Loading...
Loading...
Found 2,007 Skills
Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"
Set a tracking document as the source of truth for the current feature or task. Use when starting work on a feature, bug fix, or multi-step task that benefits from a persistent record of decisions, discoveries, and progress. Keeps the document updated as work proceeds.
Mandatory unless the user explicitly opts out. Use when non-trivial work on features, bug fixes, refactorings, or changes to code, tests, configuration, dependencies, runtime assets, or design requires explicit planning before implementation.
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Write a structured incident postmortem or post-incident review. Use when asked to write a postmortem, incident report, P1/P2 review, outage report, or RCA (root cause analysis). Generates a blameless postmortem with timeline, root cause, contributing factors, impact summary, and action items.
Create PRDs through the gather-criticize loop, sync existing PRDs, push amendments, and check PRD status.
Generate a high-level overview of a file, directory, or project — answering "what is this and how is it organized." Produces a single summary entry covering purpose, structure, entry points, and dependencies. Re-running on the same target overwrites the existing overview.
Analyze existing code to generate structured learning entries documenting patterns, decisions, and concepts. Works on files, directories, or entire projects. Supports selective (3-5 per file) and exhaustive modes, plus source annotations for fine-grained control.
Log genuine, recurring repository friction to .agents/PAPERCUTS.md — confusing setup, a flaky repo command or script, a misleading in-repo error, stale generated files, or a non-obvious gotcha that will cost the next contributor time. Also use to review, deduplicate, and resolve existing entries. Gate hard before logging: only friction the repository itself can fix counts. Never log the agent's own sandbox/permission errors, shell-scripting mistakes, transient flakiness, or third-party tool quirks the repo can't change.
Convert PRD to structured task list with automatic linking
Research, discuss, and write specs. Use this when creating or refining specs.
ADR format and methodology for documenting significant technical decisions with context, alternatives considered, and consequences. Use when making or documenting architectural decisions.