CtrlK
BlogDocsLog inGet started
Tessl Logo

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

79

1.16x
Quality

73%

Does it follow best practices?

Impact

85%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md

The canonical home for this skill is prompt-engineering-patterns in wshobson/agents

SKILL.md
Quality
Evals
Security

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.

Highly actionable with executable code and clear sequencing in the validation/error-recovery patterns, but it is over-long and inlines content that duplicates existing bundle reference files instead of linking to them.

Suggestions

Link the on-disk reference files (e.g. 'See [few-shot-learning.md](references/few-shot-learning.md)') and move the per-pattern deep dives there, keeping SKILL.md a concise overview.

Cut the Best Practices, Common Pitfalls, and Success Metrics sections or move them to a reference file; they restate knowledge Claude already has and pad the token budget.

Remove the verbatim restatement of the description in the opening line to avoid redundancy.

DimensionReasoningScore

Conciseness

The body restates the description verbatim in the intro and includes sections (Core Capabilities, Best Practices, Common Pitfalls, Success Metrics) that restate concepts Claude already knows; the catalog is otherwise useful but could be trimmed.

3 / 5

Actionability

Multiple copy-paste-ready Python patterns with real imports (anthropic, langchain, pydantic) and concrete examples covering common production cases.

5 / 5

Workflow Clarity

A clear 'When to Use' entry plus 'Quick Start', and patterns like Error Recovery and Validation embed feedback loops (try/except fallback, verify-then-revise); minor gaps since this is primarily a pattern catalog rather than a single end-to-end workflow.

4 / 5

Progressive Disclosure

Seven bundle files exist that map directly to the section topics (chain-of-thought, few-shot-learning, prompt-templates, system-prompts, etc.) but the body references none of them, inlining ~475 lines of content that clearly belongs in those separate files.

2 / 5

Total

14

/

20

Passed

Description

78%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 strong, well-formed description that answers both what and when with mostly concrete language and clear trigger phrasing. The main weakness is a somewhat abstract opening framing rather than a crisp enumeration of concrete capabilities.

DimensionReasoningScore

Specificity

Lists several concrete actions ('optimizing prompts', 'improving LLM outputs', 'designing production prompt templates'), but the opening verbs ('Master advanced prompt engineering techniques', 'maximize LLM performance, reliability, and controllability') are somewhat abstract rather than enumerating concrete capabilities.

4 / 5

Completeness

Both 'what' (master advanced prompt engineering techniques) and 'when' (Use when optimizing prompts, improving LLM outputs, or designing production prompt templates) are explicitly stated; the 'what' could be more concretely enumerated rather than phrased at a high level.

4 / 5

Trigger Term Quality

Natural trigger phrases like 'optimizing prompts', 'improving LLM outputs', and 'production prompt templates' are present, though some common synonyms (e.g. 'prompt design', 'few-shot', 'chain-of-thought') are omitted.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (production prompt engineering) with distinct, specialized triggers that are unlikely to collide with unrelated skills.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Dicklesworthstone/pi_agent_rust
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.