yaml-master

Execute proactive YAML intelligence: automatically activates when working with YAML files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/productivity/002-jeremy-yaml-master-agent/skills/yaml-master/SKILL.md

Quality

Content

50%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 body is well-organized with prerequisites, sequenced instructions, output spec, error handling, and examples, and it correctly offloads detail to a real bundled reference file. Its weakness is actionability and validation rigor: the core steps are abstract directives rather than executable commands, and the config-edit workflow lacks an explicit validate-fix-retry feedback loop, which the rubric flags for batch/structural operations.

Suggestions

Add at least one executable validation command per common target next to each step (e.g. `yq eval '.' file.yaml`, `python -c 'import yaml; yaml.safe_load(open("f"))'`, `kubectl apply --dry-run=client -f file.yaml`, `docker compose config`) so the Instructions are copy-paste-ready rather than descriptive.

Insert an explicit validate -> fix -> re-validate feedback loop (a numbered checkpoint plus 'do not proceed until validation passes') for the formatting/schema steps, since YAML edits are batch/structural operations the rubric treats as requiring feedback loops to reach level 3.

Tighten the Examples section to show a concrete before/after YAML diff instead of prose 'Input/Output' descriptions, and link the per-topic detail (formatting rules, schema checks) to specific sections of SKILL.full.md rather than a single Resources line.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining what YAML or Kubernetes is, but it leans on prose-style instructions ('Parse and validate YAML syntax (identify the first breaking error and its location)') and repeated headings rather than tight executable guidance, so it could be tightened to fully earn level 3.	2 / 3
Actionability	It gives some concrete pointers (validation commands like `kubectl apply --dry-run=client`, risk patterns to look for), but the core Instructions are abstract directives ('Normalize formatting', 'Identify risky patterns') with no executable commands or code, matching the 'some concrete guidance but incomplete' anchor rather than copy-paste-ready level 3.	2 / 3
Workflow Clarity	Steps are numbered and sequenced, and there is a follow-up validation checklist, but for config edits that are effectively batch/structural changes the workflow lacks an explicit validate-then-fix-then-retry feedback loop with checkpoints, which the rubric requires to reach level 3 for this category of operation.	2 / 3
Progressive Disclosure	There is a clear one-level-deep pointer to a real bundled file ('Full detailed guide ... ${CLAUDE_SKILL_DIR}/references/SKILL.full.md', which exists) plus external spec links, but the main body mixes overview, instructions, examples, and output into one file and the reference is signaled only in a single Resources line rather than clearly split per topic, so it is structured-but-could-be-better rather than the well-signaled level-3 pattern.	2 / 3
	Total	8 / 12 Passed

Description

35%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 establishes a clear YAML/config niche with named actions, but it relies on boilerplate auto-activation phrasing ('Use when appropriate context detected') instead of concrete natural trigger terms and lacks an explicit 'Use when...' clause, capping completeness and trigger quality. It is distinguishable but somewhat generic in how it signals when to fire.

Suggestions

Replace the boilerplate 'Use when appropriate context detected' with an explicit 'Use when...' clause listing concrete triggers, e.g. 'Use when working with YAML files (.yml/.yaml), or when the user mentions Kubernetes manifests, GitHub Actions workflows, Docker Compose, or YAML syntax/validation errors.'

Lead the description with specific actions the user would recognize ('validate YAML syntax, normalize indentation and quoting, detect duplicate keys and bad anchors, check configs against the target schema'), mirroring the level-3 example style.

Drop generic filler ('Execute proactive YAML intelligence', 'Trigger with relevant phrases based on skill purpose') that adds no trigger value and reads as fluff.

Dimension	Reasoning	Score
Specificity	The description names the YAML domain and several concrete actions ('validate syntax, enforce consistent formatting, and keep configuration files schema-correct'), but these are framed as a prose overview rather than a tight enumeration of actions, so it sits at 'names domain and some actions, but not comprehensive' rather than the full list of multiple specific actions at level 3.	2 / 3
Completeness	It states what the skill does, but the when is only implied via 'automatically activates when working with YAML files' plus the vague 'Use when appropriate context detected' — there is no explicit 'Use when...' clause with concrete triggers, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Natural trigger terms users would say are essentially absent; the text uses generic phrasing ('working with YAML files', 'Use when appropriate context detected', 'Trigger with relevant phrases based on skill purpose') rather than concrete keywords like 'YAML files', '.yml', 'compose', 'GitHub Actions', or 'validate', matching the 'no natural keywords; technical jargon or overly generic' anchor.	1 / 3
Distinctiveness Conflict Risk	The YAML niche is fairly distinct (YAML/config tooling for Kubernetes, GitHub Actions, Compose) so it is unlikely to broadly conflict, yet the generic 'proactive YAML intelligence' framing and absent concrete triggers mean it could overlap with general config or formatting skills, landing at 'somewhat specific but could still overlap'.	2 / 3
	Total	7 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/productivity/002-jeremy-yaml-master-agent/skills/yaml-master/SKILL.md
Commit: bddba3c

Reviewed: 1 day 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.