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

Blog Docs Log in Get started

fibery

Fibery integration. Manage Workspaces. Use when the user wants to interact with Fibery 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/fibery/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's CLI workflow and command examples are genuinely actionable and the connection sequence is well-instrumented, but the skill is dominated by a massive, largely fabricated entity list that wastes the context window, and its destructive/batch operations lack any validation steps.

Suggestions

Delete the fabricated 'Chat *' entity list (and the bulk entity enumeration overall); if entity vocabulary is needed, move it to a references/ file and link to it from SKILL.md.

Add explicit validation/verification steps for destructive and batch operations — e.g., read an entity back after update, confirm before delete-entity, and check batch-commands results before proceeding.

Move the popular-actions table and proxy-flag reference into a separate reference file, keeping SKILL.md a concise overview that points one level deep to details.

Dimension	Reasoning	Score
Conciseness	Roughly 290 of 449 lines are a flat list of 'entity' names, the large majority fabricated 'Chat *' entries (e.g., 'Chat Metaverse', 'Chat Cryptocurrency', 'Chat Smart Contract') that are not real Fibery concepts — severely verbose and heavily padded with content that earns no place, matching 'Severely verbose; heavily padded'.	1 / 5
Actionability	It provides concrete, executable CLI commands for install, auth, connection, action search/run, and proxying, plus a popular-actions table and a proxy-flag table — mostly copy-paste ready, but placeholders like CONNECTION_ID and the literal 'QUERY' keep it from being fully executable, fitting 'Mostly executable guidance; concrete code or commands with minor gaps'.	4 / 5
Workflow Clarity	The connection flow is well sequenced with state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll loop, but the skill covers destructive and batch operations (delete-entity, update-entity, batch-commands) with no validation or verification steps, invoking the cap that limits workflow_clarity to 3 for destructive/batch skills lacking validation.	3 / 5
Progressive Disclosure	No bundle files exist and everything is inlined into one SKILL.md, including a ~290-line entity/reference list that clearly belongs in a separate file; section headers provide some structure so it is above a monolithic 1, but the scale of inlined bulk content fits 'Minimal structure; content that clearly belongs in separate files is inlined' (noticeably below midpoint).	2 / 5
	Total	10 / 20 Passed

Description

61%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 a distinct product (Fibery) with an explicit trigger clause, giving it good distinctiveness and adequate completeness. Its weaknesses are shallow specificity ('Manage Workspaces' understates a full integration) and limited trigger-term coverage beyond the product name.

Suggestions

Replace the generic 'Manage Workspaces' with 2-3 concrete actions the skill performs (e.g., 'create, query, and update entities; manage spaces and users').

Broaden the trigger clause with natural variations users would say, e.g., 'Use when the user wants to interact with Fibery data, workspaces, entities, or records.'

Dimension	Reasoning	Score
Specificity	The description names the Fibery domain but the only action stated is the generic 'Manage Workspaces' — minimal and not comprehensive, matching the anchor 'Names the domain but actions are minimal or generic'; it is above a 1 because a concrete-ish action is named, but below a 3 since there are not 1-2 specific concrete actions.	2 / 5
Completeness	It states both a 'what' ('Manage Workspaces') and an explicit 'when' ('Use when the user wants to interact with Fibery data'); the 'when' is explicit but generic and the 'what' is shallow, fitting 'Has both what and when; when could be more explicit or specific' rather than the richly concrete level 5.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Fibery data' includes the natural keyword 'Fibery' and a reasonable trigger phrase, but coverage is thin with no synonyms or common variations (e.g., 'Fibery workspace', 'entities', 'records'), matching 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'Fibery' gives a clear niche with distinct triggers and minimal conflict risk with other skills, matching 'Clear niche with distinct triggers; minimal conflict risk'.	5 / 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/fibery/SKILL.md
Commit: f484c82

Reviewed: ~19 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.