CtrlK
BlogDocsLog inGet started
Tessl Logo

rudderstack-http

RudderStack HTTP integration. Manage data, records, and automate workflows. Use when the user wants to interact with RudderStack HTTP data.

49

Quality

53%

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/rudderstack-http/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 actionable Membrane CLI guidance is solid and executable, but it is buried under a massive unrelated keyword list that wastes context and signals over-claiming. Removing the keyword dump and adding verification checkpoints would markedly improve the skill.

Suggestions

Delete the ~200-line bullet keyword list; it is unrelated padding that does not guide any concrete action.

Add a validation/verification step after running actions or proxy requests (check the `output`/error field, confirm state before proceeding) so destructive or batch operations get a feedback loop.

Move any genuine API reference or per-action detail into a bundled reference file (e.g. references/ACTIONS.md) and link to it one level deep from the overview.

DimensionReasoningScore

Conciseness

The body inlines a ~200-line bullet dump of largely unrelated terms (GDPR, AWS, Slack, 'Like', 'Share', 'Bookmark') that is pure padding unrelated to the workflow; the CLI section itself is lean, so this sits at 'noticeably verbose; several padded sections' rather than the severely-padded level 1.

2 / 5

Actionability

It provides concrete, copy-paste-ready membrane commands (login, connection ensure, action list/run, request) with a flag table, matching 'mostly executable guidance with minor gaps'; it is not level 5 because common-case worked examples of action output handling are not shown.

4 / 5

Workflow Clarity

There is a clear connection sequence with state handling (READY/BUILDING/CLIENT_ACTION_REQUIRED) and polling, but running actions (which can be batch/destructive data operations) has no validate-then-verify checkpoint before acting, so the workflow-clarity cap of 3 applies.

3 / 5

Progressive Disclosure

It is a monolithic single file with no bundle files; the keyword wall is content that clearly should not be inlined at all, matching 'minimal structure; content that clearly belongs in separate files is inlined.'

2 / 5

Total

11

/

20

Passed

Description

61%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 clearly targets a distinct niche and includes an explicit use-when trigger, but its capability description is generic. Replacing 'Manage data, records, and automate workflows' with concrete RudderStack operations would lift specificity and completeness.

Suggestions

Replace generic verbs with concrete RudderStack actions, e.g. 'Send track/identify/group events, route data to destinations, and query event streams.'

Add natural trigger synonyms users actually say, such as 'events', 'track calls', 'destinations', or 'data pipeline'.

Keep the explicit 'Use when...' clause but tie it to those concrete triggers (e.g. 'Use when the user wants to send or inspect RudderStack events or manage destinations').

DimensionReasoningScore

Specificity

It names the RudderStack domain but the actions ('Manage data, records, and automate workflows') are generic rather than concrete, matching the 'names the domain but actions are minimal or generic' anchor; it does not list concrete operations like track/identify/transform/route, so it stays below 3.

2 / 5

Completeness

Both a 'what' ('RudderStack HTTP integration. Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with RudderStack HTTP data') are present; the 'what' is somewhat generic so it does not reach the fully-concrete level 5.

4 / 5

Trigger Term Quality

'Use when the user wants to interact with RudderStack HTTP data' includes the product name and a natural phrase, but misses common synonyms users would say (events, track, destinations, pipelines), landing on 'some relevant keywords but missing common variations.'

3 / 5

Distinctiveness Conflict Risk

Scoped specifically to 'RudderStack HTTP', it carves a clear niche with distinct triggers and minimal overlap risk with unrelated skills.

5 / 5

Total

14

/

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.