From asta-tools
Use this skill to export and open A2A agent task outputs — "export the task results", "convert the task output to HTML", or work with the structured artifacts produced by an A2A agent task run.
How this skill is triggered — by the user, by Claude, or both
Slash command
/asta-tools:artifactsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
[Artifacts](https://a2a-protocol.org/latest/specification/#artifacts) are the structured outputs produced by A2A agents. They accumulate in the `artifacts[]` field of the task response.
Artifacts are the structured outputs produced by A2A agents. They accumulate in the artifacts[] field of the task response.
# 1. Dump task result
TASK_DIR=$(mktemp -d)
asta <agent> task "<TASK_ID>" > "$TASK_DIR/task.json"
# 2. Export (caller decides output dir and format)
asta artifacts --input "$TASK_DIR" --output "$OUT_DIR" --format md
Produces per-artifact files organized by subtype, plus index.md, references.bib, and manifest.json.
Works on partial task data too — useful for previewing mid-run.
--format md — markdown, one .md per artifact. Cross-artifact links use relative .md paths. Best for LLM consumption, version control, and indexing into asta-documents.--format html — self-contained HTML with index.html. Open with open "$OUT_DIR/index.html". Best for reading or sharing.When another skill hands off to this one to export a run, default to writing under:
.asta/<invoking-skill>/<slug>/
Where <slug> is YYYY-MM-DD-<short-query-slug> — date-first for
chronological ordering, short-slug derived from the primary input (query,
topic, etc.). Register the exported artifacts with asta-documents into a
single per-skill aggregate index at .asta/<invoking-skill>/index.yaml so
consumers can search across all runs.
Example (theorizer run):
.asta/generate-theories/2026-04-17-media-polarization/ # per-run outputs
.asta/generate-theories/index.yaml # aggregate index
After export, read manifest.json and register each entry with asta documents add. Each manifest entry has: name, description, filename, mime_type, and optionally subtype and metadata. Map these directly to:
file://<absolute-path-to-OUT_DIR>/<filename> as the URL--name from name--summary from description (fall back to name)--mime-type from mime_type--tags from subtype if present--extra from metadata as JSON if presentUse --root <dir> to target a scoped index (e.g. per-agent) instead of the default .asta/documents/.
npx claudepluginhub allenai/asta-plugins --plugin asta-toolsCreates and manages autonomous AI agent tasks via the Manus API. Supports task creation, polling, status tracking, and downloading output files.
Provides standardized Markdown templates for research, planning, implementation, and review agent outputs. Use when generating or parsing agent responses in autonomous dev workflows.
Converts markdown to DOCX, PPTX, XLSX, and PDF office documents for exportable deliverables from knowledge work outputs.