CI
aiblueprinthq/ai-blueprint
Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook.
Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag.
Install CI
$ npx skills add openJiuwen-ai/sciencediscovery --skill ci -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery ci --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ci .claude/skills/ci && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ci" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ci into .claude/skills/ci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ci", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ciType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add openJiuwen-ai/sciencediscovery --skill ci -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery ci --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/ci .agents/skills/ci && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ci" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ci into .agents/skills/ci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ci", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openJiuwen-ai/sciencediscovery --skill ci -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery ci --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/ci .cursor/skills/ci && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ci" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ci into .cursor/skills/ci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ci", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/openJiuwen-ai/sciencediscovery.git --path .agents/skills/ci--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openJiuwen-ai/sciencediscovery --skill ci -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery ci --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/ci .gemini/skills/ci && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ci" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ci into .gemini/skills/ci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ci", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install openJiuwen-ai/sciencediscovery ciInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add openJiuwen-ai/sciencediscovery --skill ci -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/ci .github/skills/ci && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ci" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ci into .github/skills/ci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ci", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openJiuwen-ai/sciencediscovery --skill ci -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery ci --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/ci .opencode/skills/ci && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ci" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/.agents/skills/ci into .opencode/skills/ci/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ci", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ci- GitHub stars
- 159
- Token cost
- ~2.2k tokens
- SKILL.md length
- 1,202 words
- Files
- 2 (incl. references)
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag.
- Works in 6 steps: Never weaken a sandbox assertion to make… → Call the pnpm ci:* entry points, never… → UT is one layer. A UT test needing the… → …
- Editing .github/workflows/
- SKILL.md covers What runs where, One plan, three layers, Shared rules and Platform routing, plus 1 more section
- Calls pnpm, node and gh
What it does
CI is an agent skill from openJiuwen-ai/sciencediscovery. Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag. Use when a job fails, when editing .github/workflows/, when asking which layer runs what, when reproducing a pipeline failure locally, or when a job needs the bubblewrap sandbox. Running the layers before proposing a change, and reading the result a proposal receives, belong to create-github-pr.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/github.md`).
It sits in DevOps & Cloud, covering CI/CD and Pull requests. It works with GitHub Actions and GitHub. The repository describes itself as: ScienceDiscovery is an all‑in‑one agentic workbench built specifically for scientific research. The licence is Apache-2.0.
When your agent uses it
- Editing .github/workflows/
- Asking which layer runs what
- Reproducing a pipeline failure locally
- A job needs the bubblewrap sandbox
Example prompts
- “/ci”
Requirements
- Python 3
- Docker
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Never weaken a sandbox assertion to make a pipeline green. Tests that
- Call the pnpm ci:* entry points, never their underlying commands. Do not
- UT is one layer. A UT test needing the sandbox says so with
- Read the failing job log before theorising. If the log is not accessible
- Preserve the real test exit code when adding artifact upload steps. Stage
- Reproduce a pipeline failure with the same layer entry point, on a checkout
What it can do on your machine
Read from SKILL.md and the folder at commit ab1403f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pnpmnodegh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
CI loads about 2.2k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 1,202 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from openJiuwen-ai/sciencediscovery at commit ab1403f, republished under its Apache-2.0 licence (© openJiuwen-ai). 1,202 words, ~2,187 tokens.
Download SKILL.mdSave it as
.claude/skills/ci/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- ci
- description
- Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag. Use when a job fails, when editing .github/workflows/, when asking which layer runs what, when reproducing a pipeline failure locally, or when a job needs the bubblewrap sandbox. Running the layers before proposing a change, and reading the result a proposal receives, belong to create-github-pr.
ScienceDiscovery CI
Project-local skill for ScienceDiscovery.
CONTRIBUTING.md owns the layer entry points
(pnpm ci:ut, ci:st, ci:e2e) and the writable CI_RESULTS_DIR /
CI_RUNTIME_DIR overrides. .ci/README.md documents
the toolchain image and the scheduler's tag catalog. This skill covers what the
pipeline does with those entry points: how to read a run, how to validate a
workflow change, and how to attribute a failure. Running the layers before
proposing a change, and reading what the proposal receives, are in
create-github-pr.
What runs where
Here, the CI e2e layer and pnpm ci:e2e mean the mocked browser subset.
E2E as a validation method also includes user journeys through public API, CLI
and local-stack product entry points; see the
E2E skill. Those journeys have their own documented
driver commands and are not automatically run by the browser layer. Adapter
smokes in ci:st are not E2E merely because they call a model.
GitHub Actions is the only CI, and it is the gate, on the pull request.
gitcode.com is a read-only mirror: nothing runs there and nothing is decided
there. The CodeArts pipeline that used to run on a GitCode merge request, and
the QEMU guest it needed because its pool could not create user namespaces,
were removed — GitHub's ubuntu-latest runs every layer natively. What that
removal cost, and nothing has replaced, is the externally registered code-check
child (SCA, anti-poison, static analysis, blacklist); nothing runs those on a
change today.
