Name: madkudu
Rating: 56.8 (1 reviews)
Author: membranedev

madkudu

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

Quality

65%

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/madkudu/SKILL.md

Quality

Content

67%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 solid, command-rich integration guide with a clear connection workflow and explicit polling/error feedback loops. Its main weaknesses are some marketing filler, placeholder-only examples without a worked end-to-end call, and minor numbering inconsistencies in the workflow steps.

Suggestions

Trim the opening paragraph and the line "Use action names and parameters as needed." to assume Claude's competence and save tokens.

Add one fully worked end-to-end example (e.g. connection ensure -> action list with a real intent -> action run fetching a lead score) instead of only placeholder commands.

Fix the step numbering (add a 1a, or relabel the unlabeled 'Step 2' reference) so the workflow sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-dense and efficient, but the opening marketing paragraph ("MadKudu helps B2B SaaS companies identify their best leads...") and filler like "Use action names and parameters as needed." add explanation that could be trimmed, matching 'mostly efficient but includes some unnecessary explanation'; not a 4 because the padding is more than minor.	3 / 5
Actionability	It provides copy-paste-ready commands ("npm install -g @membranehq/cli@latest", "membrane connection ensure ... --json", "membrane action run <actionId> --connectionId=CONNECTION_ID --json") plus a proxy flag table, fitting 'mostly executable guidance with minor gaps'; not a 5 because examples rely on placeholders and lack a fully worked end-to-end call (e.g. an actual lead-score retrieval).	4 / 5
Workflow Clarity	The sequence install -> authenticate -> connection ensure -> poll until READY -> handle client actions -> search -> run is clear, with explicit feedback loops ("poll again", "Keep polling until state is no longer BUILDING") and error-state handling, matching 'clear sequence with most checkpoints present'; not a 5 because of numbering inconsistencies ("1b" with no 1a, references to an unlabeled 'Step 2').	4 / 5
Progressive Disclosure	The skill is a single well-sectioned file (Overview, Working with MadKudu, Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices) with no nested references and clear navigation, matching 'good structure; most content appropriately placed; minor organization gaps'; not a 5 because denser inline content (the clientAction state table and proxy flag table) could live in separate reference files.	4 / 5
	Total	15 / 20 Passed

Description

62%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 with an explicit 'Use when' clause and a clear product niche, but the capability verbs are generic and trigger-term coverage is limited to the product name. Tightening the actions and adding synonyms would raise it.

Suggestions

Replace generic verbs ('manage data, records') with concrete MadKudu-specific actions like 'score leads and accounts, enrich customer data, fetch predictive scores'.

Expand trigger terms with natural phrasings users would say, e.g. 'lead scoring', 'account scoring', 'predictive scoring', or 'enrich MadKudu data'.

Make the 'when' clause more concrete, e.g. 'Use when the user wants to score leads/accounts or pull MadKudu customer predictions.'

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the MadKudu domain plus a few actions, but those actions are generic rather than concrete, matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor; not a 4 because the actions lack specific, granular coverage.	3 / 5
Completeness	It has a clear "what" ("MadKudu integration. Manage data, records, and automate workflows.") and an explicit "when" ("Use when the user wants to interact with MadKudu data."), satisfying both, but the trigger phrasing is generic rather than concrete, landing at 'both what and when; when could be more explicit'; not a 5 because the trigger is not concrete enough.	4 / 5
Trigger Term Quality	The phrase "interact with MadKudu data" plus "MadKudu" provide relevant keywords, but coverage stops there with no synonyms or variations, fitting 'some relevant keywords but missing common variations'; not a 4 because natural term coverage is thin beyond the product name.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to the named product MadKudu gives it a clear niche with low conflict risk, but the generic action verbs (manage data, records) leave minor overlap risk, matching 'mostly distinct; minor overlap risk'; not a 5 because the action language is not as distinctive as the product name.	4 / 5
	Total	14 / 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/madkudu/SKILL.md
Commit: f484c82

Reviewed: 6 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.