AI Skill Directory

This skill writes ad headlines, supporting lines, and main body copy for paid placements and keeps each line inside the target platform's character limits. It can start from a blank brief, rework copy using past performance numbers, or produce large static batches. Platform specs cover Google responsive search, Meta, LinkedIn, TikTok, and X.

This skill packages a customer problem for the engineering team, product managers, or company leaders. The brief states the impact, describes the issue, lists what support already tried, gives reproduction steps for bugs, and says what is needed. It fits cases with repeated reports, a churn threat, or a missed SLA.

Anthropic's runbook skill, from its operations plugin, documents a recurring task so on-call or ops staff can repeat it reliably. It records the purpose, prerequisites, exact commands step by step, how to confirm it worked, troubleshooting, how to roll back and who to escalate to. It can also update an existing runbook.

Anthropic's ux-copy skill, from its design plugin, writes or critiques the short text inside a product. It covers button and link labels, error messages, empty screens, confirmation dialogs, tooltips, loading states and onboarding lines, following stated principles and patterns for each. Give it the context and any existing copy, and it suggests clearer wording.

Anthropic's sql-queries skill, from its data plugin, is reference guidance for writing correct and efficient SQL. It notes differences between PostgreSQL, Snowflake, BigQuery, Redshift and Databricks and shows common patterns such as window functions, CTEs and cohort retention. The model uses it automatically when it writes, speeds up or converts queries.

This skill writes cold email campaigns by confirming each decision with you before it produces final copy. It moves through four steps: campaign direction, subject lines and the opening-line approach, body structure, and then the full set of variants and follow-ups. At each step it offers two or three options with a recommendation, and it can start from a strategy document, a website, client notes or past campaign results. Three first-line approaches are built in, including one that uses public data to point out a visible problem.

This skill creates and edits notes in Obsidian's flavor of Markdown. It handles wikilinks, embeds, callouts, frontmatter properties, tags, and comments, along with math, Mermaid diagrams, and footnotes.

This skill writes one ready-to-paste prompt for a named AI tool, such as an LLM, Cursor, Midjourney, or a video generator. It confirms the target tool when that is unclear, pulls the task, output format, constraints, and audience out of a rough idea, and asks at most three clarifying questions. It prefers simple techniques over those that raise the risk of invented content, and never asks a model to reveal hidden reasoning. The result is a single prompt block with a one-line note on what was optimized.

This skill writes fiction chapters in an outline-first order. It gathers context for the chapter with a story command-line tool that keeps later chapters out and stays within a token budget, builds a scene-by-scene outline for your approval, and only then writes the full prose. Afterward it records scene dates, continuity state and setups planted or paid off, and rebuilds the project's registries. It expects a story bible plus a character file or more, and ideally a plot structure, and it passes line editing to a companion skill.

Anthropic's process-doc skill, from its operations plugin, captures how a piece of work really gets done when it mostly lives in one person's head. It produces a flowchart, a RACI chart showing who is responsible, accountable, consulted and informed, and a written standard operating procedure. It also records exceptions and edge cases, which helps with handoffs and audits.

Assembles raw writing material into a journey of beats, grounding terms before each beat lands.

Writes instructions, docs, and prompts that agents can follow reliably without ambiguity.

Mines raw writing fragments without forcing structure—explore before you shape.

Applies Vercel writing guidelines so product UI copy and docs stay clear and consistent.

Writes clear implementation plans before coding so agents and humans share the same approach.

Shapes raw writing material into a polished article paragraph by paragraph.

Authors high-quality agent skills (SKILL.md) with clear triggers, steps, and evaluation habits.

Creates, edits, analyzes, and visualizes Excel/spreadsheet files with formulas and structure.

Stages, commits, pushes, and opens a GitHub pull request in one explicit `gh` CLI flow.