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.

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/skills-catalog/skills/(development)/confluence-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

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

The body is well-structured and actionable, with concrete tool calls and three worked examples, but it suffers from redundant sections and lacks explicit validation checkpoints for destructive page-update operations. At ~185 lines with examples and an output template inlined, it would benefit from splitting detail into reference files.

Suggestions

Merge the duplicated 'Project Detection Strategy' and 'Configuration Detection Workflow' sections into one, and drop the 'Important Notes' bullets that restate 'Best Practices' (Markdown-mandatory, search-first, and ID-confusion are each stated twice).

Add explicit validation checkpoints to the create/update workflows: fetch the page and confirm the page ID before updateConfluencePage, verify the space ID from getConfluenceSpaces before createConfluencePage, and confirm the write succeeded afterward — destructive overwrites currently have only advisory 'validate IDs' guidance.

Move the three worked Examples and the Output Format template into references/ files (e.g., references/examples.md, references/output-format.md) and reference them one level deep from SKILL.md to cut the main file roughly in half.

DimensionReasoningScore

Conciseness

The body is mostly lean but contains real duplication: the 'Project Detection Strategy' steps are restated nearly verbatim in 'Configuration Detection Workflow', and 'Important Notes' repeats Best Practices bullets (Markdown-mandatory, search-first, and the ID-confusion warning appear twice). Fits anchor 3 — could be tightened — but there is no padding explaining concepts Claude already knows, so not a 2.

3 / 5

Actionability

Concrete tool invocations with argument shapes (createConfluencePage(cloudId, spaceId, title, body)) plus three fully worked example workflows make the guidance mostly executable. Minor gaps (e.g., getConfluenceSpaces and getPagesInConfluenceSpace signatures only partially specified, search shown only generically) keep it from anchor 5.

4 / 5

Workflow Clarity

The sequence is clear ('Always Start Here' for search, then details, then create/update, mirrored in numbered examples), but validation is advisory ('Validate space exists before creating pages') rather than explicit checkpoints with error-recovery loops. Updating pages destructively overwrites the body with no explicit verify-before-write step, so the destructive-operation cap of 3 applies even though the ordering itself is good.

3 / 5

Progressive Disclosure

No bundle files exist and everything is inline in a ~185-line SKILL.md — well over the under-50-line threshold where a single well-organized file alone earns a 5. Sections and headers are clear, but the Examples section (~45 lines) and the Output Format template (~30 lines) are content that clearly belongs in separate reference files, matching anchor 3 ('content that should be separate is inline').

3 / 5

Total

13

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, explicit trigger phrases users would naturally say, and an unusually good negative boundary that prevents mis-triggering for Jira or general web search. The main weakness is that the capability statement itself ('Expert in Confluence operations') is generic, with the concrete actions carried entirely by the trigger quotes.

DimensionReasoningScore

Specificity

The capability statement 'Expert in Confluence operations using Atlassian MCP' is domain-level, but concrete actions (search, create a page, update a page, list spaces, add a comment) are explicitly enumerated in the trigger phrases. This lists several specific actions with minor gaps (e.g., getting page details is not named), fitting anchor 4 rather than 5, where the comprehensive action list would appear in the capability statement itself.

4 / 5

Completeness

Both what ('Expert in Confluence operations using Atlassian MCP') and when ('Use when the user says...') are present, plus a negative boundary clause. The 'what' portion could be more explicit and concrete, matching anchor 4 ('when' could be more explicit/specific in reverse here) rather than the fully explicit anchor 5.

4 / 5

Trigger Term Quality

Phrases like 'search Confluence', 'create a Confluence page', and 'add a comment to a page' are natural terms users would actually say, giving good keyword coverage. A few common variations and synonyms (e.g., 'Confluence docs', 'wiki') are missing, so it does not reach anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Confluence via Atlassian MCP) with an explicit exclusion ('Do NOT use for Jira issues, general web search, or local file creation') that disambiguates the closest competing skill. Minimal conflict risk, matching anchor 5.

5 / 5

Total

17

/

20

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.

Validation — 16 / 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.