One workflow defines the gate. nightly.yml and release.yml are not a second
and third definition: both call ci.yml through workflow_call, so what they
run is the row below, and the reason they exist is in their own file headers.
| Pipeline | Gate | Trigger | Profile | Jobs |
|---|---|---|---|---|
.github/workflows/ci.yml | yes | push to main, pull request, or workflow_dispatch | pr | ci:ut and ci:st (each recording coverage), mocked ci:e2e, Coverage (merges UT's and ST's data, runs nothing), x86_64 + aarch64 release binaries (smoke-gated), the Docker image |
.github/workflows/nightly.yml | — | 16:00 UTC daily, or manual | daily | calls ci.yml, adds real E2E, with a nightly-<date>-<sha> version |
.github/workflows/release.yml | — | push of a version tag | release | calls ci.yml with the tag's version, then publishes if it passes |
The binary and Docker jobs are distribution gates and sit outside the plan: the
four-entry smoke that proves a built binary boots is a job's exit code, not a
planned identity, so planned == executed == passed says nothing about it.
One plan, three layers
ci:ut, ci:st and ci:e2e are not three suites. Each runs
test/support/tagged/shared.mjs against the pr profile in
test/support/tagged/profiles.mjs, narrowed to that layer's category. That
profile is stated as tag dimensions rather than as a selector string, and
pnpm test:policy prints it — read that before theorising about what a job
covers. Each pipeline names its own: a pull request takes pr, nightly.yml
takes daily, and release.yml takes the credential-free release profile
(same policy as pr). Daily adds the disjoint e2e-real slice. The job passes it as an
argument, so the command in the log is the command that reproduces the run.
The three hermetic groups partition the PR plan, so these layers together run exactly
pnpm test:shared, the command a developer runs locally.
What this means when reading a failure: selection comes from the tags in each
test's source and from nothing else. A job's credentials, devices, installed
services and CI_* variables cannot add a case or remove one — a missing
capability fails the plan's preflight instead, before any test body runs. A
skipped case is a failed run. So "the layer passed but ran fewer tests" is not
a possible outcome any more; node .ci/tagged-summary.mjs fails the job unless
planned == executed == passed, including when no plan was produced at all.
Real E2E runs only in daily CI with explicit credentials. Live ST, NPU, legacy and macOS work is tagged out of the shared selector and
keeps its own opt-in entry points; test/support/tagged/MIGRATION.md is the
ledger of what is in and what is out.
Show full SKILL.md (563 more words)Show less
Shared rules
- Never weaken a sandbox assertion to make a pipeline green. Tests that
assert isolation or the sandbox's
/workspaceview must run on a host where bubblewrap can create namespaces. Every job that needs it installs bubblewrap and clearskernel.apparmor_restrict_unprivileged_usernsbefore using it. - Call the
pnpm ci:*entry points, never their underlying commands. Do not create a second test definition, and do not add a list of cases beside the tags:pnpm ci:catalog:checkfails a layer that runs anything other than a slice of the shared plan, an entry point that drifts off that slice, and a package test file that sits outside the collection patterns the plan is built from.pnpm ci:selftestis that guard's regression suite.pnpm test:run --<group> <value>builds its own selector from the tag vocabulary and can therefore reach outside the shared plan. That is the developer entry point; CI uses--slice, which is appended to the shared selector withandand is always a subset of it. Do not put a query in a workflow. - UT is one layer. A UT test needing the sandbox says so with
sandbox:bubblewrap, which the plan turns into a preflight the whole run fails on; it does not move the test to a different job. Do not add aci:ut:*entry point besideci:ut. - Read the failing job log before theorising. If the log is not accessible with the available credentials, ask for it instead of inferring the failure from a status badge.
- Preserve the real test exit code when adding artifact upload steps. Stage the result, upload diagnostics, then restore that exit code.
- Reproduce a pipeline failure with the same layer entry point, on a checkout
of the commit the run tested, with
CI_RESULTS_DIR/CI_RUNTIME_DIRpointed somewhere writable. Each layer leavesrun.logand a summary underCI_RESULTS_DIR/<layer>/, and its frozen plan underCI_RESULTS_DIR/<layer>/tagged/.
Platform routing
For .github/workflows/, GitHub-hosted runner behavior, gh run, or GitHub
artifacts, read references/github.md completely before
acting.
Common failure signals
| Symptom | Meaning |
|---|---|
bwrap: No permissions to create new namespace | The host forbids user namespaces. On Ubuntu 24.04 that is the AppArmor restriction the jobs clear with sysctl kernel.apparmor_restrict_unprivileged_userns=0; do not weaken Runner tests instead. |
| Playwright is green with fewer tests than expected | A skip is not a pass, and the plan already says so. Read <CI_RESULTS_DIR>/e2e/tagged/summary.json: it names every planned journey that did not report one. |
EMPTY_SELECTION, EMPTY_MODULE or COLLECTION_DRIFT | A collection problem, not a product failure. The plan is frozen from source, so a selector that matches nothing, a module that registers no test, and a source that changed between freezing and running are all failures of the run. |
PREPARATION_FAILED | The shared runner's own setup — install, build, the five service virtualenvs, the pinned Chromium — did not complete. The message names the log to read; nothing was collected yet, so this is never a product assertion. |
API test expects runner_exec, gets undefined | An execution never ran; check sandbox availability first. |
BLOCKED: isolated E2E stack did not become healthy | The Runner refused to serve; inspect the sandbox probe before application logs. |
ERR_PNPM_OUTDATED_LOCKFILE | pnpm-lock.yaml is behind a package.json; regenerate it with pnpm install --lockfile-only. |
| The E2E job spends its first minute downloading conda packages | Expected. E2E_SCIENTIFIC_ENVS=1 provisions the managed Python base so the environment journey runs instead of reporting a skip; it is about 330 MB on a runner with no cache. |
© openJiuwen-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in .agents/skills/ci of openJiuwen-ai/sciencediscovery.
