Name: quality-gate-size-analysis
Rating: 62.4 (1 reviews)
Author: DataDog

quality-gate-size-analysis

Analyze static quality gate on-disk size changes, correlate with Confluence exception records and GitHub PRs by milestone

Quality

73%

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 ./.claude/skills/quality-gate-size-analysis/SKILL.md

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and concise, giving executable commands and high-value domain pitfalls, but its multi-step batch workflow lacks explicit validation checkpoints and it keeps all detail inline with no progressive disclosure to reference files. Adding verify/retry checkpoints and splitting reference material into bundled files would improve the lower-scoring dimensions.

Suggestions

Add explicit validation checkpoints in the batch steps (e.g. confirm the Datadog query returned raw_data, verify each Confluence page has a non-empty "Bounds Granted", and handle PRs with no milestone before attributing a release).

Introduce a feedback loop for Step 4: when a metric spike has no matching PR or exception, re-search by feature keyword and re-correlate rather than only flagging once.

Move the static reference material (dashboard link, CQL/folder details, gate_name variants) into a bundled reference file under references/ and link to it from the body to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful — executable Datadog queries, gh CLI commands, and a "Key Details and Pitfalls" section of non-obvious domain gotchas — without padding concepts Claude already knows, matching the lean/efficient anchor.	3 / 3
Actionability	Provides copy-paste-ready executable commands and queries (Datadog metric strings, `gh pr view --json ...`, CQL search, `getConfluencePage` with contentFormat=markdown) plus explicit JSON field lists, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Five clearly sequenced steps with sub-steps are present, but this batch fetch/correlation workflow lacks explicit validation checkpoints or feedback loops (e.g. confirming a metric query returned data, handling missing milestones), matching the anchor for steps listed with validation gaps.	2 / 3
Progressive Disclosure	No bundle files exist and all detail lives inline in a ~150-line monolithic SKILL.md with no external references; while well-sectioned, content that could be split (e.g. the exception/dashboard reference details) is inline, matching the anchor for some structure with content that should be separate inline.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is specific and distinct, naming concrete actions and a clear niche, but it lacks an explicit "Use when..." trigger clause and relies on technical jargon rather than natural user phrasing. Adding when-to-use guidance and more natural trigger terms would raise the completeness and trigger-term scores.

Suggestions

Add an explicit trigger clause such as "Use when investigating agent package size growth, attributing size increases to releases, or reviewing quality-gate exception coverage."

Include more natural phrasings a user might say (e.g. "package size", "size budget", "release size attribution") alongside the technical terms.

Keep the concrete actions but lead with the user-facing scenario to strengthen the when-to-use signal.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions across distinct data sources — "Analyze static quality gate on-disk size changes", "correlate with Confluence exception records", "GitHub PRs by milestone" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance; the when is only implied, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant domain keywords ("static quality gate", "on-disk size", "Confluence exception records", "GitHub PRs", "milestone") but they are technical jargon with no common natural variations, matching the anchor for some relevant keywords missing variations.	2 / 3
Distinctiveness Conflict Risk	Targets a very narrow niche (static quality gate on-disk size correlated with Confluence exceptions and GitHub milestone attribution) with distinct triggers unlikely to overlap with other skills.	3 / 3
	Total	10 / 12 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: DataDog/datadog-agent
Path: .claude/skills/quality-gate-size-analysis/SKILL.md
Commit: 5723c24

Reviewed: 8 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.