94.8K skills · sorted by popularity
Turn notes, fragments, or transcripts into an article through a paragraph-by-paragraph discussion. Compare opening options, establish what readers need to know, and save agreed sections in a separate document while preserving the original material.
Review code changes from a chosen Git reference against two separate criteria: documented coding standards and the original requirements. Independent reviewers check each criterion, then present findings separately so convention problems and requirement gaps remain visible.
Explore a writing topic through probing questions and collect promising sentences, anecdotes, metaphors, and unfinished thoughts. It saves these fragments in a single Markdown file, giving you raw material to develop before deciding on an outline.
Plan work too large for one agent session by mapping decisions and their dependencies in an issue tracker. Resolve questions one at a time, preserve the reasoning, and identify what must be settled before execution can begin.
Set up automated checks before each Git commit using Husky and lint-staged. Format staged files with Prettier, run existing type checks and tests, and verify the setup using the repository's package manager.
Prepare a repository for engineering skills by documenting where issues are tracked, which triage labels organize incoming work, and where glossaries and architecture decision records belong. Review the existing setup and confirm drafts before writing configuration files.
Investigate difficult bugs and performance slowdowns by building a repeatable test or script that detects the exact symptom. Reduce the failing case, compare possible causes, and verify the fix with checks that catch the bug if it returns.
Create and edit documents that AI agents follow, including skills and project instructions. Organize steps and reference material, define clear completion criteria, and refine document links and wording to reduce duplication and unnecessary context.
Ask the agent to explain its last message again with some context. The revised explanation uses ASD-STE100, a simplified technical English standard, and the vocabulary defined in the project's glossary.
Turn a decision that needs someone else’s knowledge into a Markdown questionnaire. Clarify who will answer and what information is needed, then create prioritized questions with answer spaces for asynchronous replies or a meeting.
Write a pull request description that helps reviewers understand a code change. Use a compact diagram or diff, show before-and-after evidence, and explain how reversible the change is and what areas it may affect.
Turn a specification and its tickets into code by coordinating multiple agents around task dependencies. Combine their work on one integration branch, use test-driven development, review the result, and close tickets through the issue tracker’s workflow.
Turn plans, specifications, or conversations into small development tickets that each deliver verifiable behavior. Identify which tickets must finish first, review the breakdown together, and publish approved tickets to local files or the configured issue tracker.
Summarize the current conversation into a handoff document so another agent can continue the work. Reference existing project materials, suggest skills for the next session, and redact sensitive information.
Review a coding session and identify improvements to the agent’s working environment. Examine file navigation, automated checks, instructions, tool use, and information access, then present proposed changes in order of severity.
Build features or fix bugs by writing one failing test, then the smallest implementation that passes it. Tests check behavior through public interfaces, the entry points callers use, so they remain useful when internal code changes.
Design modules that offer substantial behavior through a small interface, the rules callers must understand. Use shared design terms to simplify usage, contain complexity, choose where implementations can vary, and make behavior easier to test.
Inventory existing tests and identify gaps. Link requirements, business rules, risks, and bugs to stable test identifiers and executable evidence, maintaining a test registry that shows what is covered and what still needs verification.
Organize feature development using files in the repository. Break larger goals into user stories, assign them to sprints, guide implementation and review, and track progress through confirmed merges without an external project management tool.
Check skills before distributing them to Codex or Cursor. Identify unsupported metadata fields, Claude-specific variables in shell examples, and inconsistencies between source skills and their installation copies using the project's compatibility checker.
Track module dependencies and verification commands in REGRESSION.md. After a change, check the affected module and downstream consumers, then report command exit codes as evidence that existing behavior still works or needs attention.
Set up Everything Claude Code skills and hooks in DeepSeek Harness. Covers linking skill folders, generating hook settings, checking that hooks run, updating the setup, and investigating missing skills or inactive hooks.
Maintain clear business definitions and relationships in an existing glossary or CONTEXT.md. Flag unresolved meanings and refer lasting design choices to the existing architecture decision record workflow, keeping terminology separate from decision rationale and task status.
Map the impact of a proposed change using real dependencies and project documentation. Identify affected code, data, interfaces, tests, and release steps, then compare the implemented changes with the plan to expose gaps and unverified risks.