Name: retently
Rating: 61.6 (1 reviews)
Author: membranedev

retently

Retently integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more. Use when the user wants to interact with Retently data.

Quality

73%

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/retently/SKILL.md

Quality

Content

67%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 action-rich with concrete Membrane CLI commands and a solid connection-state workflow, but it is held back by padding (an overview section, a Retently intro, and a redundant Popular actions section) and small sequencing inconsistencies. Tightening the prose and fixing the Step 2 / 1b references would raise it notably.

Suggestions

Remove the filler "## Retently Overview" bullet list and the "Use action names and parameters as needed" line, and trim the Retently intro paragraph.

Fix the step numbering: either label a "Step 1a" / "Step 2" or rewrite the "Skip to Step 2" and "1b" references to point to concrete section anchors.

Make "## Popular actions" deliver either a short list of common actions or remove the heading and fold its discovery command into the existing "Searching for actions" section.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean CLI commands but carries noticeable padding: an intro paragraph explaining what Retently is, a filler "## Retently Overview" bullet list with "Use action names and parameters as needed", and a "## Popular actions" section that duplicates the earlier search command.	3 / 5
Actionability	It provides many copy-paste-ready executable commands (install, login, connection ensure/get --wait, action list/run, request) plus a full proxy flag table, but placeholders like CONNECTION_ID need substitution and "Popular actions" promises actions while delivering only a discovery command.	4 / 5
Workflow Clarity	The connect-to-run sequence is clear with a genuine state-machine feedback loop (READY / CLIENT_ACTION_REQUIRED -> re-poll / CONFIGURATION_ERROR), but "Skip to Step 2" references an unlabeled Step 2 and "1b" appears without a 1a, leaving minor sequencing gaps.	4 / 5
Progressive Disclosure	It is a single self-contained file with well-organized section headers and no nested references, though the clientAction state machine and proxy flag table could plausibly live in separate reference files; no bundle files are present to verify.	4 / 5
	Total	15 / 20 Passed

Description

78%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 cleanly names the product and its primary entities and includes an explicit "Use when" trigger, making it distinct and reasonably complete. It could improve by adding concrete action verbs beyond "Manage" and natural trigger synonyms like surveys, NPS, or customer feedback.

Suggestions

Replace the generic verb "Manage" with concrete actions (e.g., create, list, update, delete) for the named entities.

Expand the trigger clause with natural user phrases such as "surveys", "NPS", "customer feedback", or "Retently contacts".

Drop "and more" in favor of a tighter, exhaustive enumeration or a clear category label.

Dimension	Reasoning	Score
Specificity	"Manage Persons, Organizations, Deals, Leads, Projects, Activities and more" lists six concrete entity types, giving comprehensive object coverage, though "Manage" is a single generic action verb rather than several distinct actions.	4 / 5
Completeness	It states both what ("Manage Persons, Organizations, Deals, Leads, Projects, Activities") and when ("Use when the user wants to interact with Retently data"), but the when-clause is generic rather than a set of concrete trigger phrases, so it falls short of a 5.	4 / 5
Trigger Term Quality	It covers the core named-product trigger ("Retently", "Retently data") but misses natural synonyms users would say such as surveys, NPS, customer feedback, or contacts.	4 / 5
Distinctiveness Conflict Risk	Everything is anchored to the specific named product "Retently", giving it a clear niche with minimal risk of triggering for the wrong skill.	5 / 5
	Total	17 / 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/retently/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.