skill-meta-prompt

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

Quality

66%

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

Quality

Content

71%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 highly actionable with concrete templates and a complete worked example, and its six-phase workflow is well sequenced with verification baked in. Its main weaknesses are verbosity from decorative/redundant sections and a monolithic inline structure that would benefit from real reference files.

Suggestions

Trim or remove the ASCII flow-diagram box and "The Bottom Line" section; the phase headers already convey the sequence.

Move the full technique catalog and/or the worked API example into reference files under references/ and link to them one level deep, since no bundle files currently exist.

Verify the cross-referenced paths (skills/blocks/codex-host-adapter.md, frontier-model-routing.md, fable5-prompting.md, docs/GPT-5.6-PROMPTING.md) resolve in the target environment, or mark them as optional external dependencies.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient structured guidance with no basic-concept padding, but the ~35-line ASCII flow diagram, the repeated technique listings across the overview/techniques/phases, and the decorative "The Bottom Line" section are unnecessary tokens that could be tightened.	3 / 5
Actionability	It provides copy-paste-ready material: an exact output-format template, a Phase 1 question script, an expert-archetype table, and a fully worked API-documentation example that covers a common case end-to-end.	5 / 5
Workflow Clarity	The six phases are clearly sequenced with a visual flow, built-in verification design, a verification checklist, and error-handling feedback loops, but Phases 2-4 are grouped together and some inter-phase checkpoints are implicit rather than explicit.	4 / 5
Progressive Disclosure	Section headers give reasonable structure and external blocks are signaled in the Model-Specific Adjustments section, but there are no actual bundle files and the ~140-line technique catalog plus ~70-line worked example are inlined rather than split into one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

62%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 cleanly states both a what and a when with a natural trigger phrase, but it leans on the vague "proven optimization techniques" rather than naming concrete capabilities. It is solid and distinct, just not maximally specific or trigger-rich.

Suggestions

Replace "proven optimization techniques" with 1-2 concrete techniques the skill applies (e.g., task decomposition, fresh-eyes review, iterative verification) to lift specificity.

Expand the trigger with synonyms users actually say, e.g. "use when a prompt needs refinement, improvement, or restructuring".

Add file-format or output cues if applicable, or a second trigger condition, to widen distinctiveness beyond a single refinement phrase.

Dimension	Reasoning	Score
Specificity	"Craft better prompts using proven optimization techniques" names the prompt domain and one concrete action (craft/refine prompts), but "proven optimization techniques" is generic with no enumerated techniques, so coverage is not comprehensive.	3 / 5
Completeness	Both what ("Craft better prompts using proven optimization techniques") and when ("use when your prompt needs refinement") are present, but the trigger is a single phrase and the "what" is somewhat unspecific, so it is not a fully concrete what+when pair.	4 / 5
Trigger Term Quality	Natural terms like "prompts", "better prompts", and "prompt needs refinement" appear, but common synonyms such as "improve prompt", "rewrite prompt", or "prompt engineering" are missing, leaving keyword coverage partial.	3 / 5
Distinctiveness Conflict Risk	Meta-prompt generation is a fairly distinct niche and the refinement trigger is narrow, but there is minor overlap risk with general prompt-engineering or writing-improvement skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/skill-meta-prompt/SKILL.md
Commit: 242e51d

Reviewed: 3 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.