CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-patterns

Reference patterns for augmented coding with AI. Use when discussing AI coding patterns, anti-patterns, obstacles, context management, steering AI, or looking up Lexler's patterns collection.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/ai-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 an efficient, well-structured reference index: it bootstraps its data source with a real script, catalogs patterns tersely, and points to the full documents one level deep. It is consistently strong across dimensions with only minor gaps — no example of reading an individual pattern file and slightly implicit navigation from catalog entries to documents.

DimensionReasoningScore

Conciseness

The body is a lean catalog — each obstacle/anti-pattern/pattern gets a single-line description with no explanation of concepts Claude already knows. Only minor filler exists ("Patterns not on the main journey but useful in practice"), so it sits at anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Provides concrete, executable commands: the ensure-patterns-repo bootstrap script, `ls` commands for browsing patterns/anti-patterns/obstacles, and the online URL. A minor gap keeps it from anchor 5: no example of actually opening and reading a specific pattern document (e.g. cat of a pattern file path).

4 / 5

Workflow Clarity

The sequence is clearly signaled — "First Step: Ensure Repository Exists and Update", then "Patterns Location" base path, then "Browse All" commands. As a simple lookup skill with no destructive or batch operations, no validation checkpoints are required; the only minor gap is not stating what to do after browsing.

4 / 5

Progressive Disclosure

Well-organized category sections (Context Management, Reliability & Quality, Communication, Additional Patterns) and the inline catalog acts as a one-level-deep index into the cloned repo's documents; the referenced bundle script (scripts/ensure-patterns-repo) exists. Not anchor 5 because the links to individual pattern documents are implicit (via ls paths) rather than clearly signaled per-pattern references.

4 / 5

Total

16

/

20

Passed

Description

70%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.

A solid description with an explicit and multi-trigger 'Use when' clause and a clearly named domain. Its main weakness is an abstract 'what' — it says patterns are referenced but not what the skill concretely does with them, and the action vocabulary is thin relative to the topic coverage.

Suggestions

Replace the abstract 'what' with concrete operations, e.g. "Browses, looks up, and summarizes individual pattern documents from Lexler's augmented-coding-patterns collection".

Add one or two common user phrasings as triggers, such as "AI-assisted coding" or "working effectively with LLMs", to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The only stated actions are "Reference patterns" and "looking up" — the domain is well named ("augmented coding with AI", "context management", "steering AI") but the description enumerates topics rather than concrete operations. It names the domain with 1-2 actions (anchor 3) but doesn't list several specific actions needed for anchor 4.

3 / 5

Completeness

Has an explicit "Use when..." clause with multiple concrete triggers (strong 'when') and a present but abstract 'what' ("Reference patterns for augmented coding with AI") that doesn't state what is actually done with the patterns. Between anchors 4 and 5; the 'what' lacks the concreteness anchor 5 requires.

4 / 5

Trigger Term Quality

Includes natural phrases users would say — "AI coding patterns", "anti-patterns", "obstacles", "context management", "steering AI", "Lexler's patterns collection" — giving good keyword coverage. Not 5 because common variations like "AI-assisted coding", "prompt engineering", or "LLM" are missing.

4 / 5

Distinctiveness Conflict Risk

Distinct niche signaled by "Lexler's patterns collection" and "augmented coding with AI"; minor overlap risk with general AI-coding or prompting skills. Mostly distinct per anchor 4, but not a fully unambiguous trigger set for anchor 5.

4 / 5

Total

15

/

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

saski/arnesto

Path

.agents/skills/ai-patterns/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.