CtrlK
BlogDocsLog inGet started
Tessl Logo

confluence

Search and manage Confluence pages and spaces using CQL, read/create/update pages with Markdown support. Use when working with Confluence documentation.

66

Quality

80%

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 ./skills/confluence/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 highly actionable command reference with excellent progressive disclosure and executable examples throughout. It loses points on conciseness due to duplicated sections (check, config, examples) and on workflow clarity because destructive operations (delete, move, permission removal) lack validation or confirmation guidance.

Suggestions

Remove the duplicated 'check' documentation — keep the validation checklist in one place (either Setup Verification or the Commands section) and cross-reference it from the other.

Drop the terminal Examples section that re-demonstrates search/get/space commands verbatim, and consolidate the two 'config show' explanations into one.

Add validation guidance around destructive operations: e.g., verify a page ID with 'page get --no-body' before 'page delete', and note that Cloud deletion moves pages to trash and how to recover them.

DimensionReasoningScore

Conciseness

The body is mostly lean command listings, but it could be tightened: the 'check' command's validation list is documented twice (Setup Verification and Commands > check), 'config show' appears in both Configuration Defaults and the config section, and the Examples section re-demonstrates commands already shown verbatim. Not 4-5 because there are several redundant sections; not 2 because there is no padding explaining concepts Claude already knows.

3 / 5

Actionability

Every command is fully executable ('$SKILL_DIR/scripts/confluence.py search "type=page AND space = DEMO"'), with argument tables, flag documentation, and copy-paste-ready examples covering search, page get/create/update, spaces, and permissions. The 'check' command even provides a self-verifying setup step.

5 / 5

Workflow Clarity

Setup has a genuine validation checkpoint with an error-recovery loop ('If anything is missing, the check command will provide setup instructions'), but the destructive and batch operations — 'page delete', 'page move', 'space permissions remove' — carry no validation or verification guidance (e.g., confirming the page or noting trash recovery), which caps this dimension at 3 per the rubric. The command-per-section structure otherwise reads clearly.

3 / 5

Progressive Disclosure

SKILL.md acts as a clear overview with well-signaled, one-level-deep references: 'See [references/creating-content.md](references/creating-content.md) for page creation and updates' and 'See [permissions.md](references/permissions.md) for read/write classification'; both files exist and the bulk of create/update detail is appropriately split out. Navigation is easy and nothing is deeply nested.

5 / 5

Total

16

/

20

Passed

Description

87%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: concrete, third-person, with an explicit 'Use when...' trigger and product-specific terms that make it highly distinct. Minor improvements possible by naming the remaining space-management actions and adding synonyms like 'wiki' or 'Atlassian'.

Suggestions

Replace the generic 'manage Confluence pages and spaces' with the concrete operations offered (e.g., 'move and delete pages, manage spaces and permissions').

Add natural synonyms users might say, such as 'Atlassian', 'wiki', or 'Confluence Cloud', to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Search and manage Confluence pages and spaces using CQL, read/create/update pages with Markdown support' — but 'manage' is generic and space-level operations are only implied, leaving minor gaps in coverage. Not 5 because coverage of the full capability set (delete, move, permissions, history) is absent; not 3 because it lists multiple specific actions rather than just 1-2.

4 / 5

Completeness

Clearly answers both: the 'what' is concrete ('Search and manage Confluence pages and spaces using CQL, read/create/update pages with Markdown support') and the 'when' is an explicit trigger phrase ('Use when working with Confluence documentation'). Third-person voice is used correctly, matching the top anchor exactly.

5 / 5

Trigger Term Quality

'Confluence', 'CQL', 'pages', 'spaces', 'documentation' are natural terms users would say, giving good keyword coverage. Not 5 because common synonyms and variations like 'wiki', 'Atlassian', or 'Confluence Cloud' are missing; not 3 because the term set goes well beyond a single generic keyword.

4 / 5

Distinctiveness Conflict Risk

'Confluence' names a specific product with its query language (CQL) and artifact types (pages, spaces), giving a clear niche with minimal conflict risk against other documentation or wiki skills. No generic language that would trigger for the wrong skill.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
odyssey4me/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.