skill-meta-prompt

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

Quality

72%

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

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable and presents a well-sequenced, verification-rich workflow with concrete templates and a worked example, but it is verbose and monolithic with no progressive disclosure into reference files despite its length.

Suggestions

Trim the ASCII flowchart and 'The Bottom Line' motivational summary to reduce token overhead without losing guidance.

Move the full worked example and/or the five-technique detail into reference files (e.g. TECHNIQUES.md, EXAMPLES.md) linked from a concise overview.

Tighten the 'What/When/How/Example' framing per technique to drop explanation Claude already has about decomposition and expert personas.

Dimension	Reasoning	Score
Conciseness	The body carries substantial actionable content, but it is padded with a large ASCII flowchart, a motivational 'The Bottom Line', and over-explained technique framing that could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	As an instruction-only skill it provides copy-paste-ready output templates, an exact required return format, expert assignment matrices, and a fully worked API-documentation example, meeting the 'fully executable/specific examples; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The six-phase process is clearly sequenced with explicit verification checkpoints (Phase 4 Verification Design, per-phase 'Verification:' steps, a closing checklist) and feedback loops via the iteration phase and error-handling sections, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	There are no bundle files and everything lives in a ~500-line monolithic SKILL.md; sections are well organized, but content that could be split out (the five techniques, the full worked example) is inline with no one-level-deep references, matching the 'some structure, content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 cleanly pairs a stated capability with an explicit 'use when' trigger, but its action language is generic ('better', 'proven optimization techniques') and the prompt domain is broad enough to risk overlap with other prompt-producing skills.

Suggestions

Replace vague modifiers with concrete actions, e.g. 'Decompose tasks, assign expert personas, and build verification steps into prompts'.

Add natural trigger variations users actually say, such as 'prompt engineering', 'write a prompt for', or 'improve this prompt'.

Sharpen distinctiveness by naming the meta-prompting niche, e.g. 'Generate structured, verifiable prompts for complex tasks' to separate it from direct task-execution skills.

Dimension	Reasoning	Score
Specificity	Names the prompt domain and the action 'Craft better prompts' but relies on vague modifiers like 'better' and 'proven optimization techniques' rather than enumerating multiple concrete actions, so it does not reach the multi-action anchor of 3.	2 / 3
Completeness	It states both what it does ('Craft better prompts using proven optimization techniques') and an explicit when clause ('use when your prompt needs refinement'), satisfying the what-AND-when-with-explicit-trigger anchor.	3 / 3
Trigger Term Quality	It surfaces some natural terms a user would say ('prompts', 'refinement', 'optimize'), but misses common variations such as 'prompt engineering' or 'write a prompt for', landing at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Prompt optimization is a somewhat specific niche, but the broad term 'prompts' could still overlap with the many skills that generate or refine prompts, matching the 'somewhat specific but could still overlap' anchor rather than a clearly conflict-free niche.	2 / 3
	Total	9 / 12 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 (519 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: 9f39f0c

Reviewed: 10 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.