Name: sprinklr
Rating: 48 (1 reviews)
Author: membranedev

sprinklr

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

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

48%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 delivers strong executable CLI guidance and a well-sequenced connection workflow, but its value is undercut by a massive inlined entity list that is pure padding with no progressive-disclosure structure. Conciseness is the dominant weakness.

Suggestions

Remove or externalize the ~194-item entity bullet list; if entity discovery is needed, point to one reference file rather than inlining an enumeration.

Define 'Step 2' explicitly (it is referenced after READY but never labeled) so the connection -> action sequence is unambiguous.

Add a brief validation/feedback step after running actions (check the output field and error states) to complete the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	The body inlines a ~194-item bullet list of generic entity names (Asset, Campaign, ... Digital Twin, Bug, Vulnerability, Anomaly) that enumerates concepts Claude does not need and does not communicate actions, matching 'Severely verbose; extensively explains concepts Claude already knows; heavily padded'. It cannot be a 2 because the padding is far more than 'several unnecessary explanations'.	1 / 5
Actionability	It provides concrete copy-pasteable commands (npm install, membrane login, connection ensure, action list/run, request) with --json flags and explanations, matching 'Mostly executable guidance; concrete code or commands with minor gaps'. It is not a 5 because placeholders like CONNECTION_ID need substitution and there is no complete end-to-end worked example.	4 / 5
Workflow Clarity	The connection flow is clearly sequenced with a state machine and explicit polling (READY -> skip to Step 2; CLIENT_ACTION_REQUIRED with connect/provide-input; CONFIGURATION_ERROR), matching 'Clear sequence with most checkpoints present; minor validation gaps'. It is not a 5 because 'Step 2' is undefined, and action-running has no result-validation feedback loop.	4 / 5
Progressive Disclosure	There is section structure (Install, Authentication, Connecting, Searching, Best practices) but no bundle files exist and the giant entity list is inlined content that belongs in a separate reference or should be omitted, matching 'Some structure but could be better organized; content that should be separate is inline'. It is not a 4 because the inlined list is a significant organization gap.	3 / 5
	Total	12 / 20 Passed

Description

55%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 answers both what and when and is distinctive by virtue of naming Sprinklr, but its actions are generic and it lacks concrete natural-language trigger phrases. Trigger term quality is the weakest dimension.

Suggestions

Replace generic verbs with concrete capabilities, e.g. 'Pull Sprinklr cases, campaigns, and conversations; search and update records; trigger workflows' to raise specificity.

Add concrete trigger phrases users would say, e.g. 'Use when the user mentions Sprinklr cases, campaigns, care queues, or wants to query Sprinklr data'.

Keep the third-person voice but tighten 'Manage data, records, and automate workflows' into specific noun phrases rather than abstract verbs.

Dimension	Reasoning	Score
Specificity	It names the domain (Sprinklr) and two actions ('Manage data, records' and 'automate workflows') but the actions are generic and not comprehensive, matching 'Names domain and 1-2 concrete actions'. The phrase 'Manage data, records' is minimal rather than fully vague, so it sits above a 2.	3 / 5
Completeness	It answers both 'what' ('Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with Sprinklr data'), matching 'Has both what and when; when could be more explicit or specific'. It is not a 5 because the trigger phrases are not concrete ('when the user wants to interact with Sprinklr data' is broad, not a list of trigger phrases).	4 / 5
Trigger Term Quality	The only natural trigger term a user would say is 'Sprinklr'; 'Manage data, records' and 'automate workflows' are generic and lack common variations a user would actually phrase. This matches 'One or two generic keywords; missing the natural phrases users say' and is below a 3 because it lacks relevant keyword variations.	2 / 5
Distinctiveness Conflict Risk	Tying the skill to a named proprietary platform ('Sprinklr') gives it a clear niche with minimal conflict risk, matching 'Mostly distinct; minor overlap risk with closely related skills'. It is not a 5 because the generic verbs could overlap with other data-management integrations.	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/sprinklr/SKILL.md
Commit: f484c82

Reviewed: 4 days ago

Table of Contents

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.