LangBot Deployment Guide
langbot-app/LangBot
Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.
Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps.
$ npx skills add harness/harness-skills --skill create-pipeline-v1 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install harness/harness-skills create-pipeline-v1 --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/harness/harness-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/create-pipeline-v1 .claude/skills/create-pipeline-v1 && 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 "create-pipeline-v1" agent skill from https://github.com/harness/harness-skills/tree/main/skills/create-pipeline-v1 into .claude/skills/create-pipeline-v1/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-pipeline-v1", 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/harness/harness-skills/tree/main/skills/create-pipeline-v1Type 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 harness/harness-skills --skill create-pipeline-v1 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install harness/harness-skills create-pipeline-v1 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harness/harness-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/create-pipeline-v1 .agents/skills/create-pipeline-v1 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "create-pipeline-v1" agent skill from https://github.com/harness/harness-skills/tree/main/skills/create-pipeline-v1 into .agents/skills/create-pipeline-v1/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-pipeline-v1", 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 harness/harness-skills --skill create-pipeline-v1 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install harness/harness-skills create-pipeline-v1 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harness/harness-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/create-pipeline-v1 .cursor/skills/create-pipeline-v1 && 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 "create-pipeline-v1" agent skill from https://github.com/harness/harness-skills/tree/main/skills/create-pipeline-v1 into .cursor/skills/create-pipeline-v1/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-pipeline-v1", 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/harness/harness-skills.git --path skills/create-pipeline-v1--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 harness/harness-skills --skill create-pipeline-v1 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install harness/harness-skills create-pipeline-v1 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harness/harness-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/create-pipeline-v1 .gemini/skills/create-pipeline-v1 && 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 "create-pipeline-v1" agent skill from https://github.com/harness/harness-skills/tree/main/skills/create-pipeline-v1 into .gemini/skills/create-pipeline-v1/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-pipeline-v1", 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 harness/harness-skills create-pipeline-v1Installs 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 harness/harness-skills --skill create-pipeline-v1 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/harness/harness-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/create-pipeline-v1 .github/skills/create-pipeline-v1 && 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 "create-pipeline-v1" agent skill from https://github.com/harness/harness-skills/tree/main/skills/create-pipeline-v1 into .github/skills/create-pipeline-v1/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-pipeline-v1", 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 harness/harness-skills --skill create-pipeline-v1 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install harness/harness-skills create-pipeline-v1 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harness/harness-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/create-pipeline-v1 .opencode/skills/create-pipeline-v1 && 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 "create-pipeline-v1" agent skill from https://github.com/harness/harness-skills/tree/main/skills/create-pipeline-v1 into .opencode/skills/create-pipeline-v1/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-pipeline-v1", 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.
create-pipeline-v1Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps.
Create Pipeline V1 is an agent skill from harness/harness-skills. Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps. Supports CI stages (run, run-test, background), CD stages (service/environment with action steps for K8s, Helm, ECS), approval (stage-level and inline), parallel execution, matrix/for/while strategies, caching, volumes, and templates. Use when asked for a v1 pipeline, simplified pipeline, new pipeline format, or when user specifically requests v1 syntax. Do NOT use for…
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/native-actions.md` and `references/v1-spec-schema.md`). Compatibility notes: Requires Harness MCP v2 server (harness-mcp-v2)
It sits in DevOps & Cloud, covering Container orchestration and Caching. It works with Kubernetes and Docker. The repository describes itself as: A collection of structured AI agent skills that enable Claude Code, Cursor, GitHub Copilot, and other AI coding assistants to create, operate, debug, and govern Harness CI/CD… The licence is Apache-2.0.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c25faee. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
dockerFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
acme.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires Harness MCP v2 server (harness-mcp-v2)
From compatibility in the SKILL.md frontmatter.
Create Pipeline V1 loads about 3.1k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 172 tokens; SKILL.md has 687 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.
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.
The full file from harness/harness-skills at commit c25faee, republished under its Apache-2.0 licence (© harness). 687 words, ~3,097 tokens.
.claude/skills/create-pipeline-v1/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Generate Harness v1 simplified Pipeline YAML and optionally push to Harness via MCP.
