CtrlK
BlogDocsLog inGet started
Tessl Logo

prompt-optimize

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/core/ai/prompt_optimize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 presents a clear, well-sequenced dialogue workflow with useful examples and explicit collaboration checkpoints, but it is verbose — re-explaining basic prompt-engineering concepts Claude already knows and layering on poetic prose — and ships as a single monolithic file with no progressive disclosure into references. Actionability is decent but undercut by abstract framing and the absence of a concrete final-artifact example.

Suggestions

Remove or relocate the 'Knowledge Base Reference' definitions of basic techniques (Few-shot, Zero-shot, CoT, ToT, ReAct, Step-Back) — Claude already knows these — and trim poetic passages to tighten conciseness toward the lean top anchor.

Add at least one fully-worked example of the final delivered prompt (e.g., a complete XML/Markdown prompt artifact) so the 'Phase 3: 最终交付' guidance is concrete and copy-paste-ready rather than only described.

Split the inline Knowledge Base Reference and Example Scenarios into separate reference files (e.g., references/techniques.md, references/examples.md) linked from a concise SKILL.md overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

A 'Knowledge Base Reference' section redefines concepts Claude already knows (Few-shot, Zero-shot, CoT, ToT, ReAct, Step-Back) and the body is padded with poetic flourishes ('充满巧思的艺术品', '给剑客配上能看透内心的眼睛'), so it lands at 'mostly efficient but includes unnecessary explanation or could be tightened' rather than the lean top anchor.

2 / 3

Actionability

Offers concrete dialogue examples and a specific upgrade-signal mapping (创意生成→ToT+Self-Consistency), but interleaves them with abstract behavioral direction ('对话的艺术', '激发用户的灵感') and never shows a concrete final delivered prompt artifact, fitting 'some concrete guidance but incomplete' rather than fully copy-paste-ready.

2 / 3

Workflow Clarity

A clearly sequenced 3-phase workflow (诊断与探询 → 协作构建 → 最终交付) with explicit wait-for-response decision gates ('永远等待关键决策点的回应', '绝不直接动手修改,等待回应') and supporting checklists (Quality Standards, Important Reminders) meets the 'clear sequence with explicit checkpoints' anchor; it is not the level below where checkpoints are only implicit.

3 / 3

Progressive Disclosure

The skill is a single ~240-line monolith with no bundle files or external references; though sections are well-organized with clear headings, content such as the Knowledge Base Reference and Example Scenarios is inline that could be split into reference files, matching 'some structure but content that should be separate is inline' rather than the monolithic/poorly-organized bottom anchor.

2 / 3

Total

9

/

12

Passed

Description

90%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.

A strong, well-structured description that clearly states the skill's purpose and provides explicit, natural-language activation triggers, making it both complete and distinct. Its only weakness is framing capability as persona transformation rather than enumerating concrete actions, which leaves specificity slightly below the top anchor.

DimensionReasoningScore

Specificity

Names the domain (prompt engineering) and a general action — 'collaboratively crafts high-quality prompts through flexible dialogue' — but frames capability as identity transformation ('transforms Claude into Alpha-Prompt') rather than listing multiple concrete actions, so it stops at the 'names domain and some actions, not comprehensive' anchor.

2 / 3

Completeness

Explicitly answers both what ('transforms Claude into...a master prompt engineer who collaboratively crafts high-quality prompts') and when ('Activates when user asks to...or mentions prompt engineering tasks'), with an explicit trigger clause, so it meets the 'both what AND when with explicit triggers' anchor rather than capping at 2.

3 / 3

Trigger Term Quality

Provides three explicit, naturally-spoken triggers — 'optimize prompt', 'improve system instruction', 'enhance AI instruction' — plus a 'prompt engineering tasks' catch-all, matching the 'good coverage of natural terms users would say' anchor rather than the sparse 'some relevant keywords' level below.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (prompt engineering/optimization) with distinct, specific triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor and not the overlap-prone level below.

3 / 3

Total

11

/

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
labring/FastGPT
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.