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-toolsGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.