CtrlK
BlogDocsLog inGet started
Tessl Logo

llm-prompt-optimizer

Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.

62

Quality

73%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/llm-prompt-optimizer/SKILL.md

The canonical home for this skill is llm-prompt-optimizer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A thorough, actionable prompt-engineering guide with strong templates and useful checklists, weakened by re-teaching concepts Claude already knows and by keeping all content inline in a long single file. Splitting the pattern library into a reference and trimming explanatory padding would materially raise quality.

Suggestions

Move the seven pattern templates into a references/ file (e.g. PATTERNS.md) and keep SKILL.md as a concise overview that links to it, improving progressive disclosure.

Trim sections that re-explain well-known concepts (Chain-of-Thought, Few-Shot, Structured JSON) to one-line pointers plus the template, relying on Claude's existing knowledge.

Add explicit validation checkpoints between steps (e.g. 'After drafting, run the Prompt Audit Checklist before considering the prompt production-ready') to turn the checklist into an embedded feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient with clear templates, but several sections (Chain-of-Thought, Few-Shot, Structured JSON, Reduce Hallucination) re-explain prompt-engineering concepts Claude already knows; could be tightened. Not a 2 because the RSCIT framework and before/after examples add genuine, non-obvious value.

3 / 5

Actionability

Provides concrete, copy-paste-ready templates (RSCIT before/after, CoT skeleton, JSON schema, hallucination guard, compression) covering common cases with placeholders. Not a 5 because the examples are templates rather than fully worked, substitution-free runnable artifacts.

4 / 5

Workflow Clarity

A clear numbered 1–7 sequence (Diagnose → RSCIT → CoT → Few-Shot → JSON → Hallucination → Compression) supported by an Audit Checklist and a Troubleshooting feedback section. Not a 5 because validation checkpoints are implicit rather than woven as explicit validate→fix→retry gates between steps.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, but at ~170 lines it is a monolithic single-file skill with no external references; the pattern library is a natural candidate for a separate reference file. The under-50-line simple-skill exception does not apply, so it cannot reach 5 on structure alone.

3 / 5

Total

14

/

20

Passed

Description

83%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 well-constructed description that clearly states both purpose and trigger conditions in concise third-person voice. Minor gains are available by naming specific techniques and adding a few more natural synonyms.

DimensionReasoningScore

Specificity

Names the domain ('prompt engineering techniques') and lists several concrete outcomes — 'boost output quality, reduce hallucinations, and cut token usage' — matching the anchor for several specific actions with minor gaps; not a 5 because 'proven techniques' is left generic rather than enumerated.

4 / 5

Completeness

Explicitly answers both 'when' ('Use when improving prompts for any LLM') and 'what' ('Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases are present — 'improving prompts', 'any LLM', 'hallucinations', 'token usage' — giving good keyword coverage; falls short of 5 because common synonyms (e.g. 'system prompts', 'chatbot prompts', model names) are absent.

4 / 5

Distinctiveness Conflict Risk

'Improving prompts for any LLM' carves a clear, mostly-distinct niche with low conflict risk; not a 5 because 'any LLM' is broad and could lightly overlap with general writing or agent-design skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.