Alpha: This skill is currently in internal testing only.
/create-pipeline) if unclear.references/v1-spec-schema.md for the complete v1 schema, step types, action catalog, and examplesrun: steps. Consult references/native-actions.md for the full mapping. Key rules:template: uses: buildAndPushToDocker / buildAndPushToECR / buildAndPushToGAR (never run: docker build && docker push)action: uses: kubernetes-rolling-deploy or template: uses: k8sRollingDeployStep (never run: kubectl apply)action: uses: helm-deploy or template: uses: helmDeployBasicStep (never run: helm upgrade --install)template: uses: ecsBluegreenDeployStep (never run: aws ecs update-service)template: uses: terraformStep (never run: terraform apply)gitleaksStep, banditStep, sbomOrchestrationStep)template: uses: uploadArtifactsToS3 / uploadArtifactsToGCS (never run: aws s3 cp)approval: uses: harness or approval: uses: jira (never polling scripts)action: uses: jira-create / snow-create (never run: curl)action: uses: http or template: uses: httpStep (never run: curl)run: steps only for custom build/test/lint commands with no native equivalent${{ }} expressions, script field for run steps, and action/template steps for deploymentsharness_create with resource_type pipeline| v0 Syntax | v1 Syntax |
|---|---|
<+variable> expressions | ${{ variable }} expressions |
type: CI / type: Deployment stage types | Flat stages -- no type field |
command: field in Run steps | script: field in run: steps |
Native steps (K8sRollingDeploy, HelmDeploy) | Action steps (action: uses: kubernetes-rolling-deploy) |
failureStrategies: | on-failure: |
HarnessApproval step type | approval: uses: harness (stage-level or inline) |
Deep nesting (spec: execution: steps:) | Flat structure (steps:) |
strategy: matrix: under stage spec | strategy: matrix: directly on stage or step |
pipeline:
name: My Pipeline
repo: # optional: repository config
connector: account.github
name: myorg/my-repo
clone: # optional: clone config
depth: 1
on: # optional: event triggers
- push:
branches: [main]
env: # optional: global env vars
NODE_ENV: production
inputs: # optional: pipeline inputs
branch:
type: string
default: main
stages:
- name: build
steps:
- run:
script: go buildNo version:, kind:, or spec: wrapper -- pipeline: is the root key.
Stages have no type field. Their purpose is determined by their keys.
- name: build
runtime: cloud
platform:
os: linux
arch: arm
cache:
path: node_modules
key: npm.${{ branch }}
steps:
- run:
script: npm ci- name: deploy
service: my-service
environment: staging
steps:
- action:
uses: kubernetes-rolling-deploy
with:
dry-run: false- approval:
uses: harness
with:
timeout: 30m
message: "Approve deployment?"
groups: [admins, ops]
min-approvers: 1Uses script: field (not command: or run:).
# long syntax
- run:
script: npm test
# short syntax
- run: npm test
# with container
- run:
container: node:18
script: npm test
# with shell and env
- run:
shell: bash
script: |
npm ci
npm test
env:
NODE_ENV: test
# with output variables
- id: build
run:
script: echo "TAG=v1" >> $HARNESS_OUTPUT
output: [TAG]- run-test:
container: maven
script: mvn test
report:
type: junit
path: target/surefire-reports/*.xml
splitting:
concurrency: 4Actions replace v0 native steps. See references/v1-spec-schema.md for the full action catalog.
