Name: graceblocks
Rating: 52 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

graceblocks

Graceblocks integration. Manage Organizations, Users. Use when the user wants to interact with Graceblocks data.

Quality

58%

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/graceblocks/SKILL.md

Quality

Content

50%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 is action-dense and gives a clear connection workflow with polling checkpoints, but it is dragged down by a large inlined concept list and a lack of verification steps around destructive record operations. Splitting the entity catalog out and adding pre/post validation for mutations would raise both conciseness and workflow clarity.

Suggestions

Move the long entity catalog into a separate reference file (e.g. entities.md) and keep only the action-bearing summary inline to cut padding.

Add a verification step to the record-action workflow — e.g., re-fetch the record after create/update or confirm the row count after delete — since delete/update are destructive operations.

Replace the vague 'Use action names and parameters as needed' with a concrete example showing how to discover an action id and pass its input schema, closing the actionability gap.

Dimension	Reasoning	Score
Conciseness	The ~90-term entity list (Dataset, Column, Model ... Self-Supervised Learning) is a large padded section of generic concept-naming Claude already knows and does not act on, which is noticeably verbose; the surrounding CLI guidance is efficient but does not offset the bulk.	2 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, login, connection, action search/run, and proxying with flag tables, but relies on placeholders (<actionId>, CONNECTION_ID) and a vague 'Use action names and parameters as needed', leaving minor gaps short of fully executable 5.	4 / 5
Workflow Clarity	The connection flow has a clear sequence with explicit state-checkpoint polling and a feedback loop, but destructive/batch operations (delete-record, update-record) run with no verification step, so the missing-validation cap holds workflow clarity at 3.	3 / 5
Progressive Disclosure	Section headers are reasonable but the large inlined entity catalog is content that should live in a separate reference file, and no external references are signaled; this matches the 'some structure, content that should be separate is inline' anchor.	3 / 5
	Total	12 / 20 Passed

Description

66%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 answers both what the skill does and when to use it, and its product-specific naming keeps conflict risk low. Its main weakness is thin action coverage and trigger-term variety, which leave specificity and trigger quality at the mid-level anchors.

Suggestions

Expand the action list beyond 'Manage Organizations, Users' to the concrete CRUD and workflow actions the skill supports (e.g., create/update/delete records, run pipelines) to lift specificity.

Broaden trigger phrases with natural synonyms users would say (e.g., 'Graceblocks records', 'Graceblocks tables', 'query Graceblocks data') rather than the single generic 'interact with Graceblocks data'.

Dimension	Reasoning	Score
Specificity	"Graceblocks integration. Manage Organizations, Users." names the domain and exactly two concrete actions, matching the anchor for 1-2 concrete actions but not the broader coverage required for a 4.	3 / 5
Completeness	Both a clear 'what' ("Graceblocks integration. Manage Organizations, Users.") and an explicit 'when' ("Use when the user wants to interact with Graceblocks data.") are present, but the trigger phrase is fairly generic, fitting the 4 anchor where 'when' could be more specific rather than the concrete-varied triggers of a 5.	4 / 5
Trigger Term Quality	It includes relevant keywords ("Graceblocks", "Organizations", "Users", "interact with Graceblocks data") but lacks the synonyms and natural variations users would commonly say, so it sits at the 'some relevant keywords' anchor rather than the comprehensive 4.	3 / 5
Distinctiveness Conflict Risk	"Graceblocks" names a specific product niche with distinct triggers and minimal overlap with other skills, matching the clear-niche anchor.	5 / 5
	Total	15 / 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/graceblocks/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.