skill-meta-prompt

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

Quality

61%

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

70%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 delivers a well-sequenced, verifiable meta-prompting workflow with concrete templates and a strong worked example, so workflow clarity and actionability are high. It is held back by verbosity (a redundant ASCII diagram and repeated scaffolding) and by progressive-disclosure issues: monolithic inlining plus references to external files that are not part of the bundle.

Suggestions

Remove the large ASCII phase diagram or collapse it to one line, since the same six phases are already described in the sections that follow.

Move the model-specific adjustments and the full worked example into separate reference files under references/ and link to them, so SKILL.md stays a lean overview.

Either include the referenced files (frontier-model-routing.md, fable5-prompting.md, GPT-5.6-PROMPTING.md) in the bundle or drop the references, since they currently point to non-existent paths.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful but visibly padded: a large ASCII phase diagram that duplicates the per-phase sections that follow, repeated What/When/How/Example scaffolding, and disclaimer templates that restate behavior Claude already knows.	3 / 5
Actionability	It supplies concrete, copy-paste-ready templates (the Phase 5 output format, expert-archetype table, the full API-doc example meta-prompt) with only minor gaps such as placeholder-only verification rows in the Phase 2-4 tables.	4 / 5
Workflow Clarity	The six phases are explicitly sequenced, verification is built into each technique and the output template, Fresh Eyes provides a creator->reviewer feedback loop, and a Verification Checklist closes the generated prompt.	5 / 5
Progressive Disclosure	Structure is present via clear section headers, but everything is inlined into one ~500-line file with no bundle files; references like skills/blocks/frontier-model-routing.md and docs/GPT-5.6-PROMPTING.md point to files that do not exist in this skill's bundle.	3 / 5
	Total	15 / 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 answers both what and when in third person, but leans on generic language ('craft better prompts', 'proven optimization techniques') and offers only a single, somewhat vague trigger phrase. It is adequate but not crisp enough to score highly on specificity or distinctiveness.

Suggestions

Replace 'proven optimization techniques' with the concrete actions the skill performs, e.g. 'Decompose tasks, assign specialized experts, and build verification steps into prompts'.

Add more natural trigger phrases to the description such as 'Use when the user asks to optimize, improve, or engineer a prompt, or to create instructions for a task'.

Sharpen distinctiveness by signaling the meta-prompt niche, e.g. 'Generates structured, verifiable prompts rather than executing the task itself'.

Dimension	Reasoning	Score
Specificity	The phrase 'Craft better prompts using proven optimization techniques' names the prompt domain but the action is generic and 'proven optimization techniques' is buzzword padding with no concrete actions like decompose/assign-experts/verify.	2 / 5
Completeness	Both 'what' (craft better prompts) and 'when' ('use when your prompt needs refinement') are present and explicit, but the trigger phrase is singular and could be more specific with concrete scenarios.	4 / 5
Trigger Term Quality	Includes the natural term 'prompts' and the trigger 'use when your prompt needs refinement', but misses common variations users say such as 'prompt engineering', 'meta-prompt', or 'optimize this prompt'.	3 / 5
Distinctiveness Conflict Risk	'Craft better prompts' is a recognizable niche but the wording is broad enough to overlap with general writing or task-execution skills, and nothing in the description alone sharply distinguishes it.	3 / 5
	Total	12 / 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 (530 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: 1bee725

Reviewed: ~22 hours 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.