align-target-style
Convert a user style request into concrete rewrite constraints and apply that style during de-flavoring. Use when the user specifies a target tone, audience, or writing persona.
Best use case
align-target-style is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Convert a user style request into concrete rewrite constraints and apply that style during de-flavoring. Use when the user specifies a target tone, audience, or writing persona.
Teams using align-target-style should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/align-target-style/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How align-target-style Compares
| Feature / Agent | align-target-style | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Convert a user style request into concrete rewrite constraints and apply that style during de-flavoring. Use when the user specifies a target tone, audience, or writing persona.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Align Target Style Use this skill after diagnosis and before final rewriting when the user provides an explicit style requirement. This skill turns vague style requests into usable editing constraints. ## When to Use Use this skill when the user says things like: - rewrite this in a more natural blog style - make it sound like a product manager - keep it human but more casual - remove AI flavor and make it sound like a sharp Chinese columnist ## Task Convert the requested style into a small style card. The style card should capture: - tone - formality level - sentence rhythm - degree of directness - acceptable use of first person, humor, or rhetorical questions - audience fit ## Rewrite Rules - Treat the style request as a hard preference - Keep the meaning stable - Adapt diction, pacing, structure, and emphasis to the requested style - Do not overperform the style into parody - If the style request is underspecified, infer the simplest plausible version - Prefer stable voice over obvious stylistic tricks ## Default If No Style Is Given Do not use this skill when no style is given. The agent default remains: - natural - concise - grounded - like a skilled Chinese writer ## Prompt Pattern ```text Translate the user's style request into a compact style card for rewriting. Specify tone, formality, rhythm, directness, and audience fit. Then apply that style while making the prose sound authored and natural. Preserve meaning and avoid exaggerated mimicry. ```
Related Skills
antibody_target_analysis
Antibody-Target Analysis - Analyze an antibody target: UniProt protein info, InterPro domains, protein properties, and biotherapeutic data from ChEMBL. Use this skill for immunology tasks involving get uniprotkb entry by accession query interpro ComputeProtPara get biotherapeutic by name. Combines 4 tools from 4 SCP server(s).
gene_therapy_target
Gene Therapy Target Analysis - Analyze gene therapy target: gene info, variant pathogenicity, protein structure, and clinical evidence. Use this skill for gene therapy tasks involving get gene metadata by gene name get vep hgvs Protein structure prediction ESMFold clinvar search. Combines 4 tools from 4 SCP server(s).
drug_target_identification
Drug Target Identification Pipeline - Identify drug targets for a disease by querying OpenTargets for associated targets, then retrieve detailed target info from ChEMBL and protein data from UniProt. Use this skill for drug discovery tasks involving get associated targets by disease efoId get target by name get general info by protein or gene name. Combines 3 tools from 3 SCP server(s).
nsfc-ref-alignment
检查 NSFC 标书正文引用与参考文献的一致性与真实性风险（只读）：核查 bibkey 是否存在、BibTeX 字段与 DOI 等格式问题，并生成结构化输入供宿主 AI 逐条评估“正文表述是否真的在引用该文献”；默认仅输出审核报告，不直接修改标书或 .bib（除非用户明确要求）。
nsfc-length-aligner
基于国自然标书篇幅预算标准；检查目标标书篇幅并总结差距；给出针对性优化建议；在尽量不改变原意的前提下扩写/压缩到达标。
check-review-alignment
当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"或"运行 check-review-alignment"时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合，只在发现致命性引用错误时对"包含引用的句子"做最小化改写，并复用 `systematic-literature-review` 的渲染脚本输出 PDF/Word。核心原则：不为了改而改，无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用：用户只是想生成系统综述正文（应使用 systematic-literature-review）；用户只是想新增/核对 BibTeX 条目（应使用专门的 bib 管理流程）。
opentargets-disease-target
Retrieve disease-associated targets from Open Targets using disease EFO IDs to identify therapeutic targets.
drugsda-target-retrieve
Search the protein information from the input gene name and downloads the optimal PDB or AlphaFold structures.
drug_target_structure
Drug-Target Structural Biology - Integrate drug and target structure: get drug from ChEMBL, target structure from PDB, dock them, and predict ADMET. Use this skill for structural pharmacology tasks involving get drug by name retrieve protein data by pdbcode quick molecule docking pred molecule admet. Combines 4 tools from 3 SCP server(s).
acpx
Use the ACPX CLI through DrClaw's existing exec/long_exec tools to run Codex in the current project workspace.
ui-ux-pro-max
[Frontend] Frontend UI/UX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks. Triggers on ui design, ux design, design system, color palette, typography, glassmorphism, claymorphism, neumorphism, bento grid, font pairing, ui-ux-pro-max, stunning interface, beautiful ui.
fetch
Fetch metadata and links from arXiv for a given query.