Name: datadog
Rating: 61.6 (1 reviews)
Author: membranedev

datadog

Datadog integration. Manage Monitors, Dashboards, Incidents, Notebooks, Logs, Metrics and more. Use when the user wants to interact with Datadog 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/datadog/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.

Highly actionable content with concrete, executable Membrane CLI commands and a well-instrumented connection workflow including validation and feedback loops. The main weaknesses are mild verbosity from over-explaining Datadog basics and a lack of progressive disclosure, with reference-style content inlined rather than split into separate files.

Suggestions

Remove the opening paragraph defining what Datadog is and the redundant 'Datadog Overview' bullet list (which duplicates the Popular actions table) — Claude already knows what Datadog is.

Move the 20-row 'Popular actions' table into a separate reference file (e.g., references/actions.md) and link to it from the body to improve progressive disclosure and reduce the inline token load.

Anchor the dangling 'skip to Step 2' reference by labeling the 'Searching for actions' section as Step 2, and add a worked end-to-end example that runs a real action key (e.g., `membrane action run list-monitors --connectionId=... --json`).

Dimension	Reasoning	Score
Conciseness	Mostly efficient Membrane-specific guidance, but the opening paragraph defines what Datadog is (which Claude already knows) and the "Datadog Overview" bullet list duplicates the Popular actions table, adding unnecessary tokens.	3 / 5
Actionability	Fully executable, copy-paste ready commands cover the common cases (install, login, connection ensure, action list, action run with --input, proxy request) alongside a flags table and a 20-action catalog.	5 / 5
Workflow Clarity	The connection flow has explicit state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) with a poll-until-ready feedback loop, but the "skip to Step 2" reference points to an unlabeled step and the flow is section-based rather than a numbered checklist.	4 / 5
Progressive Disclosure	Good section headers provide structure, but everything is inlined in a single 165-line file with no one-level-deep references, including a 20-row actions table that functions as API reference and could live in a separate file.	3 / 5
	Total	15 / 20 Passed

Description

73%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.

A solid, distinctive description that clearly names the Datadog platform and includes an explicit "Use when" trigger clause. It is held back from the top tier by a single generic action verb ("Manage") and a generic "when" clause that does not enumerate concrete trigger phrases.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete Datadog objects (Monitors, Dashboards, Incidents, Notebooks, Logs, Metrics) but relies on a single generic action verb ("Manage") plus the vague "and more" rather than listing distinct concrete actions.	3 / 5
Completeness	Explicitly answers both what ("Manage Monitors, Dashboards...") and when ("Use when the user wants to interact with Datadog data"), but the "when" clause is generic rather than enumerating concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms users would say ("Datadog", "Monitors", "Dashboards", "Incidents", "Logs", "Metrics") with good coverage, though common variations like "alerts", "traces", "APM", and "SLOs" are missing.	4 / 5
Distinctiveness Conflict Risk	"Datadog" is a distinct named platform with a specific trigger ("interact with Datadog data"), giving it a clear niche and minimal conflict risk with other skills.	5 / 5
	Total	16 / 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/datadog/SKILL.md
Commit: f484c82

Reviewed: ~16 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.