confluence-automation

Automate Confluence page creation, content search, space management, labels, and hierarchy navigation via Rube MCP (Composio). Always search tools first for current schemas.

1.73x

Quality

—

Does it follow best practices?

Impact

90%

1.73x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The body is highly actionable with specific tool sequences, exact parameters, and ready-to-use CQL, and it assumes Claude's intelligence throughout. It loses points for duplicated pitfalls across sections, missing verification steps on destructive operations, and a monolithic structure with no progressive disclosure.

Suggestions

Remove the standalone "Known Pitfalls" section or replace it with cross-references, since the same pitfalls already appear under each workflow's Pitfalls subsection.

Add explicit verification steps after destructive/batch operations (e.g. re-fetch a page after UPDATE_PAGE to confirm the new version, or verify DELETE_PAGE succeeded) to close the feedback loop.

Move the detailed Quick Reference table and consolidated pitfall reference into a references file (e.g. REFERENCE.md) and keep SKILL.md as a concise overview with a clearly signaled link.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no beginner explanations of Confluence), but the standalone "Known Pitfalls" section restates pitfalls already covered in each workflow's Pitfalls subsection — storage format, version+1, numeric IDs, rate limits — adding avoidable repetition.	2 / 3
Actionability	Guidance is concrete and executable: exact tool slugs, precise parameter and field paths (e.g. "body.storage.value", "version.number"), and copy-paste-ready CQL examples like `title ~ "meeting" AND lastModified > now("-7d") ORDER BY lastModified DESC`.	3 / 3
Workflow Clarity	Workflows are clearly sequenced with prerequisite/optional role tags and a Setup validation checkpoint ("Confirm connection status shows ACTIVE"), but destructive operations like DELETE_PAGE and UPDATE_PAGE lack explicit post-action verification or error-recovery feedback loops, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized (Core Workflows, Common Patterns, Known Pitfalls, Quick Reference), but the skill is a monolithic ~200-line single file with no bundle references; the Quick Reference table and consolidated pitfalls could be split into a reference file to keep SKILL.md an overview.	2 / 3
	Total	9 / 12 Passed

Description

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 specific and clearly distinct, naming several concrete Confluence capabilities and a precise integration path. Its main gap is the absence of an explicit "Use when…" trigger clause, which leaves the when-to-use guidance implied rather than stated.

Suggestions

Add a "Use when…" clause naming natural user triggers, e.g. "Use when the user asks to create or update Confluence pages, search content with CQL, manage spaces, or tag labels."

Include common term variations users might say (e.g. "Confluence docs", "wiki pages", "CQL search") to improve trigger-term coverage.

Drop the procedural "Always search tools first for current schemas" from the description and move it into the body, keeping the description focused on what/when.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "page creation, content search, space management, labels, and hierarchy navigation" — matching the anchor for several specific concrete actions rather than a single vague domain.	3 / 3
Completeness	It clearly states what the skill does, but lacks a "Use when…" clause or equivalent explicit trigger guidance; the trailing "Always search tools first for current schemas" is an instruction, not a when-trigger, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like "Confluence page creation", "content search", and "labels" are natural, but each appears in a single phrasing with no common variations or explicit trigger phrases, fitting the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	Scoping to Confluence automation "via Rube MCP (Composio)" carves out a clear niche with distinct triggers that are unlikely to overlap with other skills.	3 / 3
	Total	10 / 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: about 21 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.