Skip to main content

Deterministic runtime for invest-wiki agent skills

Project description

invest-llm-wiki

Chinese-first md-first investment research wiki skills for Claude Code, Codex, and OpenClaw.

What this repo is

invest-llm-wiki is a versioned skill-pack repository, not an application SDK. The repository currently contains the canonical skill catalog, agent-facing adapter readmes / manifests, the PyPI package source for invest-wiki-runtime, preset/docs scaffolding, and contract tests around those surfaces.

Compatibility

  • Claude Code
  • Codex
  • OpenClaw

Language

The main skill authoring language is Chinese-first. This English README exists for open-source discoverability.

For AI Agents

Use these entry points depending on the task:

Install the packaged skills with:

npx skills add xdsjs/invest-llm-wiki

Or install only what you need:

npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-dossier
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-ingest
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-right-business
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-right-people
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-right-price
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-article
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-lint
npx skills add xdsjs/invest-llm-wiki --skill invest-wiki-query

Install the matching runtime version:

python3 -m pip install -U invest-wiki-runtime==0.1.0

Run the runtime directly from the skill:

python3 -m invest_wiki_runtime config get-root
python3 -m invest_wiki_runtime config set-root --root /absolute/path
python3 -m invest_wiki_runtime dossier run --ticker STZ

The runtime root config file still lives at ~/.config/invest-llm-wiki/config.toml. Skills guide the agent through config get-root / config set-root, then execute the relevant business command. Repo tags, skill docs, and the PyPI runtime version stay strictly aligned.

For repository maintainers, scripts/sync/sync_surfaces.py and scripts/verify/verify_repo.py still exist to refresh adapter manifests and verify the committed repo surface; they are not developer installation entrypoints.

The investment-research preset is documented here as a contract, not as an installed runtime pack. It describes the file and workflow boundaries that the skill pack should satisfy.

Planned preset shape

The later investment-research preset is intended to cover:

  • invest-wiki-dossier
  • invest-wiki-ingest
  • invest-wiki-right-business
  • invest-wiki-right-people
  • invest-wiki-right-price
  • invest-wiki-article
  • invest-wiki-lint
  • invest-wiki-query

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

invest_wiki_runtime-0.1.0.tar.gz (66.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

invest_wiki_runtime-0.1.0-py3-none-any.whl (60.3 kB view details)

Uploaded Python 3

File details

Details for the file invest_wiki_runtime-0.1.0.tar.gz.

File metadata

  • Download URL: invest_wiki_runtime-0.1.0.tar.gz
  • Upload date:
  • Size: 66.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for invest_wiki_runtime-0.1.0.tar.gz
Algorithm Hash digest
SHA256 cc5105b702a6ee799e102a8b1bb379b673a05348a26c8857f5b6e6ff88c9bc22
MD5 bdea16e49fd50d8e0256f482d5aed689
BLAKE2b-256 b4589edfd80a39d0e4361101e031ced957a35e9fd6820a546e8adef0e319c05d

See more details on using hashes here.

Provenance

The following attestation bundles were made for invest_wiki_runtime-0.1.0.tar.gz:

Publisher: publish-runtime.yml on xdsjs/invest-llm-wiki

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file invest_wiki_runtime-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for invest_wiki_runtime-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 460922775c31ae8a6b1f5e1a81683cc7d500823f9f68574ac850fe86aadd0fbd
MD5 621f01f40ed0de94c91f2c19d1b179f6
BLAKE2b-256 dc68be61004e350fe11de6dbb6bbc194f31f7739028f3588c21c5775f6d28ab7

See more details on using hashes here.

Provenance

The following attestation bundles were made for invest_wiki_runtime-0.1.0-py3-none-any.whl:

Publisher: publish-runtime.yml on xdsjs/invest-llm-wiki

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page