CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with a clear sequenced pipeline, concrete component mappings, and copy-paste examples, but it is a long monolithic file with some frontmatter duplication and large reference tables that could be externalized into bundle files. Conciseness and progressive disclosure are the weaker dimensions.

Suggestions

Remove or condense the body's 'When to Use' / 'Do Not Use When' sections since they restate triggers already in the frontmatter description, saving tokens.

Extract the large tech-stack→skills/agents and intent→component mapping tables into a references/ file (e.g. COMPONENT_MAP.md) and link to it from SKILL.md, moving from a monolithic file toward one-level-deep progressive disclosure.

Collapse the redundant quick-pattern table (Section 4) into the intent→components table (Phase 3) to eliminate overlapping content.

DimensionReasoningScore

Conciseness

The ~380-line body is mostly efficient domain-specific ECC mapping rather than generic concept explanation, but it duplicates frontmatter content (the 'When to Use'/'Do Not Use When' sections restate the description's triggers) and could tighten overlapping tables (intent→components vs. quick-pattern table). It matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the fully lean score-3 anchor.

2 / 3

Actionability

Provides concrete ECC component mappings, exact workflow sequences with specific commands (/plan, /tdd, /verify), and three full copy-paste-ready optimized prompts in fenced blocks, matching the 'fully executable... copy-paste ready' anchor.

3 / 3

Workflow Clarity

A clearly sequenced 6-phase pipeline (Phase 0→5) with an explicit Phase 4 missing-context checklist and a gating rule ('If 3+ critical items are missing, ask the user up to 3 clarification questions') plus /verify gates in examples, matching the 'clear sequence with explicit validation steps... checklists' anchor.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), so all content sits in a single ~380-line monolithic SKILL.md with large reference tables (tech-stack→skills, intent→components) that could be split into separate files. It matches 'some structure but could be better organized; content that should be separate is inline'; the under-50-line simple-skill carve-out does not apply here.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, third-person, and answers both what the skill does and when to trigger it, with strong bilingual trigger coverage and explicit conflict-avoidance guidance. It is one of the stronger descriptions against the rubric anchors.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt'), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Analyze raw prompts... output a ready-to-paste optimized prompt') and when ('TRIGGER when: user says...'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Strong coverage of natural phrasings users would say in both English ('optimize prompt', 'improve my prompt', 'help me prompt') and Chinese ('优化prompt', '帮我优化这个指令'), matching the 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

Clear niche (prompt-optimization advisory) with distinct triggers plus explicit conflict avoidance ('DO NOT TRIGGER when user says "优化代码", "optimize this code"'), making overlap with refactoring skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
affaan-m/ECC
Reviewed

Table of Contents

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.