create-rule

Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.

Quality

40%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/customaize-agent/skills/create-rule/SKILL.md

Quality

Content

55%

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

The skill provides highly actionable and well-structured workflow guidance for creating rules, with excellent contrastive examples and a thorough validation process. However, it is severely over-length and verbose — it explains concepts Claude already knows (what rules/skills/CLAUDE.md are, why contrastive examples work), includes a full reproduction of official documentation, and keeps all content inline rather than splitting into reference files. The token cost of loading this skill is disproportionate to the unique value it adds.

Suggestions

Cut the 'About Rules' section (Rules vs Skills vs CLAUDE.md table, 'What Rules Provide' list) — Claude already knows this context and it wastes ~150 words of token budget.

Remove or drastically shorten the 'Claude Code Official Rules Guidelines' appendix section — it duplicates official documentation and adds ~300 words of redundant content.

Extract the complete rule examples and anti-patterns catalog into separate reference files (e.g., EXAMPLES.md, ANTI-PATTERNS.md) and link to them from the main skill.

Remove the 'Why Contrastive Examples Work' subsection explaining research rationale — Claude doesn't need to be convinced why the pattern works, just told to use it.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It explains concepts Claude already knows (what rules are, what skills are, what CLAUDE.md is), includes a full comparison table of Rules vs Skills vs CLAUDE.md, explains why contrastive examples work from a research perspective, and repeats the official Claude Code documentation nearly verbatim at the end. Much of this content could be cut to under 100 lines while preserving all actionable guidance.	1 / 3
Actionability	The skill provides fully concrete, executable guidance: complete rule file templates with proper frontmatter, multiple complete rule examples (early returns, API validation), specific directory structures, glob pattern tables, a detailed checklist, and copy-paste-ready markdown templates. Every step has concrete artifacts.	3 / 3
Workflow Clarity	The 7-step rule creation process is clearly sequenced with explicit validation checkpoints (Step 6: Validate the Rule with specific checks, Step 7: Iterate with decompose/filter/reweight cycle). The refinement loop includes feedback-based iteration. The checklist at the end serves as a final validation gate.	3 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no references to external files. Content that could be split out (the complete examples, the anti-patterns catalog, the official Claude Code guidelines appendix, the comparison table) is all inline. The official documentation section at the end is essentially duplicated content that adds significant length without being organized as a reference.	1 / 3
	Total	8 / 12 Passed

Description

25%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is poorly written with spelling errors ('repetative', 'implemenataion', 'Esentially'), vague language, and lacks concrete actions. It attempts to convey when the skill should be used through an illustrative quote, which is creative but unreliable for skill selection. The 'what' component is almost entirely missing — it never clearly states what the skill produces or how it works.

Suggestions

Specify concrete actions the skill performs, e.g., 'Creates a new rule entry in the project's rules file to prevent recurring mistakes, documenting the issue pattern and the correct approach.'

Add a proper 'Use when...' clause with natural trigger terms, e.g., 'Use when a recurring mistake is identified, when a lesson learned needs to be codified, or when the user asks to create a rule, guideline, or prevention measure.'

Fix spelling errors and use third-person voice throughout, e.g., 'Captures implementation lessons and codifies them as reusable rules' instead of the current second-person and informal phrasing.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'gap or repetative issue' and 'create rule for this issue' without specifying concrete actions. It does not list what the skill actually does in terms of specific operations (e.g., 'writes a new rule to a rules file', 'formats the rule in YAML').	1 / 3
Completeness	The description attempts to answer 'when' with 'Use when found gap or repetative issue' and the quoted trigger phrase, but the 'what' is extremely weak — it only vaguely says 'create rule for this issue.' There is no explicit 'Use when...' clause with clear, structured trigger guidance, but the intent of when to use it is partially conveyed.	2 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like 'gap or repetative issue' and 'implementation agent' are not how users naturally phrase requests. It relies on an internal monologue quote rather than searchable trigger terms like 'create rule', 'add guideline', 'prevent mistake', or 'lesson learned'.	1 / 3
Distinctiveness Conflict Risk	The concept of creating rules from mistakes is somewhat distinctive, but the vague language ('gap or repetative issue') could overlap with general debugging, retrospective, or documentation skills. The quoted phrase adds some uniqueness but is not a reliable distinguishing trigger.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (612 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: NeoLabHQ/context-engineering-kit
Commit: 3711edf

Reviewed: 20 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.