Name: qwilr
Rating: 48.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

qwilr

Qwilr integration. Manage Accounts. Use when the user wants to interact with Qwilr data.

Quality

53%

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/qwilr/SKILL.md

Quality

Content

45%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 Membrane CLI workflow at the end is genuinely actionable and well-sequenced with state-handling feedback loops, but it is buried under ~1390 lines of duplicated, generic, Qwilr-irrelevant padding that destroys token efficiency and leaves the skill as a structureless monolith with no progressive disclosure. The actionable core is good; everything above it is the problem.

Suggestions

Delete the duplicated 'Qwilr Overview' bullet list (lines ~17-1409) entirely, or move a single deduplicated, Qwilr-specific glossary into a references/ file linked from the body.

Add an explicit numbered workflow (1. Install CLI -> 2. Authenticate -> 3. connection ensure -> 4. poll until READY -> 5. action list -> 6. action run) so the full sequence is a clear checklist rather than implied.

Provide at least one fully concrete end-to-end example with real values (e.g. a sample action list output and a run command with a resolved actionId) to lift actionability from mostly-executable to copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Roughly 1390 of 1535 lines are a massively duplicated bullet list of generic business-document terms (e.g. 'Privacy Policy', 'Invoice', 'Disaster Recovery Plan') repeated verbatim many times with no Qwilr-specific value — textbook heavily-padded, severely-verbose content matching anchor 1, not the merely-verbose anchor 2.	1 / 5
Actionability	The Membrane CLI section gives real, copy-paste-ready executable commands (e.g. 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://qwilr.com" --json') plus a proxy flags table, matching anchor 4's 'mostly executable guidance' rather than 5 because parameters use placeholders and there is no fully concrete end-to-end example.	4 / 5
Workflow Clarity	The connection flow has an explicit state-based feedback loop (poll with --wait until READY, handle CLIENT_ACTION_REQUIRED by re-polling, surface CONFIGURATION_ERROR), fitting anchor 4's clear sequence with most checkpoints present; it falls short of anchor 5 because the top-level install->auth->connect->search->run sequence is implied rather than a clean numbered checklist and 'Step 2' is referenced without a clear 'Step 1'.	4 / 5
Progressive Disclosure	It is a single monolithic file with no external references (references/, scripts/, assets/ are empty) and the giant duplicated Qwilr Overview list is inlined content that clearly belongs in a separate reference file or should be removed, matching anchor 2's 'content that clearly belongs in separate files is inlined' rather than anchor 3 which requires at least some clearly-signaled references.	2 / 5
	Total	11 / 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 is third-person, has an explicit 'Use when' trigger clause, and names a distinct service, but it is thin: one generic action ("Manage Accounts") and a vague trigger phrase. It clears the bar for completeness and distinctiveness but under-delivers on specificity and trigger term coverage.

Suggestions

Expand 'what' with 2-3 concrete Qwilr actions, e.g. 'Create and manage Qwilr projects, blocks, templates, and accounts.'

Broaden the trigger phrase to surface natural synonyms users say, e.g. 'Use when the user wants to manage Qwilr proposals, quotes, blocks, templates, or account data.'

Tighten the vague 'interact with Qwilr data' into a concrete trigger that reflects actual Qwilr output types.

Dimension	Reasoning	Score
Specificity	Names the domain ("Qwilr integration") and one concrete resource action ("Manage Accounts"), but offers only that single generic action and no broader coverage of Qwilr capabilities, fitting anchor 3 rather than 4 which requires several specific actions.	3 / 5
Completeness	Provides both a 'what' ("Qwilr integration. Manage Accounts.") and an explicit 'when' ("Use when the user wants to interact with Qwilr data."), so it is not capped at 3, but the 'when' is generic and the 'what' is thin, landing on anchor 4 rather than the concrete-trigger anchor 5.	4 / 5
Trigger Term Quality	Includes the natural keyword "Qwilr" and the phrase "interact with Qwilr data", but misses common variations or synonyms a user might say (proposals, quotes, blocks, templates), matching anchor 3 rather than the well-covered anchor 4.	3 / 5
Distinctiveness Conflict Risk	"Qwilr" is a distinct niche with a service-specific trigger, giving minimal conflict risk, but the generic "Manage Accounts" phrasing leaves minor overlap with other account-management skills, matching anchor 4 rather than the fully-distinct anchor 5.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1535 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: membranedev/application-skills
Path: skills/qwilr/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.