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.
74
65%
Does it follow best practices?
Impact
90%
1.73xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/confluence-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 strong in specificity and distinctiveness, clearly identifying Confluence-related operations and the integration mechanism. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Trigger terms could also be expanded to include common user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Confluence pages, wiki content, Atlassian knowledge bases, or managing Confluence spaces.'
Include additional natural trigger terms users might say, such as 'wiki', 'Atlassian', 'knowledge base', 'Confluence article', or 'team documentation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'page creation, content search, space management, labels, and hierarchy navigation'. Also specifies the integration method (Rube MCP / Composio) and includes a procedural note about searching tools first. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific Confluence operations, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the capabilities listed, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Confluence', 'page creation', 'content search', 'space management', 'labels', and 'hierarchy navigation'. However, it misses common user variations like 'wiki', 'Atlassian', 'knowledge base', or 'Confluence page' as a phrase users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Confluence', 'Rube MCP (Composio)', and Confluence-specific operations like space management and hierarchy navigation. Unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized Confluence automation skill with clear workflow sequences and good documentation of pitfalls and parameters. Its main weaknesses are the lack of concrete executable examples (no actual tool call payloads or sample inputs/outputs) and significant redundancy between per-workflow pitfalls and the consolidated Known Pitfalls section. Trimming duplicated content and adding 1-2 concrete call examples would significantly improve it.
Suggestions
Add at least one concrete, complete tool call example (e.g., a full CONFLUENCE_CREATE_PAGE invocation with actual parameter values and expected response structure) to improve actionability.
Remove the consolidated 'Known Pitfalls' section or the per-workflow pitfalls — having both creates redundancy that wastes tokens. Consolidate into one location.
Consider extracting the CQL operators/fields reference and the Quick Reference table into separate linked files to improve progressive disclosure and reduce the main file's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy — pitfalls are repeated across sections and again in a consolidated 'Known Pitfalls' section. The content could be tightened by ~30% without losing information. However, it doesn't over-explain basic concepts Claude already knows. | 2 / 3 |
Actionability | Tool sequences are clearly named and ordered with key parameters documented, which is good. However, there are no executable code/command examples — no actual MCP tool call syntax, no example payloads, and no concrete input/output examples showing what a real CONFLUENCE_CREATE_PAGE call looks like with its parameters filled in. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, each tool annotated as [Required], [Optional], [Prerequisite], or [Fallback]. The setup section includes a verification checkpoint (confirm ACTIVE status before proceeding). Update workflows explicitly require fetching current version first, and pitfalls call out version conflict handling. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a quick reference table, but it's quite long (~200+ lines) and monolithic. The 'Known Pitfalls' section largely duplicates pitfalls already listed in each workflow section. Content like CQL operators/fields reference or the full quick reference table could be split into separate files to keep the main skill leaner. | 2 / 3 |
Total | 9 / 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.