Monitor CI
nrwl/nx
Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.
Where task data and taskset code live across prime-tasks and prime-envs, and how to fix a broken task.
Install Prime Tasks
$ npx skills add PrimeIntellect-ai/prime-envs --skill prime-tasks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PrimeIntellect-ai/prime-envs prime-tasks --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/PrimeIntellect-ai/prime-envs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prime-tasks .claude/skills/prime-tasks && 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 "prime-tasks" agent skill from https://github.com/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasks into .claude/skills/prime-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prime-tasks", 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/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasksType 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 PrimeIntellect-ai/prime-envs --skill prime-tasks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PrimeIntellect-ai/prime-envs prime-tasks --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrimeIntellect-ai/prime-envs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/prime-tasks .agents/skills/prime-tasks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prime-tasks" agent skill from https://github.com/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasks into .agents/skills/prime-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prime-tasks", 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 PrimeIntellect-ai/prime-envs --skill prime-tasks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PrimeIntellect-ai/prime-envs prime-tasks --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrimeIntellect-ai/prime-envs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/prime-tasks .cursor/skills/prime-tasks && 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 "prime-tasks" agent skill from https://github.com/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasks into .cursor/skills/prime-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prime-tasks", 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/PrimeIntellect-ai/prime-envs.git --path skills/prime-tasks--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 PrimeIntellect-ai/prime-envs --skill prime-tasks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PrimeIntellect-ai/prime-envs prime-tasks --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrimeIntellect-ai/prime-envs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/prime-tasks .gemini/skills/prime-tasks && 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 "prime-tasks" agent skill from https://github.com/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasks into .gemini/skills/prime-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prime-tasks", 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 PrimeIntellect-ai/prime-envs prime-tasksInstalls 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 PrimeIntellect-ai/prime-envs --skill prime-tasks -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PrimeIntellect-ai/prime-envs.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/prime-tasks .github/skills/prime-tasks && 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 "prime-tasks" agent skill from https://github.com/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasks into .github/skills/prime-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prime-tasks", 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 PrimeIntellect-ai/prime-envs --skill prime-tasks -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PrimeIntellect-ai/prime-envs prime-tasks --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrimeIntellect-ai/prime-envs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/prime-tasks .opencode/skills/prime-tasks && 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 "prime-tasks" agent skill from https://github.com/PrimeIntellect-ai/prime-envs/tree/main/skills/prime-tasks into .opencode/skills/prime-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prime-tasks", 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
prime-tasks- GitHub stars
- 130
- Token cost
- ~504 tokens
- SKILL.md length
- 221 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Where task data and taskset code live across prime-tasks and prime-envs, and how to fix a broken task.
- Works in 2 steps: prime-tasks: fix the task dir. For an… → prime-envs (this repo): after the…
- A Harbor task has a bad image
- SKILL.md covers Rules and Fix a broken task
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Prime Tasks is an agent skill from PrimeIntellect-ai/prime-envs. Where task data and taskset code live across prime-tasks and prime-envs, and how to fix a broken task. Use when a Harbor task has a bad image, test, instruction, or asset, or before editing a taskset in prime-envs to work around one task.
Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud. The repository describes itself as: Environments by the Prime Intellect Research Team. The licence is Apache-2.0.
When your agent uses it
- A Harbor task has a bad image
- Before editing a taskset in prime-envs to work around one task
Example prompts
- “/prime-tasks”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- prime-tasks: fix the task dir. For an image fix, change the Dockerfile under environment/, build and push the image, and set the new ref…
- prime-envs (this repo): after the prime-tasks PR merges, point the taskset at its merge commit. Update git_commit_id in registry.json, or…
What it can do on your machine
Read from SKILL.md and the folder at commit a46b48d. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Prime Tasks loads about 504 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 221 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 PrimeIntellect-ai/prime-envs at commit a46b48d, republished under its Apache-2.0 licence (© PrimeIntellect-ai). 221 words, ~504 tokens.
Download SKILL.mdSave it as
.claude/skills/prime-tasks/SKILL.md (or your agent's skills folder).- name
- prime-tasks
- description
- Where task data and taskset code live across prime-tasks and prime-envs, and how to fix a broken task. Use when a Harbor task has a bad image, test, instruction, or asset, or before editing a taskset in prime-envs to work around one task.
prime-tasks vs. prime-envs
| Repo | Holds |
|---|---|
prime-tasks | Raw Harbor task data: task.toml (with the image ref), instruction.md, environment/ (Dockerfile, assets), tests/, solution/. |
prime-envs | Runtime logic: taskset classes, configs, prompts, judges, registry.json, and the pinned prime-tasks commit. |
Rules
- Do not put task data in this repo. No task dirs, Dockerfiles, test files, or data files for single tasks.
