prose-style-reference
Extended writing reference for documentation and content creation. Load for blog posts, READMEs, technical guides, and long-form writing.
Best use case
prose-style-reference is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Extended writing reference for documentation and content creation. Load for blog posts, READMEs, technical guides, and long-form writing.
Teams using prose-style-reference 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/prose-style-reference/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How prose-style-reference Compares
| Feature / Agent | prose-style-reference | 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?
Extended writing reference for documentation and content creation. Load for blog posts, READMEs, technical guides, and long-form writing.
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
# Prose Style Reference Heavy reference for extended writing tasks. For the condensed rules, see `writing-clearly-and-concisely`. ## Part 1: Composition Principles (Strunk) Based on William Strunk Jr.'s *The Elements of Style* (1918). These rules produce clear, forceful prose. ### Active Voice The active voice is more direct and vigorous than the passive. | Passive | Active | |---------|--------| | My first visit to Boston will always be remembered by me. | I shall always remember my first visit to Boston. | | A survey of this region was made in 1900. | This region was surveyed in 1900. | | There were a great number of dead leaves lying on the ground. | Dead leaves covered the ground. | | The sound of a guitar somewhere in the house could be heard. | Somewhere in the house a guitar hummed sleepily. | | It was not long before he was very sorry that he had said what he had. | He soon repented his words. | Eliminate perfunctory expressions: *there is*, *there are*, *it was*, *could be heard*. Replace with verbs that do work. The passive is acceptable when the receiver of the action is the topic of the paragraph, or when the actor is unknown or unimportant. ### Positive Form Make definite assertions. Use *not* for denial or antithesis, never evasion. | Negative evasion | Positive form | |------------------|---------------| | He was not very often on time. | He usually came late. | | did not remember | forgot | | did not pay any attention to | ignored | | did not have much confidence in | distrusted | | not important | trifling | The reader wants to be told what *is*, not what *is not*. ### Concrete Language Prefer the specific to the general, the definite to the vague. | Abstract | Concrete | |----------|----------| | A period of unfavourable weather set in. | It rained every day for a week. | | He showed satisfaction as he took possession of his well-earned reward. | He grinned as he pocketed the coin. | | In proportion as the manners, customs, and amusements of a nation are cruel and barbarous, the regulations of their penal code will be severe. | In proportion as men delight in battles, bull-fights, and combats of gladiators, will they punish by hanging, burning, and the rack. | The surest way to hold the reader's attention is to be specific, definite, and concrete. ### Omit Needless Words A sentence should contain no unnecessary words, a paragraph no unnecessary sentences, for the same reason that a drawing should have no unnecessary lines and a machine no unnecessary parts. | Wordy | Concise | |-------|---------| | the question as to whether | whether | | there is no doubt but that | doubtless | | used for fuel purposes | used for fuel | | he is a man who | he | | in a hasty manner | hastily | | owing to the fact that | since | | in spite of the fact that | though | | call your attention to the fact that | remind you | | the fact that he had not succeeded | his failure | Revise *the fact that* out of every sentence. Eliminate *who is*, *which was* when superfluous: | Wordy | Concise | |-------|---------| | His brother, who is a member of the same firm | His brother, a member of the same firm | | Trafalgar, which was Nelson's last battle | Trafalgar, Nelson's last battle | Combine step-by-step presentation of a single idea into one sentence: | 51 words | 26 words | |----------|----------| | Macbeth was very ambitious. This led him to wish to become king of Scotland. The witches told him that this wish of his would come true. The king of Scotland at this time was Duncan. Encouraged by his wife, Macbeth murdered Duncan. He was thus enabled to succeed Duncan as king. | Encouraged by his wife, Macbeth achieved his ambition and realised the prediction of the witches by murdering Duncan and becoming king of Scotland in his place. | ### Emphatic Endings Place the most important words at the end of the sentence. | Weak ending | Strong ending | |-------------|---------------| | Humanity has hardly advanced in fortitude since that time, though it has advanced in many other ways. | Humanity, since that time, has advanced in many other ways, but it has hardly advanced in fortitude. | | This steel is principally used for making razors, because of its hardness. | Because of its hardness, this steel is principally used in making razors. | The beginning of a sentence is the other strong position. Any element other than the subject becomes emphatic when placed first: "Deceit or treachery he could never forgive." ### Parallel Structure Express co-ordinate ideas in similar form. | Broken parallel | Parallel | |-----------------|----------| | Formerly, science was taught by the textbook method, while now the laboratory method is employed. | Formerly, science was taught by the textbook method; now it is taught by the laboratory method. | | It was both a long ceremony and very tedious. | The ceremony was both long and tedious. | | A time not for words, but action. | A time not for words, but for action. | Correlative expressions (both/and, not/but, either/or) must be followed by the same grammatical construction. ### Paragraph Discipline - One paragraph per topic. - Begin with a topic sentence; end in conformity with the beginning. - Vary sentence structure to avoid monotonous loose-sentence chains. ### One Tense in Summaries When summarising, choose present or past tense and hold it throughout. Shifting tenses signals uncertainty. --- ## Part 