deploy
Skill0 starsChanged 4 months agoMITView on GitHub
Use only for a human-requested deployment after QA PASS and review APPROVE have been recorded.
155 other projects use a version of this.
Adopted by
Most recently taken up by
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 8, 2026
- KingKongRobotics/jumpertheir own version, first seen Nov 8, 2026
- stakeme-team/arc-agent-kittheir own version, first seen Nov 8, 2026
- dockhold/mcptheir own version, first seen Nov 8, 2026
- KhaiTrang1995/nexus-kbtheir own version, first seen Nov 8, 2026
- ribato22/vibechecktheir own version, first seen Nov 8, 2026
Used with
Projects with it also use pm-discovery, qa-phase and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ww-w-aiSkillpm-discovery
PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.
Also in 3 projects that use this
- ww-w-aiSkill
qa-phase
Run QA tests at various levels (L1-L5) for features under PDCA management. Integrates with MCP tools to execute structured test plans.
Also in 3 projects that use this
- +10 more from ww-w-ai
Other versions155 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 155
- ok-oldking/ok-wuthering-waves★ 8.6ksame name
- memovai/mimiclaw★ 5.8ksame name
- KingKongRobotics/jumper★ 3.1ksame name
- jhd3197/ServerKit★ 1.8ksame name
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- mattmireles/gemma-tuner-multimodal★ 1.5ksame name
- microsoft/power-platform-skills★ 1.1ksame name
- jazzyalex/agent-sessions★ 941same name
- awslabs/agent-plugins★ 918same name
- patrickjaja/claude-desktop-extra★ 734same name
145 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- branch-safelySkill
- deployment-decisionsSkill
- deploy-vercelSkill
- deploy-vpsSkill
- documentationSkill
- e2e-testingSkill
- feature-testingSkill
- monitoringSkill
- orchestrateSkill
- quality-reviewSkill
- requirements-gatheringSkill
- solution-designSkill
- task-breakdownSkill
- ui-uxSkill
- unit-testingSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 139 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before anything else, confirm all three:
- Distinctive: line 18
If any is missing, stop and tell the user what is missing.
- Very specific: line 22
Read .agents/skills/deploy-project/SKILL.md if it exists.
- Distinctive: line 24
If it exists and looks correct: use it.
- Very specific: line 25
If it does not exist: load deployment-decisions and guide the user through choosing and setting up a deployment process.
- Distinctive: line 29
Run the project build first.
- Distinctive: line 31
Never print, copy, log, or report tokens, passwords, or API keys.
- Distinctive: line 32
Never deploy to production without explicit human approval.
- Distinctive: line 37
If the deployment failed, diagnose the specific step before suggesting fixes.
- Very specific: line 38
Ask the user if they want to set up monitoring (load monitoring skill).
“Common” is measured: kept by at least 6 in 10 of the 139 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Deploy
Guide the user through deploying. Do not assume they know how. Do not handle credentials directly.
Gate check
Before anything else, confirm all three:
- Explicit human deployment request.
qa-report.mdsaysPASS(orPASS_WITH_NOTESwith the limitation noted).review.mdsaysAPPROVE.
If any is missing, stop and tell the user what is missing. Do not proceed.
Check for an existing deployment process
Read .agents/skills/deploy-project/SKILL.md if it exists. This is a project-level deployment skill saved from a previous run or set up manually.
- If it exists and looks correct: use it. Tell the user what you are about to do and run the deployment. Report the result.
- If it does not exist: load
deployment-decisionsand guide the user through choosing and setting up a deployment process.
During deployment
- Run the project build first. Report success or failure. Do not proceed to deploy if the build fails.
- For commands that need credentials (pushing to a remote, deploying to a service): use the project's established CLI method. Prefer
ghCLI when available (already authenticated). If a service CLI is needed, ask the user to runservice loginfirst, then continue. - Never print, copy, log, or report tokens, passwords, or API keys.
- Never deploy to production without explicit human approval.
After deployment
- Report the deployment URL or confirmation evidence from the provider.
- If the deployment failed, diagnose the specific step before suggesting fixes.
- Ask the user if they want to set up monitoring (load
monitoringskill). - Save the deployment process to
.agents/skills/deploy-project/SKILL.mdif one was created during this run, so future deployments skip the decision phase.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.