glite-arf

Interactively register one or more project metrics in meta/metrics/, grounded in project/description.md. Use during project setup or any time a new measurement needs to be tracked across tasks.

Create a new not-started task folder with task.json and task_description.md. Use when any skill or workflow needs to create a new task.

Run an interactive brainstorming session to review state and choose next actions.

One-shot interactive onboarding for a newly forked Glite ARF template. Shows the safety acknowledgement, installs dependencies, runs doctor.py, chains into create-project-description, provisions the paid services the project declared, then invokes the four meta/ sub-skills. Use once per fork, right after cloning.

Interactively scaffold a new asset type under meta/asset_types/, grounded in project/description.md. Creates a specification.md stub patterned on the built-in asset types. Use during project setup when a custom asset kind is needed; accept "none for now" to skip.

Interactively add one or more entries to meta/categories/, grounded in project/description.md. Use during project setup or any time a new cross-cutting tag is needed.

Interactively add one or more task types to meta/task_types/, grounded in project/description.md. Use during project setup or any time a recurring kind of task needs standardized planning and implementation guidance.

Check a Markdown file against the project markdown style guide and report violations. Use after editing `.md` files or when reviewing markdown quality.

Check a Python file against the project Python style guide and report violations. Use after editing Python files or when reviewing code style.

Verify an ARF skill's structure, shared metadata, symlinks, and markdown quality. Use after creating or updating any skill under `arf/skills/`.

Compare task results against published literature and write the comparison output.

Create a deduplication checkpoint task that scans for duplicate papers and overlapping work. Use when the project needs a new dedup checkpoint.

Guide creation of `project/description.md` and `project/budget.json` for a new or revised ARF project. Use when project goals, scope, or budget need to be defined.

Run an ARF task through all required stages and merge the final PR.

Generate a daily project summary with structured news files. Use when creating the daily digest for a specific date.

Generate follow-up task suggestions from completed task outputs and project context.

Execute `plan/plan.md`, produce assets, and verify results.

Synthesize research outputs into a task plan with steps, costs, risks, and checks.

Review libraries and prior tasks to write implementation-oriented code research.

Conduct structured internet research and write `research/research_internet.md`.

Analyze a completed Claude Code or Codex session (task execution, brainstorm, project-description, or any other skill invocation) and identify self-corrected mistakes, uncorrected mistakes that affected the result, and human interventions, then propose concrete ARF framework improvements. Prints findings to the chat; does not save reports.

Plan and execute a framework change across every related ARF file — specifications, verificators, aggregators, skills, scripts, hooks, tests, materializers, and docs — in a dedicated infrastructure branch and worktree, with style checks and the full test suite. Use whenever anything under `arf/` or generic parts of `meta/` needs to change.

Provision, validate, monitor, and tear down remote GPU machines for task execution. Use when a task needs remote machine setup, monitoring, or teardown.

Download a paper, create metadata assets, and register it in the current task.

Resolve paper identifiers, fetch the PDF and metadata, and prepare inputs for paper asset creation. Use when you need to download a research paper from partial identifiers.

Review downloaded papers and write `research/research_papers.md`.