reliability.
Deduplicate pitfalls — keep the per-workflow pitfalls concise and remove the redundant Known Pitfalls section, or consolidate all pitfalls into one section and remove inline duplicates.
Consider splitting the quick reference table and detailed per-workflow parameter/pitfall sections into a separate REFERENCE.md file to keep SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy — pitfalls are repeated across sections and the Known Pitfalls section (e.g., email/phone format, done integer, auto-merge) duplicates information already stated in per-workflow pitfalls. The quick reference table adds value but the overall document is quite long (~250 lines) with some information Claude could infer from tool schemas after calling RUBE_SEARCH_TOOLS. | 2 / 3 |
Actionability | The skill provides specific tool names, exact parameter names with types and formats, concrete examples of data structures (e.g., email array of objects format), and clear tool sequences for each workflow. Every workflow has labeled steps with specific tool slugs and key parameters, making it highly actionable and copy-paste ready. | 3 / 3 |
Workflow Clarity | Tool sequences are clearly numbered with labeled steps (Required/Optional/Prerequisite), which is excellent. However, there are no explicit validation checkpoints or error recovery feedback loops — for example, no guidance on what to do if PIPEDRIVE_ADD_A_DEAL fails, no verification step after creation, and no mention of checking response success/error codes before proceeding to the next step. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's a monolithic document with no bundle files to offload detailed content. The per-workflow parameter lists and pitfalls could be split into separate reference files, keeping SKILL.md as a concise overview with links. The single external link to Composio docs is helpful but insufficient for progressive disclosure. | 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
- davepoon/buildwithclaude
- Commit
d065ead
- 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.