Name: kodagpt
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

kodagpt

KodaGPT integration. Manage Organizations. Use when the user wants to interact with KodaGPT data.

Quality

69%

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/kodagpt/SKILL.md

Quality

Content

76%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 content is highly actionable with concrete, executable CLI commands and a clear connection-state workflow. Its main gaps are missing validation/confirmation around destructive content operations and an undefined 'Step 2' reference.

Suggestions

Add a validation/confirmation checkpoint before destructive actions like delete-content and update-content (e.g., 'List contents first and confirm with the user before deleting'), which would lift workflow clarity above the 3 cap.

Define 'Step 2' (referenced by 'skip to Step 2') — add the corresponding section or reword to 'proceed to Searching for actions'.

Trim the introductory paragraph describing what KodaGPT is and who uses it, since it does not help Claude execute the integration.

Dimension	Reasoning	Score
Conciseness	The body is largely operational commands and tables with only minor over-explanation (the introductory paragraph on what KodaGPT is and who uses it could be trimmed), matching 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands with flags for login, connection ensure/wait, action list/run with JSON input, and proxy requests, plus a popular-actions table with concrete keys — covering the common cases.	5 / 5
Workflow Clarity	The connection flow is sequenced with state-based branching and polling, but destructive/batch actions (delete-content, update-content) run with no validation or confirmation checkpoint, which per the rubric caps workflow clarity at 3; 'Step 2' is also referenced but never defined.	3 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and tables and no nested references, but at ~150 lines with all content inlined it has minor organization gaps rather than the ideal split/signaling of a 5.	4 / 5
	Total	16 / 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 correctly answers both what and when with an explicit 'Use when...' clause, and benefits from naming a specific app. Its main weakness is generic action language and thin trigger-term coverage.

Suggestions

Replace the generic 'Manage Organizations' with the actual concrete capabilities shown in the body (e.g., 'Create, update, and delete knowledge-base content, run semantic search, and send messages to KodaGPT chatbots').

Expand the trigger phrase to include natural variations users would say, e.g., 'Use when the user wants to search or manage KodaGPT knowledge-base content or chat with a KodaGPT chatbot.'

Align the description with the body — the body covers content/chatbot actions, not 'Organizations', which is misleading.

Dimension	Reasoning	Score
Specificity	Names the domain ('KodaGPT integration') and one concrete action ('Manage Organizations'), but the action is fairly generic and coverage is not comprehensive, fitting the '1-2 concrete actions' anchor.	3 / 5
Completeness	Provides both a 'what' ('KodaGPT integration. Manage Organizations.') and an explicit 'when' ('Use when the user wants to interact with KodaGPT data.'), but the trigger phrase is generic rather than concrete, so it sits below the 5 anchor.	4 / 5
Trigger Term Quality	Includes relevant terms ('KodaGPT', 'interact with KodaGPT data', 'Organizations') but lacks common variations or synonyms, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Tied to a named app (KodaGPT) giving it a clear niche with minimal conflict risk, though 'Manage Organizations' is generic enough to allow minor overlap, keeping it just below 5.	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/kodagpt/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.