CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

error-pattern-safety

Apply safe error-pattern matching rules for agentic engines.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/error-pattern-safety/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 body is a strong, actionable reference: concrete patterns, runnable commands, an explicit validation workflow, and a recovery section for unsafe patterns. Its main weakness is redundancy — the same safe patterns and near-identical Go/JS test snippets are repeated, inflating token cost without adding guidance.

Suggestions

Consolidate the repeated safe-pattern examples ('Dangerous Pattern Examples', 'Safe Pattern Examples', 'Examples from Current Codebase') into one canonical example set to cut ~30 lines of duplication.

Merge the Go and JavaScript empty-string validation snippets into a single section showing both forms once, instead of restating the same test in 'Pattern Safety Rules', 'Validation Tests', and the checklist.

DimensionReasoningScore

Conciseness

The body is mostly efficient with distinct section intents, but the same patterns (e.g. `(?i)error.*permission.*denied`) repeat across four sections and the Go and JavaScript empty-string test snippets are near-duplicates, so it fits 'mostly efficient but could be tightened' rather than the verbose anchor below.

3 / 5

Actionability

Concrete executable material throughout — real patterns, specific commands (`make test-unit`, `make test-js`, `TestAllEnginePatternsSafe`), and before/after fix examples. It falls short of the copy-paste-ready anchor because the test snippets use 'your-pattern' placeholders.

4 / 5

Workflow Clarity

'Adding New Error Patterns' is a clear 4-step sequence with explicit validation (run `make test-unit`, check `TestAllEnginePatternsSafe`), a recovery path ('How to Fix Unsafe Patterns' before/after), and a final Testing Checklist — satisfying all three elements of the top anchor.

5 / 5

Progressive Disclosure

A single, well-sectioned SKILL.md with clear headers and an explicit References list; no bundle files exist so nothing is misfiled. At ~200 lines, content like 'Examples from Current Codebase' could live in a separate reference file, keeping it at the 'good structure, minor organization gaps' anchor rather than the well-signaled-references anchor.

4 / 5

Total

16

/

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 states a clear, moderately specific 'what' but omits any 'when to use' guidance and lacks the natural trigger synonyms (regex, infinite loop) users would most likely say. It sits at the midpoint of the rubric — serviceable but underperforming its content.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing or editing regex error patterns for agentic engines, or when a JavaScript regex with the g flag hangs or loops infinitely.'

Include natural synonyms such as 'regex', 'regular expression', and 'infinite loop' so the description matches how users actually phrase the request.

Enumerate 2-3 concrete actions (write safe patterns, validate against empty-string matches, convert Go patterns to JavaScript) instead of the single generic 'Apply ... rules'.

DimensionReasoningScore

Specificity

The description names the domain ('error-pattern matching rules for agentic engines') and one action ('Apply'), but does not enumerate concrete actions like writing, validating, or converting patterns, so it matches the 'names domain and 1-2 concrete actions' anchor rather than the several-specific-actions anchor.

3 / 5

Completeness

It answers 'what' (apply safe error-pattern matching rules) but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'error-pattern', 'matching', and 'agentic engines' are relevant keywords, but the natural phrases a user would say — 'regex', 'regular expression', 'infinite loop', 'hang' — are missing, matching the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

'for agentic engines' plus 'error-pattern matching' carves a fairly distinct niche with only minor overlap risk against generic regex-safety or error-handling skills, fitting the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.