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

Blog Docs Log in Get started

gorillastack

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/gorillastack/SKILL.md

Quality

Content

38%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 genuinely executable Membrane CLI guidance, but it is dominated by a massive, duplicated, largely-irrelevant entity list that destroys token efficiency, lacks validation steps for destructive operations, and inlines content that should live in a separate reference file.

Suggestions

Remove the ~400-line entity bullet list (and its duplicates); if a catalog of available entity types is needed, move it to a references/ file and link to it from the overview.

Add a validation/verification checkpoint before destructive actions like delete-rule and delete-tag-group (e.g. confirm the target ID with the user or run a get-* action first).

Show at least one fully-resolved example of `membrane action run` with real-looking parameter JSON so the command is copy-paste runnable end-to-end.

Dimension	Reasoning	Score
Conciseness	The ~400-line "GorillaStack Overview" entity list (e.g. "Asset", "Liability", "Equity", "Revenue", "Profit", "Loss") is heavily padded with generic nouns unrelated to the product and riddled with duplicates (Report, Alert, Notification, Task, Comment each appear multiple times); this is severely verbose padding, matching the 1 anchor and not a 2 because the bulk is pure filler rather than minor over-explanation.	1 / 5
Actionability	Concrete executable commands are provided throughout ("membrane search gorillastack --elementType=connector --json", "membrane action run --connectionId=CONNECTION_ID ACTION_ID --json", "membrane request CONNECTION_ID /path/to/endpoint") with flag tables; not a 5 because placeholders like CONNECTION_ID/ACTION_ID are never shown filled in a working example and not a 3 because the guidance is genuinely executable.	4 / 5
Workflow Clarity	A rough sequence exists (install → login → connect → action list → action run → request), but destructive actions ("Delete Rule", "Delete Tag Group") and batch operations have no validation or verification checkpoints, capping this at 3 per the destructive-operation rule; not a 4 because checkpoints are absent and not a 2 because the order is coherent.	3 / 5
Progressive Disclosure	No references/scripts/assets bundle exists and the entire content is inlined into SKILL.md, with the giant entity catalog clearly belonging in a separate file but presented as a monolithic block; not a 3 because there is no signaled reference structure to navigate and not a 1 because section headers do exist.	2 / 5
	Total	10 / 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 in concise third-person voice with a distinct branded trigger, but it names only one concrete capability and offers few natural keyword variations. It is competent but not comprehensive.

Dimension	Reasoning	Score
Specificity	"GorillaStack integration. Manage Organizations." names the domain and one concrete action (Manage Organizations), matching the anchor for 1-2 concrete actions but not comprehensive; it is not a 4 because only a single action is named and not a 2 because the domain and an action are explicit.	3 / 5
Completeness	It states both a clear "what" ("GorillaStack integration. Manage Organizations.") and an explicit "when" ("Use when the user wants to interact with GorillaStack data"); not a 5 because the trigger phrasing is generic and not a 3 because both halves are present.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with GorillaStack data" provides a relevant natural trigger and the proper noun "GorillaStack", but lacks common variations or synonyms; not a 4 because coverage is thin and not a 2 because a genuine user-phrase is present.	3 / 5
Distinctiveness Conflict Risk	The proper noun "GorillaStack" gives a clear niche with minimal conflict risk, though the generic "Manage Organizations" leaves minor overlap risk; not a 5 because the action half is broad and not a 3 because the branded trigger is distinctly scoped.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (540 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: membranedev/application-skills
Path: skills/gorillastack/SKILL.md
Commit: f484c82

Reviewed: 5 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.