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.

69

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A solid, mostly actionable skill body with a clear workflow and concrete tool-call examples. The main weakness is verbosity from a duplicated configuration section, a Markdown-structure template that over-explains basics Claude knows, and a safety rule repeated three times.

Suggestions

Collapse the "Project Detection Strategy" and "Configuration Detection Workflow" into a single section — they describe the same Cloud-ID detection steps twice.

Remove or drastically shrink the Output Format section; it teaches Markdown basics (headings, bullets, code blocks) that Claude already knows, which the conciseness rubric explicitly penalizes.

State the "always Markdown, never HTML" rule once (e.g. in Best Practices) and drop the repetitions in the Creating, Updating, and Important Notes sections.

DimensionReasoningScore

Conciseness

The core workflow (search/get/create/update tool calls) is efficient, but the Output Format section spends ~30 lines teaching Markdown structure Claude already knows, configuration guidance is duplicated across "Project Detection Strategy" and "Configuration Detection Workflow", and the Markdown-not-HTML rule is stated three times.

3 / 5

Actionability

Concrete tool calls with realistic arguments (search("..."), getConfluencePage(cloudId, pageId), createConfluencePage(cloudId, spaceId=..., title=..., body=...)) plus three fully worked end-to-end examples make guidance mostly executable, with only minor gaps around placeholder resolution.

4 / 5

Workflow Clarity

A clear numbered workflow (Finding Content → Getting Details → Creating → Updating) with "Always Start Here" sequencing and validation reminders ("Validate space exists before creating pages", "Validate IDs"), though explicit validate-then-retry feedback loops for overwriting updates are only implied.

4 / 5

Progressive Disclosure

Well-organized into clear sections (When to Use, Configuration, Workflow, Best Practices, Examples, Output Format) with no nested references; the Examples and Output Format template could arguably live in a reference file, but the single-file structure is navigable.

4 / 5

Total

15

/

20

Passed

Description

100%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.

An exemplary description: it states the capability concretely, enumerates natural user trigger phrases, and draws clear negative boundaries against overlapping domains. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (search, create, update, list spaces, add comment, get page details) tied to a named domain (Confluence via Atlassian MCP), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ("Expert in Confluence operations using Atlassian MCP") and when ("Use when the user says..." with concrete trigger phrases).

5 / 5

Trigger Term Quality

Six natural phrasings a user would actually say ("search Confluence", "create a Confluence page", "update a page", "find documentation in Confluence", "list spaces", "add a comment to a page") cover the surface broadly.

5 / 5

Distinctiveness Conflict Risk

A clear Confluence-only niche with explicit negative boundaries ("Do NOT use for Jira issues, general web search, or local file creation") minimizes conflict with adjacent skills.

5 / 5

Total

20

/

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.

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.