sentry-automation
Automate Sentry tasks via Rube MCP (Composio): manage issues/events, configure alerts, track releases, monitor projects and teams. Always search tools first for current schemas.
71
58%
Does it follow best practices?
Impact
94%
1.77xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/sentry-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 reasonably strong with specific capabilities and a clear domain niche around Sentry automation via Rube MCP. Its main weaknesses are the lack of an explicit 'Use when...' clause and missing natural trigger terms that users would commonly associate with error monitoring and tracking. The operational instruction about searching tools first is a nice touch but doesn't compensate for the missing trigger guidance.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Sentry error tracking, monitoring exceptions, managing alerts, or working with Composio/Rube MCP for Sentry.'
Include natural user-facing trigger terms like 'error tracking', 'error monitoring', 'crash reports', 'exceptions', and 'bug tracking' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: manage issues/events, configure alerts, track releases, monitor projects and teams. Also includes the operational guidance to search tools first for current schemas. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate Sentry tasks via Rube MCP with specific capabilities listed), but lacks an explicit 'Use when...' clause. The 'when' is only implied by the domain terms. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Sentry', 'issues', 'events', 'alerts', 'releases', 'projects', 'teams', and 'Composio/Rube MCP'. However, it misses common user variations like 'error tracking', 'error monitoring', 'bug tracking', 'crash reports', or 'exceptions' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Sentry' and 'Rube MCP (Composio)' which clearly carve out a unique niche. Unlikely to conflict with other skills unless there are multiple Sentry-related skills. | 3 / 3 |
Total | 10 / 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 reasonably well-organized skill that covers Sentry operations comprehensively with clear tool sequences and parameter documentation. Its main weaknesses are redundancy (slug vs display name warnings repeated 5+ times), lack of concrete executable examples for complex operations like alert rule creation, and missing validation/verification steps in workflows. The content would benefit from consolidation of repeated pitfalls, addition of concrete JSON examples, and splitting detailed workflow sections into separate files.
Suggestions
Consolidate repeated pitfalls (org slug vs display name, ID formats) into a single 'ID Resolution' section and remove duplicates from individual workflows to save ~30% of tokens.
Add a concrete JSON example for alert rule creation showing actual conditions/actions/filters arrays, since these are described as having 'specific JSON schemas' but no example is provided.
Add verification steps to destructive/creation workflows (e.g., after creating a release, call LIST_ORGANIZATION_RELEASES to confirm; after creating an alert rule, call GET_PROJECT_RULE_DETAILS to verify).
Consider moving the detailed workflow sections (alerts, releases, monitors) into separate referenced files, keeping SKILL.md as an overview with the quick reference table and setup instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes repetitive information — pitfalls about org slugs vs display names are repeated across nearly every workflow section and again in the Known Pitfalls section. The quick reference table at the end largely duplicates information already presented in the workflow sections. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | Tool names and parameter lists are concrete and specific, which is good. However, there are no executable code examples or concrete JSON payloads for alert rule conditions/actions/filters, which are described as having 'specific JSON schemas.' The ID resolution patterns use pseudocode rather than actual tool call examples. The skill describes rather than demonstrates for the more complex workflows. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with labeled steps and [Required]/[Optional]/[Prerequisite] annotations, which is helpful. However, there are no validation or verification checkpoints — for example, after creating an alert rule or release, there's no step to verify it was created correctly. The setup section does include a verification step for connection status, but the core workflows lack feedback loops. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's quite long (~200+ lines) with all content inline. The alert rules, releases, and monitoring sections could be split into separate reference files. The only external reference is the Composio toolkit docs link. The quick reference table is a nice touch but adds to the monolithic feel. | 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 | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.