Name: librato
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

librato

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

Quality

66%

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/librato/SKILL.md

Quality

Content

71%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 executable commands and a connection-readiness workflow that includes validation and error-recovery branches. The main weaknesses are mild redundancy/padding and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Remove the redundant "Popular actions" section (it restates the discovery command) and trim the opening "what Librato is" paragraph to a one-line context note.

Fix the step navigation: either label "Step 1 / Step 2" explicitly or drop the bare "skip to Step 2" references so the sequence is self-contained.

Move the detailed connection state machine (CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR handling) and the proxy flags table into a reference file (e.g. references/connections.md) and link to it from the body to add one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes mild padding ("Librato is a monitoring platform for metrics-driven teams... Developers and operations teams use it to monitor application and infrastructure performance") and a near-empty "Popular actions" section that repeats the discovery command already shown under "Searching for actions". It is not a 4 because those redundancies could be trimmed, and not a 2 because the bulk is executable and not heavily padded.	3 / 5
Actionability	Copy-paste-ready commands cover the common cases end to end: install (`npm install -g @membranehq/cli@latest`), auth (`membrane login ...`), connect (`membrane connection ensure "https://metrics.librato.com" --json`), poll (`... connection get <id> --wait --json`), search, run (with `--input '{...}'`), and proxy with a full flags table. It is not a 4 because the guidance is fully executable rather than having minor gaps.	5 / 5
Workflow Clarity	The connection flow is a clear sequence with an explicit validation/feedback loop (poll until `READY`, branch on `CLIENT_ACTION_REQUIRED` and re-poll after the user acts, handle `CONFIGURATION_ERROR`/`SETUP_FAILED`). It is not a 5 because the prose refers to "Step 2" without a labeled Step 1/Step 2 structure, leaving navigation slightly implicit, and not a 3 because real checkpoints and error-recovery branches are present.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the ~154-line body is a single monolithic file with the detailed connection state machine and proxy flag table all inline. Sections are well-headed, but content that could live one level deep in reference files is inlined and no references are signaled. It is not a 4 because there is no appropriate split or navigation into separate files, and not a 2 because the in-file section structure is reasonable rather than a wall of text.	3 / 5
	Total	15 / 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 identifies a distinct niche (Librato) and includes an explicit "Use when" trigger, but the capability language is generic and omits Librato's defining concept (metrics). Tightening the action list and adding metric-specific trigger terms would lift the weaker dimensions.

Suggestions

Replace generic verbs with concrete Librato actions, e.g. "Query metrics, manage instruments and spaces, and configure alerts."

Add the natural trigger term "metrics" (and "alerts") so users searching by what Librato actually does will match, e.g. "Use when the user wants to query or visualize Librato metrics, instruments, spaces, or alerts."

Keep the explicit "Use when..." clause but pair it with the specific entities above to move completeness from a generic "what" to a concrete one.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Librato domain but the actions are generic ("manage", "automate") rather than concrete operations, matching the anchor that names the domain with minimal/specific actions. It is not a 3 because no genuinely concrete, specific actions (e.g. "query metrics", "create alerts") are listed.	2 / 5
Completeness	Both a "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Librato data") are present, satisfying the anchor for both being present with room for greater specificity. It is not a 5 because the "what" is generic rather than concrete, and not a 3 because the "when" is explicitly stated rather than weakly implied.	4 / 5
Trigger Term Quality	It surfaces relevant keywords ("Librato", "data", "records", "interact with Librato data") but misses the most natural term users would say for this platform — "metrics" — and offers no synonyms or variations. It is not a 4 because keyword coverage is thin rather than merely missing a few terms.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product "Librato" with a trigger ("interact with Librato data") carves out a clear niche with minimal overlap risk against other skills. It is not a 4 because the product name alone makes conflict with unrelated skills very unlikely.	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/librato/SKILL.md
Commit: f484c82

Reviewed: 6 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.