hermes-agent/scripts
Teknium e34a29be56
feat: install skill sets from AI Catalog + agentskills discovery indexes
Prototype of the skill-set layering discussed with agentskills.io:

- AI Catalog (/.well-known/ai-catalog.json) entries typed
  application/agent-skills+json point at an agentskills PR #254
  discovery index and represent an installable skill set.
- The optional io.hermes.skill-set extension carries set-level usage
  intent: a suggested load-alias command and a shared instruction
  preamble. Clients that ignore the extension still install the
  correct set.
- tools/skill_set_catalog.py implements the client: $schema gating,
  required sha256 digest verification, skill-md + archive (.tar.gz/.zip)
  artifacts, and #254 archive-safety rules (traversal/absolute-path/
  link rejection, decompression caps).
- hermes skills install-set <url> installs every member through the
  existing quarantine -> scan -> install pipeline, then creates the
  /<name> skill bundle so the whole set loads in one turn.
- scripts/publish_skill_set.py is the publisher-side counterpart:
  builds the static .well-known tree (catalog + index + artifacts)
  from local skill directories with byte-stable archives.
2026-08-08 10:15:06 -07:00
..
ci fix(ci): follow artifact download redirect without auth 2026-08-05 11:16:18 -04:00
lib
observability
sandbox feat(dev-sandbox): support fake installer / fake main / git clones 2026-08-04 17:36:26 -04:00
tests test(install): exercise 8.3 normalization by running install.ps1, not by parsing it 2026-08-04 15:34:32 -06:00
toolperf_abeval feat(scripts): reproducible core-toolset A/B eval harness (toolperf_abeval) 2026-08-05 13:43:30 -07:00
whatsapp-bridge fix(whatsapp): guard bridge reconnect against hangs and unhandled rejections 2026-08-03 10:03:57 +05:30
LIVETEST_README.md
add_contributor.py
analyze_livetest.py
audit_pr_attribution.py
benchmark_browser_eval.py
build_model_catalog.py
build_skills_index.py
capture-cage-terminal.sh
check-windows-footguns.py
check_subprocess_stdin.py
contributor_audit.py chore: release v0.20.0 (2026.8.3) 2026-08-03 09:57:23 -07:00
dev-sandbox.sh feat(dev-sandbox): support fake installer / fake main / git clones 2026-08-04 17:36:26 -04:00
discord-voice-doctor.py
docker_config_migrate.py
docker_rebootstrap_nous_session.py
generate_conformance_vectors.py
hermes-gateway
install.cmd
install.ps1 fix(install): resolve 8.3 profile aliases so a built desktop app stops reporting failure 2026-08-04 15:34:32 -06:00
install.sh
install_psutil_android.py
iso-certify.py
keystroke_diagnostic.py
kill_modal.sh
lint_diff.py
micro_compaction_report.py
profile-tui.py
publish_skill_set.py feat: install skill sets from AI Catalog + agentskills discovery indexes 2026-08-08 10:15:06 -07:00
release.py chore: map kweiner contributor email 2026-08-08 14:06:30 +05:30
run_tests.sh fix(tests): forward HERMES_TEST_* knobs through the hermetic runner 2026-08-05 19:46:43 -04:00
run_tests_parallel.py
sample_and_compress.py
smoke_nemo_relay_shared_metrics.py Merge updated client resource metrics into active-install metrics 2026-08-04 15:10:41 -07:00
tool_search_livetest.py
tool_search_livetest2.py
tool_search_livetest_ue.py
tool_search_livetest_ue_disc.py
tool_search_livetest_ue_hard.py