Name: scoredetect
Rating: 50.4 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

scoredetect

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

Quality

55%

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/scoredetect/SKILL.md

Quality

Content

53%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 with a well-validated connection workflow, but is undermined by a leaked AI apology, padding, an incoherent overview, and a dangling cross-reference that breaks the sequence. Tightening the prose and fixing the structural references would meaningfully raise the score.

Suggestions

Delete the leaked apology line ("I am sorry, I cannot provide an API documentation URL...") and the generic "Use action names and parameters as needed" filler to remove padding.

Fix the dangling "skip to Step 2" reference by labeling the next section as Step 2 (Searching for actions), and remove or substantiate the incoherent Job/Media/Result/Project/Workspace overview.

Add a verification step after running actions (e.g. inspect the `output` field and confirm success before proceeding) so destructive action runs include a checkpoint.

Dimension	Reasoning	Score
Conciseness	The leaked AI apology ("I am sorry, I cannot provide an API documentation URL for 'ScoreDetect'...") plus the introductory "what is ScoreDetect" explainer and "Use action names and parameters as needed" filler are several unnecessary padded sections, matching anchor 2 even though the CLI command blocks themselves are efficient.	2 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, login, connection, action list/run, and proxy with a full flags table, but uses placeholders (CONNECTION_ID, QUERY, actionId) and lacks an end-to-end worked example with real output, fitting anchor 4.	4 / 5
Workflow Clarity	Connection setup has a real feedback loop (poll --wait, branch on READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the "skip to Step 2" reference points to no labeled step, the Overview section is incoherent, and running actions lacks a verification step for potentially destructive operations — validation gaps that cap this at anchor 3.	3 / 5
Progressive Disclosure	It is a self-contained single file with no bundle files and well-organized section headers, but the incoherent Overview section and the dangling Step 2 reference are minor organization gaps, fitting anchor 4.	4 / 5
	Total	13 / 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 answers both what and when with an explicit Use-when clause and a distinct app name, but its trigger phrasing is generic and only one concrete action is named. It is adequate but could be sharper with more specific actions and natural trigger terms.

Suggestions

Replace the generic "interact with ScoreDetect data" with concrete natural triggers users would actually say, e.g. "Use when the user wants to manage ScoreDetect organizations, jobs, media, or detection results."

Add one or two more concrete actions beyond "Manage Organizations" (e.g. create jobs, fetch media results) to lift specificity above anchor 2.

Dimension	Reasoning	Score
Specificity	"Manage Organizations" is the only concrete action; "ScoreDetect integration" and "interact with ScoreDetect data" are generic. It names the domain but the actions are minimal, matching anchor 2 rather than the two-concrete-action anchor 3.	2 / 5
Completeness	Both a "what" (ScoreDetect integration, Manage Organizations) and an explicit "when" clause ("Use when the user wants to interact with ScoreDetect data") are present, but the trigger is generic rather than concrete, fitting anchor 4.	4 / 5
Trigger Term Quality	It includes the natural keyword "ScoreDetect" and the phrase "interact with ScoreDetect data", but offers no synonyms or variations a user might say, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	The unique "ScoreDetect" name gives a clear niche with minimal conflict risk, but the generic concepts "Organizations" and "data" create minor overlap with other org/data-management skills, fitting anchor 4.	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/scoredetect/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.