Name: codereadr
Rating: 47.2 (1 reviews)
Author: membranedev

codereadr

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

Quality

50%

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/codereadr/SKILL.md

Quality

Content

42%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 clear connection-state workflow, but it is undermined by a massive inlined list of irrelevant, duplicated entity names and by the absence of any validation step for destructive operations. Token efficiency is the most serious weakness.

Suggestions

Delete the ~150-item "CodeREADr Overview" entity bullet list (lines 23–174): most entries are irrelevant to CodeREADr, duplicated, and waste context tokens.

Add a validation/confirmation checkpoint before destructive actions (Delete Scans, Delete Database, Delete User, Delete Service) — e.g. list-then-confirm or a dry-run — to satisfy the workflow_clarity cap.

Remove the introductory paragraph explaining what CodeREADr/SDKs are, or trim it to one line, since it explains concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	Lines 23–174 are a ~150-item bullet list of "entities" (Opportunity, Lead, Campaign, Chatter Post, Video, Sensor, etc.), many duplicated (Trend, Anomaly, Outlier appear twice), almost all irrelevant to CodeREADr — heavily padded content Claude does not need, matching the score-1 "heavily padded" anchor; it cannot be a 2 because the padding is severe, not merely noticeable.	1 / 5
Actionability	It provides concrete, executable commands throughout (e.g. `membrane connection ensure "https://www.codereadr.com/" --json`, `membrane action run <actionId> --connectionId=CONNECTION_ID --input '{...}' --json`) plus a popular-actions table with real keys, matching the score-4 anchor; it is not a 5 because no complete end-to-end example with real parameter values is shown.	4 / 5
Workflow Clarity	The connection flow is well-sequenced with state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll-after-action feedback loop, but the skill exposes destructive batch operations (Delete Scans, Delete Database, Delete User, Delete Service) with no validation or verification step, so workflow clarity is capped at 3 per the destructive-operations rule.	3 / 5
Progressive Disclosure	Section headers organize the workflow content reasonably (Install, Authentication, Connecting, Searching, Running actions, Proxy, Best practices) with no nested references, but the inlined ~150-item entity list is content that should be removed or split out, matching the score-3 anchor of "content that should be separate is inline"; not a 2 because real section structure does exist.	3 / 5
	Total	11 / 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 correctly uses third person and includes an explicit "Use when..." clause, covering both what and when. Its main weaknesses are generic action verbs and the absence of the natural trigger terms (barcode, QR, scan) a user would actually say.

Suggestions

Replace generic actions with concrete CodeREADr capabilities, e.g. "Manage barcode databases, scan sessions, devices, and users; automate scanning workflows."

Add natural trigger terms users say, such as "barcode", "QR code", "scan", and "inventory", to the description.

Sharpen the "when" clause to reference concrete triggers, e.g. "Use when the user wants to scan barcodes or manage CodeREADr databases, devices, or users."

Dimension	Reasoning	Score
Specificity	It names the domain ("CodeREADr integration") but the actions — "Manage data, records, and automate workflows" — are minimal and generic rather than concrete operations, matching the score-2 anchor; it is not a 3 because no specific concrete action (e.g. "scan barcodes", "manage databases") is given.	2 / 5
Completeness	Both halves are present: the "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with CodeREADr data"), so the missing-trigger cap does not apply; it is a 4 rather than 5 because the "when" trigger is generic and could be more specific.	4 / 5
Trigger Term Quality	"CodeREADr" and "data" are relevant keywords but common natural terms users would actually say — barcode, QR code, scan, scanning, inventory — are entirely absent, so coverage misses common variations as in the score-3 anchor; not a 2 because "CodeREADr" is a genuine (non-generic) keyword rather than only generic language.	3 / 5
Distinctiveness Conflict Risk	The explicit product name "CodeREADr" gives it a clear, mostly-distinct niche with minimal conflict risk; it is not a 5 because the generic "manage data, records, automate workflows" framing could overlap with CRM/data-management skills absent the product name.	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/codereadr/SKILL.md
Commit: f484c82

Reviewed: ~14 hours 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.