pagerduty-automation

Automate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call rotations. Always search tools first for current schemas.

1.09x

Quality

47%

Does it follow best practices?

Impact

84%

1.09x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/pagerduty-automation/SKILL.md

Quality

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 does a good job of specifying the concrete PagerDuty capabilities and is highly distinctive due to the specific product domain. However, it lacks an explicit 'Use when...' clause which caps completeness, and the trigger terms could be expanded to include more natural user language like 'who is on call' or 'incident alerts'.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about PagerDuty incidents, on-call schedules, escalation policies, or needs to manage alerting workflows.'

Include more natural user trigger terms such as 'who is on call', 'page someone', 'incident alerts', 'duty roster', or 'respond to an incident'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: manage incidents, services, schedules, escalation policies, and on-call rotations. Also specifies the mechanism (Rube MCP via Composio) and includes a behavioral instruction about searching tools first.	3 / 3
Completeness	Clearly answers 'what does this do' (automate PagerDuty tasks including incidents, services, schedules, etc.), but lacks an explicit 'Use when...' clause. The 'when' is only implied by the domain terms rather than explicitly stated.	2 / 3
Trigger Term Quality	Includes good domain-specific terms like 'PagerDuty', 'incidents', 'services', 'schedules', 'escalation policies', 'on-call rotations', but lacks common user variations like 'paging', 'alerts', 'who is on call', 'incident response', or 'duty schedule'. The mention of 'Rube MCP (Composio)' is technical jargon unlikely to appear in user queries.	2 / 3
Distinctiveness Conflict Risk	PagerDuty is a very specific product/service, and the description clearly scopes to PagerDuty automation via a specific toolchain (Rube MCP/Composio). This is unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is comprehensive in coverage but severely over-engineered for a SKILL.md file. It duplicates information that Claude can discover via RUBE_SEARCH_TOOLS (which the skill itself mandates calling first), includes no executable examples, and packs all reference material into a single monolithic document. The workflow sequences are well-organized but lack validation/error-handling steps.

Suggestions

Drastically reduce content by removing tool parameter details and pitfalls that RUBE_SEARCH_TOOLS already provides — keep only the non-obvious gotchas (e.g., status transitions being forward-only, service references needing type field).

Move the quick reference table and per-workflow tool listings into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with setup + core patterns only.

Add validation steps to workflows: e.g., after creating an incident, verify the response contains the expected ID and status; handle error responses explicitly.

Replace pseudocode patterns with concrete tool call examples showing actual parameter structures (e.g., a real PAGERDUTY_CREATE_INCIDENT_RECORD call with service object).

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~250+ lines. It exhaustively lists every tool slug, parameter, and pitfall for 6 workflow categories plus a full quick reference table. Much of this is reference material that Claude could discover via RUBE_SEARCH_TOOLS (which the skill itself says to always call first). The ID resolution patterns and incident lifecycle are things Claude already knows. Significant redundancy between workflow sections and the quick reference table.	1 / 3
Actionability	The skill provides specific tool names, parameter names, and key constraints (e.g., service references need type 'service_reference'), which is useful. However, there are no executable code examples — the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual tool call examples with concrete parameters. The guidance is specific but not copy-paste ready.	2 / 3
Workflow Clarity	Workflows are clearly sequenced with numbered steps and labeled as Required/Optional, which is helpful. However, there are no validation checkpoints or feedback loops — no guidance on verifying that an incident was actually created, checking for error responses, or handling failures. For operations that modify PagerDuty state (creating incidents, updating services), missing validation caps this at 2.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with all content inline. The detailed parameter lists, pitfalls for each workflow, and the full quick reference table could easily be split into separate reference files. There are no references to external files for detailed content — everything is crammed into one document, making it a large context burden.	1 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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: about 4 hours ago

Table of Contents

Discovery Implementation Validation

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.