CtrlK
BlogDocsLog inGet started
Tessl Logo

confluence-assistant

Expert in Confluence operations using Atlassian MCP. Use when the user says "search Confluence", "create a Confluence page", "update a page", "find documentation in Confluence", "list spaces", or "add a comment to a page". Do NOT use for Jira issues, general web search, or local file creation.

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 content is highly actionable with concrete tool calls and clear sequencing, but it suffers from redundant guidance repeated across three closing sections and lacks post-operation verification loops for destructive page edits. It is also a single monolithic file with no progressive disclosure.

Suggestions

Consolidate the overlapping guidance across "Best Practices (DO)", "IMPORTANT", and "Important Notes" — the use-Markdown, search-first, validate-IDs, and ID-type-confusion points are each repeated 2–3 times and should appear once.

Add a verification/feedback loop after page creation and update (e.g. re-fetch the page to confirm the body rendered correctly, and handle/report errors before claiming success) to support these destructive shared-document operations.

Externalize the generic Markdown output template and/or the worked examples into reference files to reduce the single-file length and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining basics Claude already knows, but the "Best Practices (DO)", "IMPORTANT", and "Important Notes" sections redundantly repeat the same guidance (use Markdown, search first, validate IDs, don't confuse ID types) two to three times, so not every token earns its place.

2 / 3

Actionability

It provides concrete, executable MCP tool calls with real arguments (e.g. createConfluencePage(cloudId, spaceId=..., title=..., body=...)) plus three worked end-to-end examples, matching the copy-paste-ready top anchor.

3 / 3

Workflow Clarity

The Finding→Getting→Creating→Updating sequence is clear and includes pre-validation ("Validate space exists before creating pages"), but creating/updating shared pages are destructive operations with no verify-after feedback loop or error-recovery checkpoint, which caps the score at 2.

2 / 3

Progressive Disclosure

Sections are well organized with easy navigation, but the skill is a monolithic ~190-line single file with no external references; material like the generic Markdown output template and worked examples could be externalized rather than kept inline.

2 / 3

Total

9

/

12

Passed

Description

100%

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, trigger-rich, complete, and well-differentiated, with an explicit exclusivity clause. It uses third-person descriptive voice and avoids vague fluff. No changes needed.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "search Confluence", "create a Confluence page", "update a page", "list spaces", "add a comment to a page" — matching the top anchor for listing several specific actions.

3 / 3

Completeness

It explicitly states both what ("Expert in Confluence operations using Atlassian MCP" plus the action list) and when via an explicit "Use when the user says..." clause, with no missing trigger guidance.

3 / 3

Trigger Term Quality

It quotes natural phrases a user would actually say ("search Confluence", "create a Confluence page", "find documentation in Confluence") giving good coverage of common variations rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The Confluence niche is distinct, and the explicit "Do NOT use for Jira issues, general web search, or local file creation" clause sharply reduces conflict risk with adjacent skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
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.