Name: pylon
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

pylon

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

Quality

63%

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/pylon/SKILL.md

Quality

Content

63%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 actionable and the connection lifecycle workflow is well sequenced, but it is held back by duplicated discovery guidance and a monolithic structure with no external references for its distinct topic areas. It scores slightly above the midpoint overall.

Suggestions

De-duplicate the action-discovery instructions in "Searching for actions" and "Popular actions" into a single section.

Add a validation/retry feedback loop for action runs and proxy writes (e.g. check the response `output`/error, retry on `CLIENT_ACTION_REQUIRED`).

Move the large connection-state reference (CLIENT_ACTION_REQUIRED fields, proxy flag table) into a referenced file and keep SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but repeats action-discovery guidance across "Searching for actions" and "Popular actions" and includes light padding ("This is the fastest way to get a connection"), matching anchor 3 rather than 4.	3 / 5
Actionability	It provides concrete, executable commands with real flags and JSON examples for install, auth, connection, action, and proxy flows, with only minor gaps (CONNECTION_ID placeholders, no sample run output), fitting anchor 4.	4 / 5
Workflow Clarity	The connection lifecycle is a clear state-machine sequence (ensure → poll → READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) with a poll-until-ready checkpoint, though it lacks a validate/retry feedback loop around action runs and destructive proxy calls, keeping it at anchor 4.	4 / 5
Progressive Disclosure	No bundle files exist and all content lives in a single ~140-line SKILL.md; it is well-sectioned by headers but distinct topics (auth, connection lifecycle, actions, proxy, best practices) are inlined rather than split into one-level-deep references, matching anchor 3.	3 / 5
	Total	14 / 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 with a clear brand-specific trigger, but leans on generic verbs ("manage") and offers limited keyword variety. It is solidly above average but not exemplary.

Suggestions

Replace generic "manage" with concrete verbs, e.g. "Create, query, and update Pylon records and datasets, and automate workflows."

Add natural synonyms and file/term variations users might say (e.g. "Pylon datasets, records, projects, or automations").

Sharpen the trigger clause beyond "interact with Pylon data" to specific intents like "when the user wants to query, create, or update Pylon records."

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Pylon domain plus a couple of actions, but "manage" is generic and the coverage is not comprehensive, matching anchor 3 rather than 4.	3 / 5
Completeness	It states a clear "what" (manage data, records, automate workflows) and an explicit "when" ("Use when the user wants to interact with Pylon data"), so both are present with the "when" only mildly generic — anchor 4, not 5 because the trigger is not specific.	4 / 5
Trigger Term Quality	The distinct brand term "Pylon" plus "data," "records," and "workflows" give some natural keywords, but common synonyms and the trigger phrasing "interact with Pylon data" is narrow, leaving relevant variations missing (anchor 3).	3 / 5
Distinctiveness Conflict Risk	The "Pylon" niche brand trigger makes it mostly distinct with minimal conflict risk, though the surrounding "manage data/records/workflows" verbs are generic, keeping it just below anchor 5.	4 / 5
	Total	14 / 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/pylon/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.