grok

Designing regex, parsers, and DSLs for grammar authoring and ReDoS-safe regex. Not for REST APIs (Gateway) or DB schemas (Schema).

Quality

66%

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 ./.archive/grok/SKILL.md

Quality

Content

67%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 well-structured, technically dense, and assumes Claude's intelligence with concrete rules and a clear phased workflow gated by a quality check. Its main weaknesses are redundant padding (the duplicated HTML comment header and Never/Avoids overlap) and reliance on reference files that are not present in the bundle.

Suggestions

Remove or collapse the HTML CAPABILITIES_SUMMARY comment block since its content is repeated in the visible body, recovering token budget.

Merge the 'Avoids' and 'Never' lists (or cross-reference) to eliminate the restated guidance.

Either include the referenced reference/*.md and _common/*.md files in the bundle or note their canonical location, so the well-signaled references are verifiable.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and assumes Claude's competence, but the large HTML CAPABILITIES_SUMMARY comment duplicates structure that reappears in the body, and the 'Avoids' section largely restates the 'Never' list — noticeable padding that could be tightened rather than the lean 5 anchor.	3 / 5
Actionability	Concrete inline rules (numbered Regex Safety checklist, three executable reject patterns with comments, named engines and complexity classes) provide mostly executable guidance; the bulk of deep detail is deferred to reference files, a minor gap versus the fully copy-paste-ready 5 anchor.	4 / 5
Workflow Clarity	The ANALYZE → GRAMMAR → IMPLEMENT → HARDEN → DOCUMENT table sequences phases with per-phase actions and rules, and CODE_QUALITY_GATE ('SEC: risk blocks completion') is an explicit checkpoint; an explicit validate→fix→retry feedback loop is implied by HARDEN rather than stated, leaving it just below 5.	4 / 5
Progressive Disclosure	A Reference Map table signals one-level-deep references clearly and content is appropriately split between overview and detail files; however no bundle files are present (references/, scripts/, assets/ absent), so the referenced paths cannot be verified, a minor organization gap against the clean 5 anchor.	4 / 5
	Total	15 / 20 Passed

Description

65%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 has a clear niche and strong distinctiveness with explicit routing away from neighboring skills, but it is limited by a single repeated verb and the absence of a positive 'Use when…' trigger clause. Adding concrete actions and an explicit positive trigger would lift specificity and completeness.

Suggestions

Add a positive 'Use when…' clause with concrete trigger phrases (e.g. 'Use when designing or auditing regex, authoring EBNF/ABNF/PEG grammars, or selecting a parser generator').

Replace the single verb 'Designing' with several distinct concrete actions (design, audit for ReDoS, select, hand off) to improve specificity.

Include a few natural synonyms users say ('pattern matching', 'EBNF/PEG', '.regex') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Designing regex, parsers, and DSLs for grammar authoring and ReDoS-safe regex" names the domain and applies one verb across several objects, but does not list multiple distinct concrete actions; it fits 'names domain and 1-2 concrete actions, but not comprehensive' rather than the several-action anchor at 4.	3 / 5
Completeness	The 'what' is clear, but there is no positive 'Use when…' clause — only negative routing ('Not for REST APIs (Gateway) or DB schemas (Schema)'), which the guideline caps at 3 for missing explicit positive trigger guidance.	3 / 5
Trigger Term Quality	Natural keywords a user would say are present (regex, parsers, DSLs, grammar, ReDoS), giving good coverage; a few natural variations/synonyms (e.g. pattern, EBNF, .regex) are absent, so it does not reach the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	An explicit niche (regex/parsers/DSLs/grammar) plus explicit negative routing to Gateway and Schema gives a clear distinct niche with minimal conflict risk, matching the 5 anchor.	5 / 5
	Total	15 / 20 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: simota/agent-skills
Path: .archive/grok/SKILL.md
Commit: f425adc

Reviewed: 5 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.