error-pattern-safety

Apply safe error-pattern matching rules for agentic engines.

Quality

63%

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 ./.github/skills/error-pattern-safety/SKILL.md

Quality

Content

77%

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

The body is a strong, actionable guideline with concrete patterns, validation checkpoints, and a testing checklist, undermined mainly by redundancy across sections and some explanation of concepts Claude already knows. Organization is solid but monolithic rather than progressively disclosed across files.

Suggestions

Consolidate the repeated bare-`.*` guidance: cover dangerous patterns once and cross-reference from the other sections instead of restating the prohibition four times.

Trim or remove the 'The Problem' explanation of `lastIndex`/zero-width behavior, which restates JavaScript regex fundamentals Claude already knows.

Consider splitting the test templates, Go-to-JavaScript conversion, and fix recipes into a reference file linked from a leaner overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and focused, but it explains the `lastIndex`/zero-width mechanism Claude already knows and repeats the bare-`.*` danger across four sections (Dangerous Patterns, Safety Rules, Current Codebase, How to Fix), so it is 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	It provides concrete, copy-paste-ready regex and Go patterns (e.g. `(?i)error.permission.denied`, `/\[(\d{4}-\d{2}-\d{2})\]\s+(ERROR):\s+(.+)/g`) plus executable test snippets and a Go-to-JavaScript conversion example, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	"Adding New Error Patterns" gives a clear numbered sequence with explicit validation checkpoints (`make test-unit`, `TestAllEnginePatternsSafe`, `TestErrorPatternsNoInfiniteLoopPotential`) plus a Testing Checklist, providing the feedback loop (write -> test -> fix) the rubric rewards at level 3.	3 / 3
Progressive Disclosure	The document is well-sectioned and lists references (repo test paths, Go/MDN regex docs) one level deep in a References section, but all content is inline in a single ~200-line file with sections (test templates, conversion guide, fix recipes) that could be split out, fitting 'some structure but could be better organized' rather than the cleanly-split level 3.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 states a clear purpose and domain but stops short of listing concrete capabilities or providing explicit usage triggers. It is adequate but generic, relying on jargon rather than natural user language.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when writing or reviewing regex error patterns for agentic engines, especially to avoid infinite loops from zero-width matches."

Include natural trigger terms users would actually say, such as "regex", "infinite loop", "zero-width match", and "global flag", alongside "error-pattern matching".

List concrete actions (e.g. "write, validate, and convert Go-to-JavaScript error patterns") to raise specificity from a single verb to multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	"Apply safe error-pattern matching rules" names a domain and a single action but does not list multiple concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill does ("Apply safe error-pattern matching rules") but has no explicit "Use when..." trigger clause, which per the guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Terms like "error-pattern matching" and "agentic engines" are relevant but technical/jargon-heavy, and common natural variations users would say ("regex", "infinite loop", "zero-width match") are missing, so it lands at 'some relevant keywords but missing common variations' rather than level 3.	2 / 3
Distinctiveness Conflict Risk	The error-pattern-safety niche for agentic engines is fairly specific, but without strong distinct trigger terms it could still overlap with general regex/programming skills, fitting 'somewhat specific but could still overlap' rather than the clearly-distinct level 3.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: github/gh-aw
Path: .github/skills/error-pattern-safety/SKILL.md
Commit: 98bac81

Reviewed: 6 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.