prompt-optimizer

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 advisory skill with a clear gated pipeline and excellent worked examples, but it is a single monolithic file with no progressive disclosure: large reference tables and examples that belong in bundled files are inlined, pushing conciseness and structure down.

Suggestions

Move the intent→component and tech-stack→skill mapping tables (Phase 3) into a references/ file (e.g. COMPONENT_MAP.md) and summarize the matching logic inline, linking to the full map for detail.

Relocate the three full worked examples into references/EXAMPLES.md, keeping only short trigger examples in SKILL.md, to cut the body length and improve token efficiency.

Consider moving the output-format spec to references/OUTPUT_FORMAT.md and referencing it, leaving SKILL.md as a concise overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and largely assumes Claude's competence, but at ~380 lines it carries material that reads like a reference catalog (the full intent→component and tech-stack→skill mapping tables) that could be delegated to a bundled reference file; some redundancy between the description, "When to Use", and "Examples" sections adds tokens that do not all earn their place.	3 / 5
Actionability	Provides concrete, executable guidance throughout: exact project-detection file checks, decision tables mapping intent/scope/stack to specific ECC components, a precise output format template, and three complete copy-paste-ready optimized prompt examples covering EN/ZH and EPIC cases.	5 / 5
Workflow Clarity	The 6-phase pipeline (Phase 0–5) is explicitly sequenced with a gating checkpoint ("If 3+ critical items are missing, ask... up to 3 clarification questions before generating") and the advisory boundary is reinforced as a guard ("do not switch into implementation mode"); output structure is pinned to an exact format.	5 / 5
Progressive Disclosure	The skill is a single monolithic SKILL.md with no bundle files (references/, scripts/, assets/ are absent); the large intent→component and tech-stack→skill mapping tables and worked examples clearly belong in separate one-level-deep reference files that the overview would point to, so structure exists but content that should be split is inlined.	3 / 5
	Total	16 / 20 Passed

Description

100%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 highly specific, third-person description that explicitly defines what the skill does, when to trigger it (bilingual EN/ZH), and when not to trigger it. It clearly carves out a distinct niche from refactoring and performance skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("identify intent and gaps", "match ECC components", "output a ready-to-paste optimized prompt") with comprehensive coverage of the skill's behavior.	5 / 5
Completeness	Explicitly answers both what ("Analyze raw prompts... output a ready-to-paste optimized prompt") and when ("TRIGGER when... DO NOT TRIGGER when...") with concrete trigger and exclusion phrases.	5 / 5
Trigger Term Quality	Comprehensive bilingual trigger phrases users would naturally say ("optimize prompt", "improve my prompt", "优化prompt", "怎么写prompt") plus explicit exclusion phrases, covering synonyms and Chinese equivalents.	5 / 5
Distinctiveness Conflict Risk	Clear niche (prompt optimization) with explicit DO NOT TRIGGER boundaries against refactoring/performance tasks ("优化代码", "optimize performance"), minimizing conflict risk with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: skills/prompt-optimizer/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.