# Kubernetes deploy
- action:
uses: kubernetes-rolling-deploy
with:
dry-run: false
# Helm deploy
- action:
uses: helm-deploy
with:
timeout: 10m
# Terraform plan
- action:
uses: terraform-plan
with:
command: apply
aws-provider: account.aws_connector
# HTTP request
- action:
uses: http
with:
method: GET
endpoint: https://acme.com- background:
container: redis
- run:
script: npm test- template:
uses: account.docker@1.0.0
with:
push: true
tags: latest- approval:
uses: jira
with:
connector: account.jira
project: PROJ# parallel steps
- parallel:
steps:
- run:
script: npm run lint
- run:
script: npm test
# parallel stages
- parallel:
stages:
- steps:
- run: go test
- steps:
- run: npm test
# step group
- group:
steps:
- run:
script: go build
- run:
script: go test# matrix (stage-level)
- strategy:
matrix:
node: [16, 18, 20]
os: [linux, macos]
max-parallel: 3
steps:
- run:
container: node:${{ matrix.node }}
script: npm test
# matrix (step-level)
- strategy:
matrix:
go: [1.19, 1.20, 1.21]
run:
container: golang:${{ matrix.go }}
script: go test# step-level
- run:
script: go test
on-failure:
errors: all
action: ignore # abort, ignore, retry, fail, success
# retry with attempts
- run:
script: go test
on-failure:
errors: [unknown]
action:
retry:
attempts: 5
interval: 10s
failure-action: fail
# stage-level
- steps:
- run:
script: go test
on-failure:
errors: all
action: abort# stage conditional
- if: ${{ branch == "main" }}
steps:
- run:
script: deploy.sh
# step conditional
- if: ${{ branch == "main" }}
run:
script: deploy.shpipeline:
repo:
connector: account.github
name: myorg/my-app
clone:
depth: 1
on:
- push:
branches: [main]
- pull_request:
branches: [main]
stages:
- name: build-and-test
runtime: cloud
platform:
os: linux
arch: arm
cache:
path: node_modules
key: npm.${{ branch }}
steps:
- run:
script: npm ci
- parallel:
steps:
- run:
script: npm run lint
- run-test:
script: npm test
report:
type: junit
path: junit.xml
- action:
uses: docker-build-push
with:
connector: dockerhub
repo: myorg/my-app
tags: [${{ pipeline.sequenceId }}, latest]pipeline:
inputs:
skip_dry_run:
type: boolean
default: false
stages:
- name: deploy-staging
service: petstore
environment: staging
steps:
- action:
uses: manifest-download
- action:
uses: manifest-bake
- action:
uses: kubernetes-rolling-deploy
with:
dry-run: ${{ inputs.skip_dry_run }}
- approval:
uses: harness
with:
timeout: 1d
message: "Approve production deployment?"
groups: [prod-approvers]
min-approvers: 1
- name: deploy-prod
service: petstore
environment: prod
steps:
- action:
uses: manifest-download
- action:
uses: manifest-bake
- action:
uses: kubernetes-rolling-deploy
with:
dry-run: falseharness_list (resource_type: project, org_id) to confirm. If the project does not exist, create it first with harness_create (resource_type: project, body: { identifier, name }) or ask the user.harness_create with the v1 pipeline YAML serialized as a yamlPipeline string in the body. Do not pass a nested JSON pipeline object; it causes serialization errors.Call MCP tool: harness_create
Parameters:
resource_type: "pipeline"
org_id: "<organization>"
project_id: "<project>"
body: { yamlPipeline: "<full v1 pipeline YAML string, including 'pipeline:' root key>" }/create-pipeline-v1
Create a v1 CI pipeline for a Node.js app with caching, parallel lint and test, and Docker push/create-pipeline-v1
Create a v1 Kubernetes deployment pipeline with staging approval and production stages/create-pipeline-v1
Create a v1 pipeline that tests across Go 1.19, 1.20, and 1.21 using matrix strategyreferences/native-actions.md before using a run: step. Native actions provide better error handling, rollback support, and UI integration.references/v1-spec-schema.md for the complete v1 spec before generating YAML.script: field in run steps, never command: or run: as the field name.action: uses: or template: uses: for deployments, never v0 native step types like K8sRollingDeploy.<+...> expressions, no type: on stages, no spec: wrapper.${{ }} syntax before presenting.<+...> instead of ${{ ... }} expressionstype: field on stages (v1 stages have no type)command: or run: as the field name instead of script:version:, kind:, spec: (v1 uses bare pipeline:)K8sRollingDeploy) instead of actions (action: uses: kubernetes-rolling-deploy)failureStrategies: instead of on-failure:harness_list (resource_type: project, org_id). Create it first or confirm org_id/project_id are correct.{ yamlPipeline: "<full v1 pipeline YAML string>" } instead of a nested JSON pipeline object.DUPLICATE_IDENTIFIER — Pipeline exists; use harness_updateINVALID_REQUEST — Check YAML structure matches v1 schema© harness, 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
SKILL.md and 2 other files (references) in skills/create-pipeline-v1 of harness/harness-skills.
