roadmap-communicator
Use when preparing roadmap narratives, release notes, changelogs, or stakeholder updates tailored for executives, engineering teams, and customers.
Works with
--- name: roadmap-communicator description: Use when preparing roadmap narratives, release notes, changelogs, or stakeholder updates tailored for executives, engineering teams, and customers. license: MIT --- # Roadmap Communicator Create clear roadmap communication artifacts for internal and external stakeholders. ## When To Use Use this skill for: - Building roadmap presentations in different formats - Writing stakeholder updates (board, engineering, customers) - Producing release notes (user-facing and internal) - Generating changelogs from git history - Structuring feature announcements ## Roadmap Formats 1. Now / Next / Later - Best for uncertainty and strategic flexibility. - Communicate direction without false precision. 2. Timeline roadmap - Best for fixed-date commitments and launch coordination. - Requires active risk and dependency management. 3. Theme-based roadmap - Best for outcome-led planning and cross-team alignment. - Groups initiatives by problem space or strategic objective. See `references/roadmap-templates.md` for templates. ## Stakeholder Update Patterns ### Board / Executive - Outcome and risk oriented - Focus on progress against strategic goals - Highlight trade-offs and required decisions ### Engineering - Scope, dependencies, and sequencing clarity - Status, blockers, and resourcing implications ### Customers - Value narrative and timing window - What is available now vs upcoming - Clear expectation setting See `references/communication-templates.md` for reusable templates. ## Release Notes Guidance ### User-Facing Release Notes - Lead with user value, not internal implementation details. - Group by workflows or user jobs. - Include migration/behavior changes explicitly. ### Internal Release Notes - Include technical details, operational impact, and known issues. - Capture rollout plan, rollback criteria, and monitoring notes. ## Changelog Generation Use: ```bash python3 scripts/changelog_generator.py --from v1.0.0 --to HEAD ``` Features: - Reads git log range - Parses conventional commit prefixes - Groups entries by type (`feat`, `fix`, `chore`, etc.) - Outputs markdown or plain text ## Feature Announcement Framework 1. Problem context 2. What changed 3. Why it matters 4. Who benefits most 5. How to get started 6. Call to action and feedback channel ## Communication Quality Checklist - [ ] Audience-specific framing is explicit. - [ ] Outcomes and trade-offs are clear. - [ ] Terminology is consistent across artifacts. - [ ] Risks and dependencies are not hidden. - [ ] Next actions and owners are specified.
More Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

