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

stackstate

StackState integration. Manage data, records, and automate workflows. Use when the user wants to interact with StackState 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/stackstate/SKILL.md

Quality

Content

63%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 genuinely actionable with executable Membrane CLI commands and a clear connection-state workflow, but it opens with padded overview content and inlines material (the feature bullet list) that would be better split into a reference file; a broken "Step 2" cross-reference is a minor workflow gap.

Suggestions

Cut or shrink the "StackState Overview" nested bullet list and the intro paragraph; Claude does not need a taxonomy of StackState feature names to run CLI actions.

Move the StackState feature taxonomy and the proxy flag table into a references/ file (e.g. reference.md) and link to it, reducing the inlined bulk.

Fix the step numbering: either label the "Searching for actions" section as Step 2 (referenced by the READY skip) or reword the cross-reference, and add a 1a heading to pair with 1b.

Dimension	Reasoning	Score
Conciseness	The core CLI guidance (install, auth, connection, actions, proxy) is efficient and executable, but ~45 lines of opening material — the StackState intro paragraph and the long nested "StackState Overview" feature bullet list — are padding that does not earn its tokens; this fits the mostly-efficient-with-some-unnecessary-explanation anchor rather than the noticeably-verbose one below.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands (npm install, membrane login, connection ensure, connection get --wait, action list/run, request) plus a flag table, covering the common cases; it falls just short of a 5 because action examples use unsubstituted placeholders (CONNECTION_ID, QUERY, <actionId>) and the Popular actions section is thin/redundant with Searching for actions.	4 / 5
Workflow Clarity	The install → authenticate → connect → wait-for-ready → search → run sequence is clear and includes genuine state-check checkpoints (READY / BUILDING / CLIENT_ACTION_REQUIRED / error) with a polling feedback loop; it stops at 4 because "skip to Step 2" references a Step 2 that is never labeled (and "1b" appears with no "1a"), a minor sequencing gap.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single ~170-line file with reasonable section headers, but content that would fit a separate reference — the 35-line StackState feature bullet list and the proxy flag table — is inlined, and there are no one-level-deep reference links, matching the some-structure-but-could-be-better-organized anchor.	3 / 5
	Total	14 / 20 Passed

Description

61%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 names the specific product and includes an explicit Use-when trigger, but its capability verbs are generic ("manage data, records, automate workflows") rather than concrete StackState actions, and the trigger keyword set is thin.

Suggestions

Replace the generic verbs with concrete StackState capabilities, e.g. "Query topology and telemetry, manage StackPacks, and run StackState API actions."

Broaden the trigger clause with natural synonyms users say, e.g. "Use when the user wants to query StackState topology, telemetry, StackPacks, or run StackState API calls."

Tie the Use-when clause to concrete trigger phrases (topology, health, alerts, StackGraph) rather than the abstract "interact with StackState data."

Dimension	Reasoning	Score
Specificity	The actions named — "Manage data, records, and automate workflows" — are generic abstractions rather than concrete capabilities; it names the StackState domain but the verbs are minimal and non-specific, matching the anchor for naming a domain with only generic actions rather than the 1-2 concrete-actions anchor above.	2 / 5
Completeness	Both halves are present: a what ("StackState integration. Manage data, records, and automate workflows.") and an explicit when ("Use when the user wants to interact with StackState data."), but the when clause is somewhat generic rather than listing concrete trigger phrases, matching the anchor where both exist yet the when could be more specific.	4 / 5
Trigger Term Quality	The trigger relies on the single natural keyword "StackState" (the product name users would say) in "Use when the user wants to interact with StackState data," but it lacks common variations or synonyms such as topology, telemetry, StackPacks, or StackGraph, so it lands at the middle anchor rather than good coverage.	3 / 5
Distinctiveness Conflict Risk	"StackState" is a specific named product, giving the skill a clear niche with distinct triggers and minimal risk of firing for an unrelated skill, matching the clear-niche anchor.	5 / 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/stackstate/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.