- Do not special-case single tasks in taskset code. No
if task.name == ...that swaps an image, test, instruction, or answer. - Pin
prime-tasksby commit SHA, never bymain.
Fix a broken task
Open two companion PRs and link them to each other:
prime-tasks: fix the task dir. For an image fix, change the Dockerfile underenvironment/, build and push the image, and set the new ref intask.toml. For an upstream dataset, export the full task dir (seedatasets/terminal-bench-2/).prime-envs(this repo): after theprime-tasksPR merges, point the taskset at its merge commit. Updategit_commit_idinregistry.json, or the pinned repo URL in the taskset. Bump the env version and add a changelog line to its README.
Taskset code may select which tasks come from prime-tasks (e.g. REPAIRED_TASKS in environments/terminal/pi_terminal_bench_2). The task data itself stays in prime-tasks.
PI-TerminalBench2.1 uses datasets/pi-terminalbench2-1 in prime-tasks.
Its image builder and grader author checks live in scripts/pi-terminalbench2-1;
prime-envs keeps only the pinned loader and its taskset integration checks.
© PrimeIntellect-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
Just SKILL.md in skills/prime-tasks of PrimeIntellect-ai/prime-envs.
Open the folder on GitHubat commit a46b48d
Compare with similar skills
Prime Tasks 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 |
|---|---|---|---|---|---|---|
| Prime Tasks this skillPrimeIntellect-ai/prime-envs | 130 | — | ~504 | Automated safety check: Pass | Apache-2.0 | |
| Monitor CInrwl/nx | 29k | 6 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Terraform and OpenTofu Guideagentscope-ai/QwenPaw | 36k | 6 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Optimize Auditvercel-labs/agent-skills | 32k | 8 repos | ~4.3k | Automated safety check: Pass | None | |
| Analyze GitHub Action Logswithastro/astro | 63k | 1 repos | ~1.3k | Automated safety check: Pass | Custom licence | |
| Openclaw Live Updateropenclaw/openclaw | 392k | — | ~3.7k | Automated safety check: Pass | MIT |
Similar skills
Terraform and OpenTofu Guide
agentscope-ai/QwenPaw
Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.
- Official
Vercel Optimize Audit
vercel-labs/agent-skills
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
- Official
Analyze GitHub Action Logs
withastro/astro
Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.
Openclaw Live Updater
openclaw/openclaw
Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.
Docs Learn PR Preview
netdata/netdata
Use only when the user explicitly asks to build, run, preview, inspect, or validate learn.netdata.cloud locally using the contents of a PR or documentation branch before merge.
More from PrimeIntellect-ai/prime-envs
Evaluation
PrimeIntellect-ai/prime-envs
Install and run a verifiers environment — smoke testing during development and full benchmark evals.
Related
Categories
Questions about Prime Tasks
What does Prime Tasks do?
Where task data and taskset code live across prime-tasks and prime-envs, and how to fix a broken task. Prime Tasks is an agent skill from PrimeIntellect-ai/prime-envs. Where task data and taskset code live across prime-tasks and prime-envs, and how to fix a broken task.
When should I use Prime Tasks?
Prime Tasks fits situations like: A Harbor task has a bad image; before editing a taskset in prime-envs to work around one task.
How do I install Prime Tasks in Claude Code?
Run `npx skills add PrimeIntellect-ai/prime-envs --skill prime-tasks -a claude-code`. Or copy the skill folder (skills/prime-tasks in PrimeIntellect-ai/prime-envs) into .claude/skills/prime-tasks in your project. Claude Code loads it when a task matches its description.
How do I install Prime Tasks in Codex?
Run `npx skills add PrimeIntellect-ai/prime-envs --skill prime-tasks -a codex`. Or copy the skill folder (skills/prime-tasks in PrimeIntellect-ai/prime-envs) into .agents/skills/prime-tasks in your project. Codex loads it when a task matches its description.
Can I use Prime Tasks 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 PrimeIntellect-ai/prime-envs --skill prime-tasks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prime-tasks, .gemini/skills/prime-tasks, .github/skills/prime-tasks and .opencode/skills/prime-tasks in your project.
What does Prime Tasks need to run?
SKILL.md names no scripts, command-line tools or credentials: Prime Tasks is instructions for the agent only.
Does Prime Tasks access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Prime Tasks 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 Prime Tasks use?
Prime Tasks 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 Prime Tasks use?
About 504 tokens (SKILL.md is roughly 2k 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 Prime Tasks?
Skills that share tags, products or a category with Prime Tasks: Monitor CI (nrwl/nx, 29k stars), Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 36k stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars) and Analyze GitHub Action Logs (withastro/astro, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prime Tasks?
PrimeIntellect-ai (a GitHub organization) maintains it in PrimeIntellect-ai/prime-envs, which has 130 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.
Source: PrimeIntellect-ai/prime-envs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.