Tessl • The management layer for AI agent skills

SkillPublic

confluence

Confluence integration. Manage document management data, records, and workflows. Use when the user wants to interact with Confluence data.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/confluence/SKILL.md

Quality

Content

65%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 a strong operational quick-start: every command is concrete and executable, the connection lifecycle is documented with state-by-state handling, and the action catalog makes capabilities discoverable. Its weaknesses are padded intro/explanatory text, a broken "Step 2" reference combined with no validation guidance for the destructive delete actions it lists, and a monolithic single-file layout that inlines catalog and reference material.

Suggestions

Fix the broken step numbering: the text says "skip to **Step 2**" twice, but no Step 2 exists — either label the "Searching for actions" section as Step 2 and "1b" as part of Step 1, or renumber the flow.

Add a validation checkpoint before destructive operations (Delete Page, Delete Blog Post) — e.g. "Before delete-page, run get-page to confirm the ID, and confirm with the user when the page has no recent versions or children" — to lift the workflow-clarity cap.

Move the popular-actions catalog and the proxy flag options table into a references/ file (e.g. references/actions.md and references/proxy.md), keeping SKILL.md as a lean overview with clearly signaled links, and delete the intro paragraph explaining what Confluence is.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — the body is dominated by executable commands and tables — but it pads concepts Claude already knows ("Confluence is a team collaboration and document management tool... a central hub for project documentation") and includes filler like "When to use which actions: Use action names and parameters as needed." This matches anchor 3 (mostly efficient with some unnecessary explanation), not 4, since the over-explanation is more than minor.	3 / 5
Actionability	Fully executable, copy-paste-ready commands cover every common case: install (`npm install -g @membranehq/cli@latest`), headless login completion (`membrane login complete <code>`), connection setup (`membrane connection ensure "https://..." --json`), action search and execution with JSON input, the proxy request syntax, and a flag-by-flag proxy options table. This matches anchor 5.	5 / 5
Workflow Clarity	The sequence (install → login → connection ensure → poll state → search actions → run) exists and includes a solid connection-state feedback loop (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR → act → re-poll). However, "skip to Step 2" references a step that is never defined, and the skill exposes destructive and batch operations (Delete Page, Delete Blog Post, list-everything actions) with no validation or verification guidance — the rubric caps workflow clarity at 3 in that case.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so everything — the 20-row action catalog, the proxy flags reference, and the detailed clientAction semantics — is inlined in a single ~160-line file. Sections are clearly headed, but content that should live in one-level-deep reference files is inline, matching anchor 3.	3 / 5
	Total	14 / 20 Passed

Description

57%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.

The description has the right structure — a third-person statement of what the skill does plus an explicit "Use when" trigger — and "Confluence" gives it a clear niche. Its weakness is generic language: the capability list ("manage document management data, records, and workflows") names no concrete actions and offers no natural synonyms (pages, spaces, wiki, Atlassian) that users would actually say.

Suggestions

Replace the abstract capability list with concrete actions, e.g. "Create, update, and delete Confluence pages, blog posts, spaces, comments, and attachments; list and query spaces, tasks, and page content."

Add natural trigger variations and synonyms to the "Use when" clause, e.g. "Use when the user mentions Confluence, Atlassian, wiki pages, spaces, blog posts, or page comments."

Tighten the redundant phrase "Manage document management data" — "manage Confluence content" or naming the object types directly reads more precisely and less like generic records-management tooling.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Confluence integration") but the actions are generic abstractions — "Manage document management data, records, and workflows" — with no concrete operations like creating pages, listing spaces, or updating blog posts. It matches anchor 2 (domain named, actions minimal/generic), not anchor 3, which requires 1-2 concrete actions.	2 / 5
Completeness	It explicitly answers both parts: the "what" ("Manage document management data, records, and workflows") and the "when" ("Use when the user wants to interact with Confluence data"), but both are generic and could be more explicit — matching anchor 4, not anchor 5, which requires concrete trigger phrases.	4 / 5
Trigger Term Quality	"Confluence" and "interact with Confluence data" are natural terms users would say, but the description includes no common variations or synonyms such as pages, spaces, blog posts, wiki, or Atlassian. This matches anchor 3 (some relevant keywords, missing variations).	3 / 5
Distinctiveness Conflict Risk	"Confluence" is a clearly named niche with a Confluence-specific trigger clause, making it mostly distinct. Minor overlap risk remains because the generic "document management data, records, and workflows" phrasing could pull in broader document- or records-management skills — anchor 4, not 5, which demands distinct triggers throughout.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/confluence/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

Discovery Implementation Validation

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.

confluence

Table of Contents

Is this your skill?