Use Vercel Action
amondnet/vercel-action
Wire amondnet/vercel-action into a GitHub Actions workflow to deploy Vercel projects from CI.
The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident.
Install Learnings
$ npx skills add kortix-ai/suna --skill learnings -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kortix-ai/suna learnings --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/kortix-ai/suna.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/learnings .claude/skills/learnings && 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 "learnings" agent skill from https://github.com/kortix-ai/suna/tree/dev/.agents/skills/learnings into .claude/skills/learnings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learnings", 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/kortix-ai/suna/tree/dev/.agents/skills/learningsType 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 kortix-ai/suna --skill learnings -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kortix-ai/suna learnings --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kortix-ai/suna.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/learnings .agents/skills/learnings && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "learnings" agent skill from https://github.com/kortix-ai/suna/tree/dev/.agents/skills/learnings into .agents/skills/learnings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learnings", 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 kortix-ai/suna --skill learnings -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kortix-ai/suna learnings --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kortix-ai/suna.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/learnings .cursor/skills/learnings && 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 "learnings" agent skill from https://github.com/kortix-ai/suna/tree/dev/.agents/skills/learnings into .cursor/skills/learnings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learnings", 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/kortix-ai/suna.git --path .agents/skills/learnings--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 kortix-ai/suna --skill learnings -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kortix-ai/suna learnings --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kortix-ai/suna.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/learnings .gemini/skills/learnings && 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 "learnings" agent skill from https://github.com/kortix-ai/suna/tree/dev/.agents/skills/learnings into .gemini/skills/learnings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learnings", 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 kortix-ai/suna learningsInstalls 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 kortix-ai/suna --skill learnings -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kortix-ai/suna.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/learnings .github/skills/learnings && 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 "learnings" agent skill from https://github.com/kortix-ai/suna/tree/dev/.agents/skills/learnings into .github/skills/learnings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learnings", 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 kortix-ai/suna --skill learnings -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kortix-ai/suna learnings --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kortix-ai/suna.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/learnings .opencode/skills/learnings && 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 "learnings" agent skill from https://github.com/kortix-ai/suna/tree/dev/.agents/skills/learnings into .opencode/skills/learnings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learnings", 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
learnings- GitHub stars
- 20k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 535 words
- Files
- 656 (incl. scripts)
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident.
- Works in 2 steps: Search the index and the full text for… → Read every matching entry in full. Obey…
- Tasks that involve Incident response
- SKILL.md covers Recall: before you touch a…, Record: after an incident or… and Ledger rules
- Tasks that involve Database migrations
What it does
Learnings is an agent skill from kortix-ai/suna. The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident. Load WHENEVER you write or review a DB migration or schema change, touch deploy/release workflows (.github/workflows/deploy-, promote.yml, vercel config), plan a promote/release, respond to a prod incident, or when another skill references a learning. ALSO load after resolving any incident or near-miss: it must leave a new ledger entry in the same session.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 656 other files, including scripts (for example `MEMORY.md`, `entries/2026-08-10T191010Z-bot-pushed-release-prs-and-repo-actions-approval-policy.md` and `entries/2026-08-10T191010Z-cancel-the-ci-run-before-killing-its-db-backend.md`).
It sits in DevOps & Cloud, covering Incident response and Database migrations. It works with Vercel and GitHub Actions. The repository describes itself as: The open-source AI Operating System.
When your agent uses it
- Tasks that involve Incident response
- Tasks that involve Database migrations
Example prompts
- “/learnings”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Search the index and the full text for the surface you are about to change
- Read every matching entry in full. Obey its Rule, and keep its Enforcement green.
What it can do on your machine
Read from SKILL.md and the folder at commit 10520d3. 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
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Learnings loads about 1.1k tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 535 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); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 535 words (~1,066 tokens).
“Every rule this repository paid for with downtime or a near-miss is one entry in a timestamped, append-only ledger. The ledger is the full history, in the order it was learned.”
- name
- learnings
Files
SKILL.md and 655 other files (scripts) in .agents/skills/learnings of kortix-ai/suna.
