
Set up or update a project's context infrastructure for agentic engineering — AGENTS.md as lean hot memory, docs/ as earned warm memory, with signal-to-noise scoring for existing guidance. Use when starting a new project, retrofitting an existing codebase, or auditing current guidance quality.
Analyze and address unresolved feedback on a GitHub pull request. Use when the user has received PR review comments and wants to systematically address each piece of feedback, or when the user mentions PR feedback, review comments, or addressing reviewer concerns.
Collaboratively plan and create well-structured Issues through interactive discussion. Use when the user wants to create an Issue, plan a feature, report a bug, or scope out work for implementation. Supports GitHub, markdown plan/ folder, and other providers.
⚠️ Renamed to forge-implement. This stub exists for migration — remove it and install forge-implement instead.
⚠️ Renamed to forge-reflect. This stub exists for migration — remove it and install forge-reflect instead.
Implement a feature or fix from an Issue, plan file, or free-text description, following project standards. Use when the user wants to start working on an Issue, implement a feature, fix a bug, or build from a plan or roadmap.
Review current changes with a lean review flow. Works on a PR, branch diff, or uncommitted changes. Tiny low-risk diffs stay inline; larger or riskier changes use fresh-context review. Use when the user wants to self-review before committing, pushing, or requesting peer review.
End-to-end implementation and self-review in a single invocation. Implements from an Issue, plan file, or free-text description, then runs a lean fresh-context review. Use when the user wants to implement and review without manual handoff between skills.
Shape a vague idea into a clear plan through codebase investigation and convergent one-at-a-time questioning. Use when the user has a rough idea or problem that needs specifying before issue creation.