Open the folder on GitHubat commit c25faee
Create Pipeline V1 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 |
|---|---|---|---|---|---|---|
| Create Pipeline V1 this skillharness/harness-skills | 115 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| LangBot Deployment Guidelangbot-app/LangBot | 18k | — | ~1.2k | Automated safety check: Notes | Apache-2.0 | |
| Build Openshell Mxc WindowsNVIDIA/OpenShell | 16k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Devopsnicepkg/auto-company | 194 | 2 repos | ~814 | Automated safety check: Pass | MIT | |
| Debug Openshell ClusterNVIDIA/OpenShell | 16k | — | ~19k | Automated safety check: Notes | Apache-2.0 | |
| Deepseek Harness Dockerrunzhliu/deepseek-harness-docker | 110 | — | ~2.7k | Automated safety check: Notes | MIT |
langbot-app/LangBot
Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.
NVIDIA/OpenShell
Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64.
nicepkg/auto-company
Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm).
NVIDIA/OpenShell
Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes.
runzhliu/deepseek-harness-docker
Deploy, configure, verify, upgrade, and troubleshoot DeepSeek Harness with the community Docker, Docker Compose, rootless Podman, and Helm runtime, including the built-in Chromium/noVNC browser…
mondoohq/mql
Deep static code review of an mql provider for logic errors, nil-handling bugs, pagination truncation, caching/id collisions, and other defects that silently give users wrong data.
harness/harness-skills
Generate audit reports and compliance trails using Harness audit trail data via MCP v2 tools.
harness/harness-skills
A skill your agent uses when working with Chaos Engineering steps inside a Harness pipeline.
harness/harness-skills
A skill your agent uses when the user asks to create, edit, update, design, or configure a Harness Chaos Experiment — including faults, probes, actions, experiment YAML, fault injection, pod-delete…
harness/harness-skills
Remove a launched Harness FME feature flag from application code, keeping the treatment FME serves today, and open a pull request.
harness/harness-skills
Configure code scanning in Harness pipelines using STO security scanners.
harness/harness-skills
Generate Harness Agent Template files for AI-powered automation agents.
Works with
Categories
Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps. Create Pipeline V1 is an agent skill from harness/harness-skills. Generate Harness v1 simplified Pipeline YAML using the new concise syntax with flat structure, ${{ }} expressions, script field, and action steps.
Create Pipeline V1 fits situations like: asked for a v1 pipeline; simplified pipeline; new pipeline format; user specifically requests v1 syntax.
Run `npx skills add harness/harness-skills --skill create-pipeline-v1 -a claude-code`. Or copy the skill folder (skills/create-pipeline-v1 in harness/harness-skills) into .claude/skills/create-pipeline-v1 in your project. Claude Code loads it when a task matches its description.
Run `npx skills add harness/harness-skills --skill create-pipeline-v1 -a codex`. Or copy the skill folder (skills/create-pipeline-v1 in harness/harness-skills) into .agents/skills/create-pipeline-v1 in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add harness/harness-skills --skill create-pipeline-v1 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-pipeline-v1, .gemini/skills/create-pipeline-v1, .github/skills/create-pipeline-v1 and .opencode/skills/create-pipeline-v1 in your project.
Going by SKILL.md and its folder, Create Pipeline V1 needs the command-line tools its instructions call (docker). Our summary lists: Node.js; Docker. Compatibility (from SKILL.md): Requires Harness MCP v2 server (harness-mcp-v2).
SKILL.md names 1 domain. In commands or code: acme.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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.
Create Pipeline V1 is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 12k 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 7.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Create Pipeline V1: LangBot Deployment Guide (langbot-app/LangBot, 18k stars), Build Openshell Mxc Windows (NVIDIA/OpenShell, 16k stars), Devops (nicepkg/auto-company, 194 stars) and Debug Openshell Cluster (NVIDIA/OpenShell, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
harness (a GitHub organization) maintains it in harness/harness-skills, which has 115 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 6, 2026.
Source: harness/harness-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.