2: AI Writing Patterns LLMs regress to statistical means. Specific, unusual, nuanced facts (statistically rare) are replaced with generic, inflated descriptions (statistically common). The subject becomes simultaneously less specific and more exaggerated. ### Puffery and Inflated Importance LLMs puff up significance by attaching claims about broader impact, legacy, or symbolism: - "marking a pivotal moment in the evolution of..." - "stands as a testament to..." - "plays a vital/significant/crucial/pivotal role" - "underscores/highlights its importance/significance" - "reflects broader trends in..." - "symbolising its ongoing/enduring/lasting impact" - "deeply rooted", "profound heritage", "steadfast dedication" - "indelible mark", "key turning point" These statements are synthesis: a disembodied narrator claiming what something *means* rather than stating what it *does*. ### Superficial "-ing" Analysis Attaching present participle phrases to make empty claims about significance: - "ensuring reliability across deployments" - "highlighting the importance of community engagement" - "showcasing the framework's capabilities" - "reflecting a commitment to innovation" - "underscoring the need for further research" Stronger tell: when the subject of these verbs is a fact, event, or inanimate thing. A person can highlight something; a railway station cannot. ### Promotional Language - "continues to captivate", "stunning natural beauty" - "groundbreaking" (figurative), "cutting-edge" - "nestled", "in the heart of", "boasts a" - "seamless", "robust", "streamlined" Say what it does. Be specific, not grandiose. ### Overused AI Vocabulary Words that co-occur heavily in LLM output. Where there is one, there are likely others: aligns/aligning with, crucial, delve/delving, emphasising, enduring, enhance/enhancing, fostering, garnered/garnering, highlight/highlighting (as verb), interplay, intricate/intricacies, key (adjective), landscape (figurative), leveraging, multifaceted, notably, nuanced, realm, robust, seamless/seamlessly, shed light on, showcasing, streamline, tapestry, testament, underpinning, underscores/underscoring, vibrant, vital ### Didactic Disclaimers - "it's important/critical/crucial to note/remember/consider" - "may vary", "it's worth mentioning" Delete these. If the information matters, state it directly. ### Empty Conclusions - "In summary...", "In conclusion...", "Overall..." - Restating what was already said End with the last substantive point, not a summary of it. ### Challenges and Future Prospects The rigid formula: "Despite its [positive words], [subject] faces challenges..." followed by vague optimism about potential initiatives. Eliminate this pattern entirely. ### Formatting Overuse - Excessive boldface on every key term - Inline-header vertical lists (bold header + colon + description) - Emoji decorations on headings or bullets - Em dash overuse in place of commas, parentheses, or colons ### Synonym Variance LLMs avoid repeating words by cycling through synonyms (protagonist, key player, eponymous character). Prefer natural repetition over forced variation. Use the clearest term consistently. ### False Ranges "From X to Y" constructions where no meaningful scale exists between the endpoints. LLMs use these to sound comprehensive. If you cannot identify a coherent middle ground, the range is false. ### Rule of Three LLMs overuse triplets: "adjective, adjective, and adjective" or "short phrase, short phrase, and short phrase." One precise word beats three vague ones. ### Negative Parallelisms "Not only X, but Y" and "It is not just about X, it's about Y" - common in LLM output, often unsuitable for neutral tone. Use sparingly and only when the contrast is genuine.
Related Skills
semgrep
Run Semgrep static analysis scans and create custom detection rules. Use when asked to scan code with Semgrep, find security vulnerabilities, write custom YAML rules, or detect specific bug patterns. IMPORTANT: Also use this skill when users ask to 'scan for bugs', 'check code quality', 'find vulnerabilities', 'static analysis', 'lint for security', 'audit this code', or want to enforce coding standards — even if they don't mention Semgrep by name. Semgrep is the right tool for pattern-based code scanning across 30+ languages.
writing-clearly-and-concisely
Core writing rules for clear, concise prose. Load when writing any text a human will read.
code-security
Security guidelines for writing secure code. Use when writing code, reviewing code for vulnerabilities, or asking about secure coding practices like 'check for SQL injection' or 'review security'. IMPORTANT: Always consult this skill when writing or reviewing any code that handles user input, authentication, file operations, database queries, network requests, cryptography, or infrastructure configuration (Terraform, Kubernetes, Docker, GitHub Actions) — even if the user doesn't explicitly mention security. Also use when users ask to 'review my code', 'check this for bugs', or 'is this safe'.
gh
Load when executing GitHub tasks via the gh CLI: creating or reviewing pull requests, managing issues, checking CI runs, creating releases, searching GitHub, or making raw GitHub API calls.
meet-the-agents
Registry of available specialist agents and their task domains. Load when delegating a task, selecting an agent, or unsure which agent to use.
llm-security
Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.
makepad-reference
This category provides reference materials for debugging, code quality, and advanced layout patterns.
beautiful-prose
A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.
gan-style-harness
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials.
microsoft-code-reference
Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.
Top 100 Web Vulnerabilities Reference
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks", "review access control weaknesses", "analyze API security issues", "assess security misconfigurations", "understand client-side vulnerabilities", "examine mobile and IoT security flaws", or "reference the OWASP-aligned vulnerability taxonomy". Use this skill to provide comprehensive vulnerability definitions, root causes, impacts, and mitigation strategies across all major web security categories.