skill-meta-prompt

Craft better prompts using proven optimization techniques — use when your prompt needs refinement

Quality

52%

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 ./.claude/skills/skill-meta-prompt/SKILL.md

Quality

Content

51%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 skill is well-structured and actionable with clear workflows, but it is heavily verbose and monolithic, explaining concepts Claude already knows while inlining material that belongs in reference files. Buried cross-skill references further weaken navigation.

Suggestions

Trim the overview ASCII diagram and the 'What/When/How' explanations of each technique to essential, non-obvious guidance only.

Move the full prompt template, expert archetype table, and worked API-doc example into separate reference files linked from a concise overview.

Either create the referenced bundle files (skills/blocks/frontier-model-routing.md, fable5-prompting.md, docs/GPT-5.6-PROMPTING.md) or remove the dangling references, and list them in a clearly signaled reference section.

Dimension	Reasoning	Score
Conciseness	The 500-line body extensively explains generic meta-prompting concepts Claude already knows and is padded with ASCII diagrams, redundant phase descriptions, and illustrative examples that earn little per token.	2 / 5
Actionability	Provides concrete templates, exact output format, expert assignment matrices, and a worked API-doc example; minor gaps where steps are abstract placeholders.	4 / 5
Workflow Clarity	Six phases are clearly sequenced with explicit verification hooks and an iterative verification technique, though some checkpoints are described as principles rather than enforced steps.	4 / 5
Progressive Disclosure	No bundle files exist yet the body inlines everything monolithically; references to skills/blocks/*.md and docs/GPT-5.6-PROMPTING.md are buried in prose with no organized file structure.	2 / 5
	Total	12 / 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 is concise and includes a 'Use when' trigger, but its capability list is thin and generic. It answers what and when but lacks the concrete, multi-action specificity of the best examples.

Suggestions

Replace generic 'optimization techniques' with 2-3 concrete actions (e.g., 'decompose tasks, assign expert personas, build verification steps').

Expand the 'when' clause with additional natural trigger phrases like 'help me write a prompt' or 'make this prompt better'.

Add a brief anti-trigger or scope note to sharpen distinctiveness from general writing/code skills.

Dimension	Reasoning	Score
Specificity	Only 'Craft better prompts' and 'refinement' are concrete actions; 'optimization techniques' is generic with no enumerated capabilities.	2 / 5
Completeness	Provides a 'Use when' clause but it is a terse one-clause trigger rather than the explicit, multi-trigger 'when' anchor for a 5.	4 / 5
Trigger Term Quality	Phrases like 'create a prompt', 'optimize this prompt', 'prompt engineering' are natural, but synonyms and variations are limited and no file/contextual extensions.	3 / 5
Distinctiveness Conflict Risk	The narrow prompt-refinement niche is fairly distinct from code/doc skills, with minor overlap risk against general writing helpers.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (529 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-meta-prompt/SKILL.md
Commit: bc76e7c

Reviewed: 4 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.