Name: quipu
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

quipu

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/quipu/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 delivers concrete, executable Membrane CLI guidance with a well-structured auth/connection workflow, but it lacks validation checkpoints before destructive action/proxy runs and leaves a few command placeholders ambiguous.

Suggestions

Add an explicit validation/verification step before running destructive actions or proxy requests (e.g. 'For POST/PUT/DELETE, confirm the target record id and dry-run a GET first') to lift workflow_clarity above 3.

Clarify placeholders that read as literals, e.g. change --intent "QUERY" to --intent "<your intent>" and state explicitly that CONNECTION_ID comes from the connection ensure output.

Trim minor explanatory asides (e.g. 'so you can focus on the integration logic rather than auth plumbing') to tighten conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command-and-table oriented content that assumes competence, with only minor over-explanation (e.g. 'so you can focus on the integration logic rather than auth plumbing'); fits anchor 4 and is below 5 due to those small trimmable asides, above 3 because padding is limited.	4 / 5
Actionability	Provides concrete, copy-paste-ready membrane commands and a full flag table, but uses ambiguous placeholders like --intent "QUERY" (quoted as if literal) and CONNECTION_ID without always showing replacement; matches anchor 4 (mostly executable, minor gaps) rather than 5.	4 / 5
Workflow Clarity	The connection/auth flow is well sequenced with a polling feedback loop and CLIENT_ACTION_REQUIRED handling, but running actions and proxy requests on financial data are destructive-capable with no verification/validation step before execution; per the destructive-operations guideline this caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Content is well organized into clear sections (Install, Auth, Connecting, Searching, Running, Proxy, Best practices) with everything inline since no bundle files exist; the skill is over 50 lines so it does not qualify for the simple-skill 5, landing at anchor 4 with minor organization gaps.	4 / 5
	Total	15 / 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 names a distinct domain (Quipu) and provides an explicit 'Use when' clause covering both what and when, but the capability verbs are generic and the trigger phrases lack concrete synonyms or variations.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Quipu-specific actions such as 'create invoices, reconcile transactions, and pull accounting reports'.

Broaden the trigger clause with natural synonyms and file/entity terms users say, e.g. 'Use when the user wants to interact with Quipu invoices, expenses, contacts, or accounting data'.

Add 1-2 specific trigger phrases (e.g. mentions of Quipu invoices or cash-flow forecasting) to lift distinctiveness and completeness toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Quipu integration') and lists a few actions ('Manage data, records, and automate workflows'), but the verbs are generic rather than concrete; fits anchor 3 (names domain + 1-2 actions, not comprehensive) and not 2 because multiple actions are named, not 4 because they lack concrete specificity.	3 / 5
Completeness	Explicitly answers both 'what' (manage data/records/workflows) and 'when' ('Use when the user wants to interact with Quipu data'); the when clause is explicit but could be more specific with concrete trigger phrases, so anchor 4 rather than 5, and clearly above 3 since both halves are present.	4 / 5
Trigger Term Quality	Includes the brand keyword 'Quipu' and 'data' via 'Use when the user wants to interact with Quipu data', but misses common variations or synonyms; matches anchor 3 and is below 4 due to thin keyword coverage and above 2 because a relevant natural term is present.	3 / 5
Distinctiveness Conflict Risk	The named brand 'Quipu' gives it a clear niche with low overlap risk, but the action phrasing ('manage data, records') is generic, so it is mostly distinct (anchor 4) rather than fully distinct (anchor 5), and clearly above 3 due to the brand-specific trigger.	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/quipu/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.