Name: summit
Rating: 64 (1 reviews)
Author: membranedev

summit

Summit integration. Manage Organizations, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Summit data.

Quality

75%

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/summit/SKILL.md

Quality

Content

76%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 highly actionable with copy-paste-ready CLI commands and a sensible setup-to-run sequence, and is reasonably concise and well-structured for a self-contained skill. Its main weakness is the absence of any validation or verification feedback loops for the destructive/batch operations the proxy and action-run commands enable.

Suggestions

Add validation/verification checkpoints for destructive operations, e.g. after `connect` confirm the connection exists with `connection list`, and after a proxy POST/PUT/PATCH/DELETE check the response status before proceeding.

Consolidate the overlapping 'Searching for actions' and 'Popular actions' sections to reduce redundancy and tighten navigation.

Trim the one-line generic context ('Summit is a project management and team collaboration platform... Think of it as a central hub') since it does not add executable guidance.

Dimension	Reasoning	Score
Conciseness	Largely efficient with executable commands, a lean flags table, and JSON examples; only minor over-explanation remains (the one-line 'Think of it as a central hub' context and the slightly redundant 'Popular actions' section restating the action-list command), fitting the 'efficient, minor trimmable instances' anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready CLI commands throughout with real flags, JSON input examples, a complete proxy-flags table, and concrete output-parsing guidance ('Take the connector ID from output.items[0].element?.id'), matching the 'fully executable, covers common cases' anchor.	5 / 5
Workflow Clarity	Setup-to-run steps are clearly numbered and sequenced, but the skill enables destructive operations (proxy POST/PUT/PATCH/DELETE with bodies and `action run` mutations) with no validation or verification checkpoints anywhere, which caps workflow clarity at 3 per the destructive-operations rule.	3 / 5
Progressive Disclosure	Self-contained single file (no bundle directories exist) with well-organized, clearly headed sections (Overview, Working with Summit, Popular actions, Best practices) and no nested references, matching the 'good structure, appropriately placed, minor organization gaps' anchor; slightly below 5 due to overlap between the 'Searching for actions' and 'Popular actions' sections.	4 / 5
	Total	16 / 20 Passed

Description

75%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 clearly names the domain and concrete capabilities and includes an explicit 'Use when' trigger, giving it solid completeness and specificity. It falls short of top marks only because the trigger clause is generic rather than enumerating concrete user phrasings.

Suggestions

Make the 'Use when' clause concrete by enumerating user phrasings, e.g. 'Use when the user wants to manage Summit organizations, pipelines, users, goals, or filters'.

Vary the verbs beyond the single 'Manage' to surface distinct concrete actions (e.g. 'create, update, and list Organizations; manage Pipelines; invite Users').

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities ('Manage Organizations, Pipelines, Users, Goals, Filters') matching the 'several specific actions, minor gaps' anchor, though it relies on one generic verb applied to five nouns rather than distinct concrete verbs.	4 / 5
Completeness	Provides both a clear 'what' ('Manage Organizations, Pipelines, Users, Goals, Filters') and an explicit 'when' ('Use when the user wants to interact with Summit data'), with the 'when' being present but somewhat generic rather than concrete trigger phrases — matching the 'has both, when could be more explicit' anchor.	4 / 5
Trigger Term Quality	Good keyword coverage with concrete domain entities (Organizations, Pipelines, Users, Goals, Filters) a user would name, but the 'Use when' clause is generic ('interact with Summit data') and omits common phrasings/synonyms, fitting the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	Names a specific product (Summit) and distinct entities giving it a clear niche with minimal conflict risk, but the generic 'interact with Summit data' trigger keeps it just below the 'distinct triggers, minimal conflict risk' of a 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: membranedev/application-skills
Path: skills/summit/SKILL.md
Commit: f484c82

Reviewed: ~23 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.