writing▌

This skill enforces Sentry's blog writing standards across every post — whether you're helping an engineer write their first blog post or a marketer draft a product announcement.

Write user stories with clear acceptance criteria to guide development from the user's perspective. \n \n Provides a structured template covering user role, desired action, business value, and detailed acceptance criteria using Given-When-Then format \n Includes reference guides for story refinement, splitting, estimation, and acceptance criteria examples \n Emphasizes user-focused writing, testability, and small story sizing appropriate for single-sprint completion \n Covers best practices for

Write clear, concise, and helpful interface copy.

Decision tree and templates for building agent skills that agents actually follow. \n \n Provides three architecture tiers based on skill complexity: Tier 1 for simple single-file skills, Tier 2 for multi-concept skills, and Tier 3 for large platforms \n Includes specialized guides for improving existing skills: modularization, anti-rationalization (preventing agent rule-ignoring), and CSO (search optimization for LLM discovery) \n Offers four skill templates covering technique, reference, disci

Structured task planning with clear breakdowns, dependencies, and verification criteria. \n \n Breaks work into small, focused tasks (2-5 minutes each) with one clear outcome and independent verification per task \n Emphasizes project-specific planning over templates, with dynamic content tailored to new projects, feature additions, bug fixes, or refactoring \n Saves plans as markdown files in the project root with slug-based naming (e.g., auth-feature.md ), never in hidden or temp folders \n Re

Detailed implementation planning for multi-step engineering tasks with bite-sized, test-driven steps. \n \n Generates comprehensive plans assuming zero codebase context, breaking work into 2–5 minute tasks following TDD principles (failing test, minimal implementation, passing test, commit) \n Produces structured markdown documents with exact file paths, complete code snippets, and specific shell commands with expected outputs \n Designed for handoff to either subagent-driven execution (fresh ag

Define patterns and messages that trigger contextual warnings or blocks during agent tool use. \n \n Rules are markdown files with YAML frontmatter stored in .claude/hookify.{rule-name}.local.md that match against bash commands, file edits, agent stops, or user prompts \n Supports simple regex patterns or advanced multi-condition rules with operators like regex_match, contains, equals, and starts_with \n Actions include warn (show message, allow operation) or block (prevent operation or stop ses

Framework for defining a single, customer-centric metric that aligns teams and drives product decisions. \n \n Measure value delivered to users, not revenue or internal activity; use proxy metrics like messages sent or nights booked that correlate with long-term outcomes \n Ensure simplicity and universal understanding across the company; avoid composite scores and technical jargon that obscure meaning \n Verify actionability by confirming teams can influence the metric through their work, and a

Framework-driven guidance for writing specs and design documents from seven product leaders. \n \n Determine fidelity level upfront: low-fi sketches for alignment, high-fi specs for implementation details \n Favor prototypes over static documentation; test the feel with real software rather than screenshots \n Use fat marker sketches and breadboarding to avoid getting stuck on UI details like colors or spacing \n Recognize that temporary design shortcuts often become permanent product decisions;

Help teams write focused, actionable product requirements documents using frameworks from 11 product leaders. \n \n Start with problem and context before solutions; include \"why now\" to justify timing and urgency against competing priorities \n Choose the right format for your product type: traditional PRDs for feature specs, prototypes or prompt sets for AI features, executable evals as living requirements \n Define success upfront with clear metrics and outcomes; keep documents lightweight a