Name: apply-anthropic-skill-best-practices
Rating: 49.6 (1 reviews)
Author: NeoLabHQ

apply-anthropic-skill-best-practices

Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md

Quality

Content

58%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 content is highly actionable with excellent workflow and feedback-loop patterns, but it is severely verbose and violates its own progressive-disclosure guidance by bundling everything into one oversized file with no reference files split out. Strengths in workflow clarity are undercut by conciseness and structure problems.

Suggestions

Trim conceptual explanation Claude already knows (metadata preloading, runtime environment mechanics, what progressive disclosure is) and cut the body well under 500 lines.

Move the worked examples and pattern catalogs (PDF form filling, BigQuery, DOCX) into separate reference files linked one level deep from SKILL.md, practicing the progressive disclosure the skill preaches.

Reduce redundant restatements of the same guidance across Core principles, Progressive disclosure, Runtime environment, and Technical notes sections.

Dimension	Reasoning	Score
Conciseness	The body runs ~1015 lines, well past the 500-line budget the skill itself advocates, and extensively explains concepts Claude already knows (how metadata preloading works, runtime environment mechanics, what progressive disclosure is) alongside padded verbose examples.	2 / 5
Actionability	It provides concrete, mostly copy-paste-ready code (pdfplumber snippets, script invocations like 'python scripts/analyze_form.py input.pdf'), templates, and input/output examples, with only minor gaps where examples are illustrative rather than fully executable.	4 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced with explicit validation checkpoints and feedback loops (validate -> fix -> retry), e.g. the PDF form filling and document editing workflows gate further steps on passing validation.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and all content is inlined in a single 1015-line SKILL.md, contradicting the skill's own advice to keep the body under 500 lines and split content into separate reference files.	2 / 5
	Total	13 / 20 Passed

Description

53%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 conveys both purpose and a rough usage trigger, but it leans on the generic word 'guide' rather than concrete capabilities and lacks the natural trigger phrases a user would say. It is moderately specific but would benefit from naming concrete actions and richer trigger terms.

Suggestions

Replace the generic word 'guide' with concrete actions, e.g. 'Reviews, structures, and refines SKILL.md files against Anthropic's best practices'.

Add explicit natural trigger phrases, e.g. 'Use when authoring a new skill, reviewing an existing SKILL.md, or improving skill structure and descriptions'.

Tighten the 'when' clause with specific triggers (writing skills, refactoring SKILL.md, evaluating skill quality) to reduce overlap with generic skill-helper descriptions.

Dimension	Reasoning	Score
Specificity	The description names the domain ('skill development', 'Anthropic's official best practices') but the only action is the generic word 'guide', with no concrete actions like reviewing, structuring, or authoring spelled out.	2 / 5
Completeness	It states both what ('Comprehensive guide for skill development based on Anthropic's official best practices') and when ('use for complex skills requiring detailed structure'), though the 'when' trigger could be more explicit and specific.	4 / 5
Trigger Term Quality	It includes some relevant keywords ('skill development', 'complex skills', 'detailed structure', 'best practices') but misses the natural phrases users actually say such as 'authoring skills', 'writing a skill', or 'review my skill'.	3 / 5
Distinctiveness Conflict Risk	The phrase 'skill development' is broad and could overlap with other skill-authoring helpers, though the 'Anthropic's official best practices' qualifier narrows the niche somewhat.	3 / 5
	Total	12 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1022 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 22 missing, 7 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	12 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md
Commit: 8539779

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.