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

Blog Docs Log in Get started

clip

Clip integration. Manage Recordses. Use when the user wants to interact with Clip 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/clip/SKILL.md

Quality

Content

68%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 an efficient, actionable guide built around concrete Membrane CLI commands and a clear connection state-machine. Its main weaknesses are a broken "Step 2" cross-reference and missing verification steps for destructive Record operations.

Suggestions

Label the "Searching for actions" section as "Step 2" (or fix the "skip to Step 2" reference) and reconcile the stray "1b" numbering so the workflow sequence is unambiguous.

Add a verification step after running create/update/delete actions, e.g. re-query or inspect the `output` field to confirm the Record changed as expected.

Provide one complete end-to-end example with a concrete actionId and input to make the action-running guidance copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body leads with executable commands and mostly avoids explaining concepts Claude already knows, with only minor filler ("so you can focus on the integration logic rather than auth plumbing") and a duplicated action-list command, fitting the efficient-with-minor-trimmings anchor.	4 / 5
Actionability	Concrete, executable commands are given throughout (install, login, connection ensure, action run, proxy flags) with real placeholders and --json guidance, but no fully worked end-to-end example with a concrete actionId is provided, matching mostly-executable guidance with minor gaps.	4 / 5
Workflow Clarity	The connection flow has a real state-machine sequence with a poll/check/re-poll feedback loop, but "skip to Step 2" references an unlabeled step, numbering is inconsistent ("1b" with no 1a), and destructive Record create/update/delete actions lack result verification, capping this at 3 per the destructive-operations guideline.	3 / 5
Progressive Disclosure	Content is well-organized under clear section headers with no nested or buried references, but at ~135 lines (over the 50-line simple-skill threshold) all content is inlined with no separate reference file for the proxy-flags table or action-discovery detail, fitting good structure with minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

57%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 provides an explicit trigger clause and ties the skill to a specific named app, but its capability statement is thin ("Manage Recordses") and uses an unnatural trigger term. Strengthening the action list and using more natural phrasing would raise specificity and trigger quality.

Suggestions

Replace the generic "Manage Recordses" with concrete actions, e.g. "Create, read, update, delete, and list Records in Clip."

Use natural user-facing trigger phrasing such as "Use when the user wants to manage Clip records or Clip data" instead of the awkward "Recordses".

Add the most common trigger synonyms (e.g. "Clip records", "Clip data", "list records") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Manage Recordses" names the domain (Records) but gives only one minimal, generic verb ("Manage") rather than listing concrete actions like create/read/update/delete, matching the anchor that names the domain with minimal actions.	2 / 5
Completeness	Both a "what" ("Clip integration. Manage Recordses.") and an explicit "when" ("Use when the user wants to interact with Clip data") are present, though each could be more specific, matching the anchor where both exist but "when" could be more explicit.	4 / 5
Trigger Term Quality	Domain terms "Clip", "Recordses", and "Clip data" are present, but "Recordses" is not a phrase users naturally say and common variations/synonyms are missing, fitting the anchor for some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	Tying triggers to the named app "Clip" gives a mostly distinct niche with only minor overlap risk, though the generic "interact with Clip data" keeps it from being fully distinctive.	4 / 5
	Total	13 / 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/clip/SKILL.md
Commit: f484c82

Reviewed: ~11 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.