CtrlK
BlogDocsLog inGet started
Tessl Logo

discourse

Discourse integration. Manage Forums. Use when the user wants to interact with Discourse data.

52

Quality

59%

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/discourse/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 highly actionable with a clean, well-sequenced connection workflow, but it opens with unnecessary background on Discourse and provides no validation guidance for its destructive create actions. Splitting the actions table into a reference file would further improve disclosure.

Suggestions

Remove or shrink the opening paragraph explaining what Discourse is — Claude already knows this.

Add a verification checkpoint for write operations, e.g. after create-topic run get-topic to confirm the result before reporting success.

Move the Popular actions table to a references/actions.md file and link to it from the body to reduce inline bulk.

DimensionReasoningScore

Conciseness

The bulk is lean commands and tables, but the opening paragraph ("Discourse is an open-source internet forum... Think of it as a modern forum platform...") explains a concept Claude already knows and includes light marketing phrasing, matching the mostly-efficient-but-could-be-tightened anchor.

3 / 5

Actionability

Concrete executable commands appear throughout (npm install, membrane login, connection ensure, action list/run, request) with a flag table and actions table, but action-run examples use generic placeholders and lack a concrete worked example, fitting the mostly-executable-with-minor-gaps anchor.

4 / 5

Workflow Clarity

The connection flow is well sequenced with polling and state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the skill exposes destructive write operations (create-topic, create-post, create-user) with no verification step, triggering the destructive-operation cap that limits this to 3.

3 / 5

Progressive Disclosure

The file is well-organized with clear section headers and a single one-level external link (official docs), with no nested references; the only gap is the 20-row Popular actions table inlined rather than split to a reference file, fitting the good-structure-minor-gaps anchor.

4 / 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 is well-targeted to a distinct platform and includes an explicit trigger clause, but its capability statement is generic ("Manage Forums") and it omits natural synonyms users would say. Tightening the action list and broadening trigger terms would lift it from mid-range to strong.

Suggestions

Replace the generic "Manage Forums" with concrete actions, e.g. "List and create topics, posts, users, and categories in Discourse."

Expand the trigger clause with natural synonyms: "Use when the user mentions Discourse, forums, topics, posts, or categories."

Keep the description in third person (it currently is) while making the "what" as specific as the "when".

DimensionReasoningScore

Specificity

"Discourse integration. Manage Forums." names the domain but the only action ("Manage Forums") is generic and minimal, matching the anchor for naming the domain with minimal/generic actions rather than the 3-anchor's 1-2 concrete actions.

2 / 5

Completeness

Both a "what" ("Discourse integration. Manage Forums.") and an explicit "when" ("Use when the user wants to interact with Discourse data") are present, but the "what" is generic so it does not reach the 5-anchor's concrete comprehensive phrasing.

4 / 5

Trigger Term Quality

It surfaces "Discourse", "Forums", and "interact with Discourse data", but misses common natural variations a user might say (topics, posts, categories, discussions), fitting the anchor for some relevant keywords missing common synonyms.

3 / 5

Distinctiveness Conflict Risk

Discourse is a specific named platform with a distinct trigger ("interact with Discourse data"), giving minimal conflict risk, though "Manage Forums" leaves minor overlap with generic community/forum skills rather than a fully clear niche.

4 / 5

Total

13

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
membranedev/application-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.