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

Blog Docs Log in Get started

heap

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

Quality

62%

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/heap/SKILL.md

Quality

Content

67%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 a well-structured, actionable guide to driving Heap via the Membrane CLI, with executable commands and a connection workflow that includes real state checkpoints and a feedback loop. Its main weaknesses are an unnecessary introductory explanation of what Heap is, an unlabeled 'Step 2' reference, and reference-grade material (clientAction states, proxy flags) inlined rather than split into reference files.

Suggestions

Trim the opening paragraph that explains what Heap is and who uses it; Claude already knows Heap, so lead directly with the integration workflow.

Fix the broken step numbering: label the 'Step 2' target explicitly (or renumber '1b' into a coherent 1/2/3 sequence) so the connection flow is unambiguous.

Move the detailed clientAction state semantics and the proxy flag reference table into a reference file (e.g. references/proxy.md) and link to it from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly commands, tables, and sequenced steps, but it opens by explaining what Heap is and who uses it ('Heap is a product analytics tool... used by product managers, marketers, and analysts') and includes prose padding ('so you can focus on the integration logic rather than auth plumbing'), fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure, action list/run, and proxy requests with clearly marked placeholders and a flags table, but 'Popular actions' only redirects to discovery and never shows concrete Funnel/Segment/Event examples, leaving a minor coverage gap.	4 / 5
Workflow Clarity	The connection workflow is a clear sequence with explicit state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED) and a poll-again feedback loop after user action, but it references an unlabeled 'Step 2' and uses an inconsistent '1b' label, a minor sequencing gap.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with no nesting, but at ~143 lines with no bundle/reference files, detailed reference material (clientAction state semantics, the proxy flags table) is inlined rather than split into one-level-deep reference files, a minor organization gap.	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 correctly pairs a 'what' with an explicit 'Use when' trigger and names Heap distinctly, but its capability phrasing is generic fluff ('manage data, records, automate workflows') rather than concrete Heap actions. Tightening the action list to real Heap capabilities (funnels, segments, events, user properties) would lift specificity and trigger-term quality.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete Heap capabilities, e.g. 'Query funnels, segments, users, events, and properties in Heap and automate workflows over that data.'

Add natural trigger synonyms users actually say, such as 'product analytics', 'events', 'funnels', or 'segments', to improve trigger-term coverage.

Keep the explicit 'Use when...' clause but make the trigger more specific, e.g. 'Use when the user wants to query or report on Heap analytics data.'

Dimension	Reasoning	Score
Specificity	The description names the Heap domain but its actions ('Manage data, records, and automate workflows') are generic and not concrete Heap-specific capabilities, matching the 'names the domain but actions are minimal or generic' anchor rather than the 3-anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It supplies both a 'what' ('Manage data, records, and automate workflows') and an explicit 'Use when...' trigger clause, so it clears the completeness-3 cap, but the 'what' is generic rather than concrete, landing just below the 5-anchor.	4 / 5
Trigger Term Quality	It includes relevant natural terms ('Heap', 'Heap data', 'interact with Heap data') but misses common variations or synonyms a user might say (analytics, events, funnels, segments), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Heap is a distinct named product with a clear trigger ('interact with Heap data'), but the generic 'manage data, records, and automate workflows' phrasing creates minor overlap risk with other data/integration skills, matching 'mostly distinct; minor overlap risk'.	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/heap/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.