- SKILL.md
- MEMORY.md
- entries/2026-08-10T191010Z-bot-pushed-release-prs-and-repo-actions-approval-policy.md
- entries/2026-08-10T191010Z-cancel-the-ci-run-before-killing-its-db-backend.md
- entries/2026-08-10T191010Z-cost-every-pending-prod-migration-before-promoting.md
- entries/2026-08-10T191010Z-never-backfill-data-inside-a-single-transaction-migration.md
- entries/2026-08-10T191010Z-node-pg-migrate-checkorder-is-index-wise-on-ledger-run-order.md
- entries/2026-08-10T191010Z-the-prod-frontend-must-never-deploy-before-the-api-serves-th.md
- entries/2026-08-10T191010Z-verify-ci-assertions-against-the-real-artifact-format-on-the.md
- entries/2026-08-10T194745Z-an-audit-reconstruction-trigger-is-only-safe-with-its-dedup.md
- entries/2026-08-10T194745Z-one-create-index-concurrently-per-table-at-a-time.md
- entries/2026-08-10T194745Z-the-vercel-prod-build-must-be-handed-the-release-version.md
- entries/2026-08-11T063009Z-a-deploy-workflow-must-not-cancel-a-build-it-cannot-outrun.md
- entries/2026-08-11T120415Z-a-per-turn-hot-path-must-not-contain-an-unbounded-third-part.md
- entries/2026-08-12T090712Z-a-cross-process-command-string-needs-a-test-that-runs-it.md
- entries/2026-08-12T100900Z-a-deployed-api-is-not-a-deployed-daemon.md
- entries/2026-08-13T075428Z-anything-created-per-deploy-needs-a-reaper-and-the-reaper-ne.md
- entries/2026-08-13T202203Z-a-platform-injected-principal-must-never-have-its-authority.md
- entries/2026-08-14T120355Z-a-tls-proxy-component-is-only-as-correct-as-the-third-party.md
- entries/2026-08-14T120355Z-bun-diverges-from-node-in-three-load-bearing-ways-around-raw.md
- … and 636 more
Open the folder on GitHubat commit 10520d3
Compare with similar skills
Learnings 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 |
|---|---|---|---|---|---|---|
| Learnings this skillkortix-ai/suna | 20k | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Use Vercel Actionamondnet/vercel-action | 764 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Deployments Cicdvercel/vercel-plugin | 301 | 1 repos | ~3k | Automated safety check: Pass | Custom licence | |
| Deploy Release Testvercel/next.js | 143k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Deploy Setupgarrytan/gstack | 136k | — | ~11k | Automated safety check: Notes | MIT | |
| Devops SpecialistCaoMeiYouRen/caomei-auth | 220 | — | ~446 | Automated safety check: Notes | MIT |
Similar skills
- Official
Deployments Cicd
vercel/vercel-plugin
Vercel deployment and CI/CD expert guidance. An agent skill from vercel/vercel-plugin.
- Official
Deploy Release Test
vercel/next.js
Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the teste2edeployrelease.yml GitHub Actions workflow.
Deploy Setup
garrytan/gstack
Detects where an app deploys, its production URL and health checks, then saves the deploy configuration in CLAUDE.md for /land-and-deploy.
Devops Specialist
CaoMeiYouRen/caomei-auth
修改 Docker、CI/CD、部署配置、环境变量、运行时参数、构建脚本和发布流程时使用。优先覆盖 Docker、Vercel、Cloudflare 与 GitHub Actions 场景。用户提到 deploy、Dockerfile、workflow、CI、CD、environment variables、build pipeline、release config 时都应触发。
CI/CD Pipeline Principles
irahardianto/awesome-agv
Rules for designing CI/CD pipelines in layers: universal lint, test and scan stages, container builds with SBOM attestation, and GitOps for orchestrated deployments.
More from kortix-ai/suna
All 19 skills in this repoPonytail Review
kortix-ai/suna
Code review focused exclusively on over-engineering. An agent skill from kortix-ai/suna.
Kortix Brand
kortix-ai/suna
Load FIRST for anything that carries the Kortix look or voice: product or mobile UI, copy of any kind, decks, social, images, email, CLI output, anything with the logo, and reviews of these.
Testing
kortix-ai/suna
A skill your agent uses for every Kortix test task, behavior change, bug fix, refactor, API route change, CLI change, SDK change, browser journey, test failure, coverage question, local benchmark…
Contributing
kortix-ai/suna
The pull request loop for this repo: branch → commit → verify in your own box (local tests + local stack) → PR into main → demo video recorded with agent-browser on the local stack → gh --attach →…
Claude Code
kortix-ai/suna
Drive Anthropic's Claude Code CLI (claude -p) as a non-interactive coding sub-agent from inside Codex.
Kortix Presentation
kortix-ai/suna
Recipe: build, edit, present or record a Kortix deck or film (a Next.js route under /presentations in apps/web, never a file).
Related
Works with
Categories
Questions about Learnings
What does Learnings do?
The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident. Learnings is an agent skill from kortix-ai/suna. The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident.
When should I use Learnings?
Learnings fits situations like: tasks that involve Incident response; tasks that involve Database migrations.
How do I install Learnings in Claude Code?
Run `npx skills add kortix-ai/suna --skill learnings -a claude-code`. Or copy the skill folder (.agents/skills/learnings in kortix-ai/suna) into .claude/skills/learnings in your project. Claude Code loads it when a task matches its description.
How do I install Learnings in Codex?
Run `npx skills add kortix-ai/suna --skill learnings -a codex`. Or copy the skill folder (.agents/skills/learnings in kortix-ai/suna) into .agents/skills/learnings in your project. Codex loads it when a task matches its description.
Can I use Learnings 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 kortix-ai/suna --skill learnings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learnings, .gemini/skills/learnings, .github/skills/learnings and .opencode/skills/learnings in your project.
What does Learnings need to run?
SKILL.md names no scripts, command-line tools or credentials: Learnings is instructions for the agent only.
Does Learnings access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Learnings 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Learnings use?
Learnings has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Learnings use?
About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Learnings?
Skills that share tags, products or a category with Learnings: Use Vercel Action (amondnet/vercel-action, 764 stars), Deployments Cicd (vercel/vercel-plugin, 301 stars), Deploy Release Test (vercel/next.js, 143k stars) and Deploy Setup (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Learnings?
kortix-ai (a GitHub organization) maintains it in kortix-ai/suna, which has 20,262 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 10, 2026.
Source: kortix-ai/suna on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.