Name: codescene
Rating: 63.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

codescene

CodeScene integration. Manage Projects. Use when the user wants to interact with CodeScene data.

Quality

75%

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/codescene/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 copy-paste-ready CLI commands and a thorough action table, and is well-structured into clear sections. Its main weakness is workflow clarity: destructive actions lack validation/verification steps, and an internal "skip to Step 2" reference points to no labeled section.

Suggestions

Add an explicit validation/confirmation step before destructive actions (e.g. "Before running delete-project or delete-team, confirm the target ID with the user and verify via get-project first") to satisfy the destructive-ops feedback-loop requirement.

Fix the broken cross-reference by labeling the next section "Step 2: Search for actions" (or change "skip to Step 2" to "skip to Searching for actions") so the navigation target is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable commands and reference tables with only minor padding such as "CodeScene is a SaaS platform... used by software architects, development managers, and CTOs" and the "auth plumbing" aside. It is not a 5 because those trimmable explanatory bits exist, and not a 3 because the bulk is real CLI commands rather than concept explanation.	4 / 5
Actionability	Quotes provide fully executable, copy-paste-ready commands ("npm install -g @membranehq/cli@latest", "membrane connection ensure 'https://codescene.com/' --json", "membrane action run <actionId> --connectionId=CONNECTION_ID --input '{\"key\": \"value\"}' --json") plus a 20-row action table covering common cases. It is not a 4 because guidance is fully executable and covers the common cases comprehensively.	5 / 5
Workflow Clarity	The connection flow is sequenced with state branches and a re-poll feedback loop ("After the user completes the action... poll again"), but destructive actions listed in the table (Delete Project, Delete Team) have no validation/verification step before execution, which caps the score at 3 per the destructive-operations guideline. It is not a 4 because of that missing validation and the unlabeled "skip to Step 2" reference, and not a 2 because a clear sequence with checkpoints exists for the connection step.	3 / 5
Progressive Disclosure	The body is organized into clear headed sections (Install, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices) with content appropriately placed and no nested references. It is not a 5 because it is a single monolithic file over 50 lines with no external reference split and a broken "skip to Step 2" cross-reference, and not a 3 because the structure is genuinely good rather than merely "some structure".	4 / 5
	Total	16 / 20 Passed

Description

73%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 concisely names the CodeScene product, includes an explicit third-person trigger clause, and is highly distinct. Its main weakness is specificity: only one action (Manage Projects) is named, under-representing the skill's actual breadth (analyses, hotspots, teams).

Suggestions

Expand the "what" with 1-2 more concrete actions, e.g. "Run analyses, inspect hotspots, and manage projects" to better reflect the skill's coverage and lift specificity.

Add a natural trigger synonym or file/context cue (e.g. "when the user mentions CodeScene, technical debt, or code hotspots") to broaden trigger-term coverage beyond the single product name.

Dimension	Reasoning	Score
Specificity	Quotes "CodeScene integration. Manage Projects." name the domain plus one concrete action (Manage Projects), matching the anchor for 1-2 concrete actions that are not comprehensive. It is not a 2 because a concrete action with a clear object is named beyond just the domain, and not a 4 because only one action is listed rather than several.	3 / 5
Completeness	It states both a "what" ("CodeScene integration. Manage Projects.") and a "when" ("Use when the user wants to interact with CodeScene data."), matching the anchor where both are present but the "what" could be more explicit. It is not a 5 because the "what" is thin (only Manage Projects, omitting analyses, hotspots, etc.) and not a 3 because both what and when are clearly present.	4 / 5
Trigger Term Quality	Quotes "Use when the user wants to interact with CodeScene data" provide a natural explicit trigger and the product name "CodeScene" is the keyword users would actually say, giving good coverage. It is not a 3 because the natural product term plus an explicit trigger phrase are present, and not a 5 because there are no synonyms or extensions beyond the single product name.	4 / 5
Distinctiveness Conflict Risk	Quotes "CodeScene integration" and "interact with CodeScene data" name a specific SaaS product, giving a clear niche with minimal conflict risk. It is not a 4 because naming a distinct product leaves essentially no overlap with other skills.	5 / 5
	Total	16 / 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/codescene/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.