- SKILL.md
- references/github.md
Open the folder on GitHubat commit ab1403f
Compare with similar skills
CI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| CI this skillopenJiuwen-ai/sciencediscovery | 159 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| CIaiblueprinthq/ai-blueprint | 463 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Michel Monitor Pull Request GitHub ActionsPackmindHub/packmind | 318 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Diy Netlifyswyxio/skills | 176 | — | ~1.1k | Automated safety check: Pass | MIT | |
| ONNX Runtime CI Managementmicrosoft/onnxruntime | 22k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Renovate Actions PR Reviewbacknotprop/plannotator | 9.3k | — | ~640 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Michel Monitor Pull Request GitHub Actions
PackmindHub/packmind
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment.
Diy Netlify
swyxio/skills
Build or audit an isolated Netlify/Vercel-style pull-request preview workflow using GitHub Actions and the project's existing hosting provider.
- Official
ONNX Runtime CI Management
microsoft/onnxruntime
Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.
Renovate Actions PR Review
backnotprop/plannotator
Reviews Renovate pull requests that bump GitHub Actions by checking pinned SHAs against upstream tags, scanning changelogs and confirming workflows stay compatible.
GitHub Actions Workflow Automation
ruvnet/agentic-flow
Generates and optimizes GitHub Actions workflows with swarm coordination, using named modes for PR management, issue tracking, releases and repository structure.
More from openJiuwen-ai/sciencediscovery
All 23 skills in this repoCode Engineer
openJiuwen-ai/sciencediscovery
A skill your agent uses when you need to write and execute Python/R code to process, transform, and analyze data, delivering reproducible computational results with complete code-level methodology…
Gitcode
openJiuwen-ai/sciencediscovery
Operate GitCode issues, PRs, wikis, code/MR refs, and cached org templates.
Structure Pocket Inspection
openJiuwen-ai/sciencediscovery
Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center.
Antibody Design
openJiuwen-ai/sciencediscovery
Prepare, launch, monitor, and summarize the real RFdiffusion to ProteinMPNN to Protenix antibody pipeline on a local or remote ScienceDiscovery Runner with sandboxed Ascend NPUs.
Science Research Team
openJiuwen-ai/sciencediscovery
A skill your agent uses to orchestrate a multi-domain research team for literature/evidence research and data analysis.
Literature Searcher
openJiuwen-ai/sciencediscovery
A skill your agent uses when a research workflow needs verified academic source retrieval through literature-search MCP interfaces available in the current session before evidence extraction.
Related
Works with
Categories
Questions about CI
What does CI do?
Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag. CI is an agent skill from openJiuwen-ai/sciencediscovery. Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag.
When should I use CI?
CI fits situations like: editing .github/workflows/; asking which layer runs what; reproducing a pipeline failure locally; A job needs the bubblewrap sandbox.
How do I install CI in Claude Code?
Run `npx skills add openJiuwen-ai/sciencediscovery --skill ci -a claude-code`. Or copy the skill folder (.agents/skills/ci in openJiuwen-ai/sciencediscovery) into .claude/skills/ci in your project. Claude Code loads it when a task matches its description.
How do I install CI in Codex?
Run `npx skills add openJiuwen-ai/sciencediscovery --skill ci -a codex`. Or copy the skill folder (.agents/skills/ci in openJiuwen-ai/sciencediscovery) into .agents/skills/ci in your project. Codex loads it when a task matches its description.
Can I use CI in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openJiuwen-ai/sciencediscovery --skill ci -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ci, .gemini/skills/ci, .github/skills/ci and .opencode/skills/ci in your project.
What does CI need to run?
Going by SKILL.md and its folder, CI needs the command-line tools its instructions call (pnpm, node and gh). Our summary lists: Python 3; Docker.
Does CI access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is CI safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does CI use?
CI is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does CI use?
About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 837 tokens, read only when the agent opens those files.
What are the alternatives to CI?
Skills that share tags, products or a category with CI: CI (aiblueprinthq/ai-blueprint, 463 stars), Michel Monitor Pull Request GitHub Actions (PackmindHub/packmind, 318 stars), Diy Netlify (swyxio/skills, 176 stars) and ONNX Runtime CI Management (microsoft/onnxruntime, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains CI?
openJiuwen-ai (a GitHub organization) maintains it in openJiuwen-ai/sciencediscovery, which has 159 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 10, 2026.
Source: openJiuwen-ai/sciencediscovery on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.