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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The content is a well-organized, concrete reference for PagerDuty automation via Rube MCP, but it is monolithic with internal redundancy and lacks executable invocation examples and explicit validation feedback loops for destructive/batch operations.

Suggestions

Move the duplicated pitfalls out of 'Known Pitfalls' (keep them only in their workflow) and consider splitting the 'Quick Reference' table plus detailed tool sequences into a separate reference file.

Add at least one concrete example tool invocation showing the argument structure, and add explicit validate-then-proceed checkpoints for destructive operations (delete override, disable service).

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, useful API detail and avoids explaining concepts Claude already knows, but it is padded by redundancy — the 'Known Pitfalls' section repeats points already in per-workflow 'Pitfalls' and the 'Quick Reference' table restates the tool sequences, so it could be tightened.	2 / 3
Actionability	Concrete tool slugs, specific parameter names, and enum values are provided throughout, but there are no executable example invocations showing the actual call/argument shape, leaving guidance concrete yet incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	Tool sequences are numbered with [Required]/[Optional] markers and the Setup section has a validation checkpoint ('Confirm connection status shows ACTIVE'), but destructive and batch operations (delete override, disable service, bulk ops) lack explicit validate-then-proceed feedback loops, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	No bundle files exist and sections are well organized, but the skill is a ~250-line monolithic file where the detailed tool sequences and quick-reference table could reasonably be split into a separate reference file, fitting the 'content that should be separate is inline' anchor.	2 / 3
	Total	8 / 12 Passed

Description

82%

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 specific, third-person, and clearly niche-scoped to PagerDuty automation with strong natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to manage PagerDuty incidents, on-call schedules, services, or escalation policies.'

Keep the concrete action list but pair it with situational triggers users would naturally say (e.g. 'when on-call rotations need updating').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete action domains — 'manage incidents, services, schedules, escalation policies, and on-call rotations' — matching the anchor for enumerating several specific concrete actions rather than vague language.	3 / 3
Completeness	The 'what' is explicit but there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guideline a missing explicit trigger caps completeness at 2; it cannot reach the level-3 anchor requiring both what and an explicit when.	2 / 3
Trigger Term Quality	Natural terms a user would actually say are well covered — 'PagerDuty', 'incidents', 'schedules', 'on-call rotations', 'escalation policies' — rather than internal jargon, satisfying the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	The PagerDuty-specific niche and Composio/Rube MCP framing make it clearly distinguishable and unlikely to trigger for the wrong skill, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 366e45b

Reviewed: 5 days 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.