Name: stack-ai
Rating: 61.6 (1 reviews)
Author: membranedev

stack-ai

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

Quality

72%

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/stack-ai/SKILL.md

Quality

Content

82%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 tight, command-driven integration guide with strong actionability and a sensible workflow including connection-state validation. The main gaps are minor labeling inconsistencies in the workflow steps and a small amount of introductory padding.

Suggestions

Trim the opening paragraph about who uses Stack AI; Claude does not need the audience description to run the integration commands.

Fix the step labeling so "skip to Step 2" and "1b" map to explicitly numbered steps (e.g. label Step 2: Search and run actions) for a cleaner sequence.

Consider moving the proxy request flag table and the full clientAction field reference into a separate REFERENCE.md so the main flow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-focused, but the opening paragraph ("used by business professionals, researchers, and citizen data scientists...") and the auth-plumbing aside are trimmable over-explanation. It is not a 5 because a few sentences do not earn their tokens, and not a 3 because the bulk is efficient.	4 / 5
Actionability	Commands are copy-paste ready and cover the common cases: install, login, connection ensure, action list/run, and a proxy flag table. It is not a 4 because the guidance is fully executable with specific examples rather than having meaningful gaps.	5 / 5
Workflow Clarity	There is a clear install→authenticate→connect→search→run sequence with a connection-state feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED). It is not a 5 because step references ("skip to Step 2", "1b") are not cleanly labeled, and not a 3 because validation checkpoints are largely present.	4 / 5
Progressive Disclosure	Content is organized into clear sections (Overview, Working with Stack AI, Best practices) with no bundle files to reference. It is not a 5 because some inlinable detail (the proxy flag table, the full clientAction schema) could live in separate reference files, and not a 3 because structure is genuinely good.	4 / 5
	Total	17 / 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 successfully covers both what the skill does and when to use it, anchored to a distinct product niche. Its main weakness is generic verb and object choices (manage data, records, automate workflows) that limit specificity and trigger-term richness.

Suggestions

Replace generic verbs with concrete actions, e.g. "Query Stack AI records, run workflow executions, and fetch app data" so capabilities are specific.

Expand the trigger clause with natural phrases users say, e.g. "Use when the user wants to query Stack AI, run a Stack AI workflow, or pull data from a Stack AI deployment."

Add domain-specific nouns (stacks, deployments, API keys) that appear in the body to strengthen trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Stack AI domain and 2-3 listed actions, but the verbs (manage, automate) are generic rather than concrete. It is not a 2 because it lists multiple actions, and not a 4 because the actions lack specificity and comprehensive coverage.	3 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Stack AI data"), but the when clause is generic rather than concrete trigger phrases. It is not a 5 because the trigger guidance is not explicit and specific.	4 / 5
Trigger Term Quality	The primary natural keyword is the product name "Stack AI", with generic supporting terms (data, records, workflows); common variations or synonyms a user might say are missing. It is not a 4 because keyword coverage is thin beyond the product name.	3 / 5
Distinctiveness Conflict Risk	The specific product name "Stack AI" gives it a clear niche with low conflict risk, though the generic "data" and "records" objects leave minor overlap with other data skills. It is not a 5 because the action phrasing is not distinctive enough to eliminate overlap risk.	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/stack-ai/SKILL.md
Commit: f484c82

Reviewed: 4 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.