CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

54

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/confluence-automation/SKILL.md

The canonical home for this skill is confluence-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%Scale 1-5

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

This is a solid, well-organized Confluence automation skill that provides clear tool sequences, specific parameter guidance, and useful pitfall warnings. Its main weaknesses are redundancy (pitfalls repeated in both workflow sections and a dedicated section), lack of executable examples showing complete tool invocations, and a monolithic structure that would benefit from splitting detailed references into separate files.

Suggestions

Consolidate the per-workflow 'Pitfalls' subsections and the 'Known Pitfalls' section into a single location to eliminate redundancy and improve conciseness.

Add at least one complete, copy-paste ready tool invocation example (e.g., a full RUBE_SEARCH_TOOLS call followed by CONFLUENCE_CREATE_PAGE with all parameters filled in) to improve actionability.

Add explicit validation/verification steps to workflows — e.g., after CREATE_PAGE, verify the page exists by calling GET_PAGE_BY_ID; after UPDATE_PAGE, confirm the version number incremented.

Remove or replace the empty 'When to Use' section at the end, which adds no value beyond the description already in the overview.

DimensionReasoningScore

Conciseness

The skill is fairly comprehensive but has notable redundancy — the 'Known Pitfalls' section largely repeats pitfalls already listed under each workflow section. The 'When to Use' section at the end is vacuous. Some parameter descriptions are useful but the overall document could be tightened by ~30% without losing information.

3 / 5

Actionability

The skill provides concrete tool names, specific parameter names, CQL syntax examples, and clear tool sequences for each workflow. However, it lacks executable code examples or copy-paste ready CQL queries/API calls — guidance is specific but stays at the parameter-description level rather than showing complete invocation examples.

4 / 5

Workflow Clarity

Each workflow has a clearly numbered tool sequence with labeled steps (Prerequisite, Required, Optional, Fallback). The update workflow correctly specifies fetching current version before updating. However, there are no explicit validation/verification checkpoints or error recovery feedback loops (e.g., 'if creation fails due to duplicate title, search and update instead'), which prevents a score of 5.

4 / 5

Progressive Disclosure

The content is well-structured with clear sections and a quick reference table, but it's a long monolithic document (~200+ lines) with no references to external files. The repeated pitfalls sections and the detailed CQL reference could be split into separate files. With no bundle files provided, everything is inlined in a single document.

3 / 5

Total

14

/

20

Passed

Description

58%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.

The description does a reasonable job listing specific Confluence operations and naming the integration mechanism (Rube MCP/Composio), giving it decent specificity and distinctiveness. However, it lacks an explicit 'Use when...' clause with natural trigger phrases, which weakens both completeness and trigger term quality. The instruction to 'always search tools first for current schemas' is an implementation detail that doesn't help with skill selection.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Confluence pages, wiki content, knowledge base articles, or Atlassian Confluence operations.'

Include natural synonyms and user-facing terms like 'wiki', 'knowledge base', 'Atlassian', 'create a page', 'find content' to improve trigger term coverage.

Move the implementation instruction ('Always search tools first for current schemas') out of the description and into the skill body, as it doesn't aid skill selection.

DimensionReasoningScore

Specificity

Lists several specific actions: page creation, content search, space management, labels, and hierarchy navigation. These are concrete Confluence operations, though some (like 'space management') are still somewhat broad.

4 / 5

Completeness

The 'what' is reasonably clear (automate Confluence operations via Rube MCP), but there is no explicit 'when' clause. The description lacks a 'Use when...' trigger guidance, which caps this at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes 'Confluence', 'page creation', 'content search', 'labels', and 'space management' as relevant keywords, but misses natural user phrases like 'wiki', 'knowledge base', 'create a page', or 'find a page'. The mention of 'Rube MCP (Composio)' is technical jargon unlikely to be used by end users.

3 / 5

Distinctiveness Conflict Risk

Confluence is a specific enough domain to distinguish this from most other skills. The mention of 'Rube MCP (Composio)' further narrows the scope. Minor overlap risk exists with generic document or wiki management skills.

4 / 5

Total

14

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.