Automate BambooHR tasks via Rube MCP (Composio): employees, time-off, benefits, dependents, employee updates. Always search tools first for current schemas.
65
53%
Does it follow best practices?
Impact
79%
1.27xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/bamboohr-automation/SKILL.mdQuality
Discovery
57%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 identifies a clear niche (BambooHR automation via Rube MCP/Composio) and lists relevant task categories, making it distinctive. However, it lacks specific concrete actions within each category and is missing an explicit 'Use when...' clause that would help Claude know when to select this skill. The trigger terms are decent but could include more natural user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about BambooHR, employee records, PTO/time-off requests, benefits enrollment, or HR data management.'
Replace category nouns with concrete action phrases, e.g., 'Look up employee records, submit and approve time-off requests, manage benefits enrollment, add dependents, update employee profiles.'
Include common user-facing synonyms like 'PTO', 'leave requests', 'HR system', 'employee directory' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (BambooHR) and lists several action areas (employees, time-off, benefits, dependents, employee updates), but these are more like categories than concrete actions. It doesn't specify what operations are performed (e.g., 'create employees', 'approve time-off requests', 'update benefit plans'). | 2 / 3 |
Completeness | The 'what' is partially addressed (automate BambooHR tasks across several domains), but there is no explicit 'Use when...' clause. The instruction to 'always search tools first' is an implementation detail rather than a trigger condition. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'BambooHR', 'time-off', 'benefits', 'dependents', 'employees', and 'Rube MCP (Composio)' which are useful triggers. However, it misses common variations users might say like 'PTO', 'leave requests', 'HR system', 'employee directory', or 'payroll'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to BambooHR via Rube MCP (Composio), which is a very specific integration. It's unlikely to conflict with other skills unless there are multiple BambooHR-related skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent but verbose BambooHR integration skill that provides good workflow coverage and clear tool sequences. Its main weaknesses are redundancy (pitfalls repeated in multiple places), lack of executable examples (pseudocode rather than concrete tool invocations), and missing validation/error-recovery steps in workflows that modify data. Trimming redundancy and adding concrete invocation examples with validation checkpoints would significantly improve it.
Suggestions
Consolidate pitfalls into a single section and remove duplicated warnings from individual workflows to reduce token count by ~30%.
Add concrete, copy-paste-ready MCP tool invocation examples with actual parameter values (e.g., a complete RUBE_SEARCH_TOOLS call followed by a BAMBOOHR_CREATE_TIME_OFF_REQUEST with sample params).
Add explicit validation/verification steps after destructive operations—e.g., after UPDATE_EMPLOYEE, call GET_EMPLOYEE to confirm the update took effect; after CREATE_TIME_OFF_REQUEST, verify the request appears in GET_TIME_OFF_REQUESTS.
Split detailed per-workflow documentation and the pitfalls/patterns sections into separate bundle files, keeping SKILL.md as a concise overview with references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but contains significant redundancy—pitfalls are repeated across individual workflows and then again in the 'Known Pitfalls' section (e.g., employee IDs being numeric, date formats). The 'Common Patterns' section largely restates the workflow sequences already described above. Several explanations (e.g., what PII is, that terminated employees retain IDs) are things Claude already knows. | 2 / 3 |
Actionability | The skill provides clear tool names, parameter lists, and step sequences, which is good. However, there are no executable code examples—the patterns are pseudocode-style numbered lists rather than actual MCP tool invocations with concrete parameter values. Key details like exact response shapes are deferred to 'check RUBE_SEARCH_TOOLS' rather than provided. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with prerequisite/required/optional labels, which is helpful. However, there are no explicit validation checkpoints or error-recovery feedback loops—for example, the employee update workflow says to verify current values but doesn't include a validation step after the update, and the time-off workflow doesn't address what to do if balance is insufficient or request creation fails. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's monolithic at ~200 lines with no bundle files to offload detail into. The detailed pitfalls, common patterns, and per-workflow documentation could be split into separate reference files. The single external link to Composio docs is appropriate but the skill itself tries to contain everything inline. | 2 / 3 |
Total | 8 / 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 | |
d065ead
Table of Contents
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.