Project Health
jezweb/claude-skills
All-in-one project configuration and health management. An agent skill from jezweb/claude-skills.
Complete reference for decision-lab (dlab). An agent skill from pymc-labs/decision-lab.
Install Dlab CLI
$ npx skills add pymc-labs/decision-lab --skill dlab-cli -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pymc-labs/decision-lab dlab-cli --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/pymc-labs/decision-lab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dlab-cli .claude/skills/dlab-cli && 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 "dlab-cli" agent skill from https://github.com/pymc-labs/decision-lab/tree/main/skills/dlab-cli into .claude/skills/dlab-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dlab-cli", 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/pymc-labs/decision-lab/tree/main/skills/dlab-cliType 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 pymc-labs/decision-lab --skill dlab-cli -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pymc-labs/decision-lab dlab-cli --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pymc-labs/decision-lab.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dlab-cli .agents/skills/dlab-cli && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dlab-cli" agent skill from https://github.com/pymc-labs/decision-lab/tree/main/skills/dlab-cli into .agents/skills/dlab-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dlab-cli", 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 pymc-labs/decision-lab --skill dlab-cli -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pymc-labs/decision-lab dlab-cli --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pymc-labs/decision-lab.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dlab-cli .cursor/skills/dlab-cli && 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 "dlab-cli" agent skill from https://github.com/pymc-labs/decision-lab/tree/main/skills/dlab-cli into .cursor/skills/dlab-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dlab-cli", 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/pymc-labs/decision-lab.git --path skills/dlab-cli--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 pymc-labs/decision-lab --skill dlab-cli -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pymc-labs/decision-lab dlab-cli --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pymc-labs/decision-lab.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dlab-cli .gemini/skills/dlab-cli && 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 "dlab-cli" agent skill from https://github.com/pymc-labs/decision-lab/tree/main/skills/dlab-cli into .gemini/skills/dlab-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dlab-cli", 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 pymc-labs/decision-lab dlab-cliInstalls 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 pymc-labs/decision-lab --skill dlab-cli -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pymc-labs/decision-lab.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dlab-cli .github/skills/dlab-cli && 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 "dlab-cli" agent skill from https://github.com/pymc-labs/decision-lab/tree/main/skills/dlab-cli into .github/skills/dlab-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dlab-cli", 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 pymc-labs/decision-lab --skill dlab-cli -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pymc-labs/decision-lab dlab-cli --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pymc-labs/decision-lab.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dlab-cli .opencode/skills/dlab-cli && 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 "dlab-cli" agent skill from https://github.com/pymc-labs/decision-lab/tree/main/skills/dlab-cli into .opencode/skills/dlab-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dlab-cli", 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
dlab-cli- GitHub stars
- 199
- Token cost
- ~957 tokens
- SKILL.md length
- 421 words
- Files
- 5 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Complete reference for decision-lab (dlab). An agent skill from pymc-labs/decision-lab.
- Works in 5 steps: Create a decision-pack — scaffold with… → Design agents — write orchestrator,… → Run a session — dlab --dpack --data… → …
- The user asks about creating decision-packs
- SKILL.md covers When to use this skill, Workflow overview, Key concepts and Critical methodology rules, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Dlab CLI is an agent skill from pymc-labs/decision-lab. Complete reference for decision-lab (dlab). Use when the user asks about creating decision-packs, designing data science agents, running sessions, analyzing results, or anything related to dlab CLI, agent architecture, parallel subagents, or decision-pack configuration. Covers the full workflow from scaffolding to analysis.
Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/agent-design.md`, `references/create-dpack-interactive.md` and `references/create-dpack.md`).
It sits in Agent Workflows, covering Subagents and Project scaffolding. The repository describes itself as: Run tested, autonomous agent workflows on your data for meaningful decision-making. The licence is Apache-2.0.
When your agent uses it
- The user asks about creating decision-packs
- Designing data science agents
- Running sessions
- Analyzing results
Example prompts
- “/dlab-cli”
Requirements
- Docker
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Create a decision-pack — scaffold with dlab create-dpack wizard or generate_dpack() programmatically
- Design agents — write orchestrator, subagent, and parallel agent configs
- Run a session — dlab --dpack --data --prompt "..."
- Monitor — dlab connect (live TUI) or dlab timeline (Gantt chart)
- Analyze results — browse session directory, logs, parallel instance outputs
What it can do on your machine
Read from SKILL.md and the folder at commit a68f132. 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
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
Dlab CLI loads about 957 tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 421 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 pymc-labs/decision-lab at commit a68f132, republished under its Apache-2.0 licence (© pymc-labs). 421 words, ~957 tokens.
Download SKILL.mdSave it as
.claude/skills/dlab-cli/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- dlab-cli
- description
- Complete reference for decision-lab (dlab). Use when the user asks about creating decision-packs, designing data science agents, running sessions, analyzing results, or anything related to dlab CLI, agent architecture, parallel subagents, or decision-pack configuration. Covers the full workflow from scaffolding to analysis.
decision-lab (dlab)
dlab runs autonomous coding agents in frozen Docker environments with domain-specific skills and parallel subagents. You package the environment, prompts, and skills into a decision-pack, point it at data, and get back reports and recommendations that hold up to scrutiny.
When to use this skill
- Creating a new decision-pack (interactive or programmatic)
- Designing agent system prompts for data science workflows
- Understanding how parallel agents, consolidators, and retry protocols work
- Analyzing a completed session's logs, outputs, and artifacts
- Running or configuring dlab CLI commands
Workflow overview
- Create a decision-pack — scaffold with
dlab create-dpackwizard orgenerate_dpack()programmatically - Design agents — write orchestrator, subagent, and parallel agent configs
- Run a session —
dlab --dpack <path> --data <data> --prompt "..." - Monitor —
dlab connect <work-dir>(live TUI) ordlab timeline <work-dir>(Gantt chart) - Analyze results — browse session directory, logs, parallel instance outputs
Key concepts
decision-pack: A directory containing config.yaml, docker/, and opencode/ (agents, skills, tools, permissions). Everything an agent needs to run.
Orchestrator (mode: primary): Coordinates the workflow, spawns parallel agents, evaluates results, writes reports. One per decision-pack.
Subagents (mode: subagent): Execute focused tasks. Each runs ONE strategy per run. If it fails, it writes diagnosis and stops — the orchestrator coordinates retries.
Consolidator: Auto-generated read-only agent that compares parallel instance results. Never picks a winner.
Parallel exploration: Fan out multiple agents with structurally diverse approaches (different priors, models, data prep). Check if they agree before recommending.
Show full SKILL.md (185 more words)Show less
Critical methodology rules
These are non-negotiable for any data science agent system:
- Never fabricate — no mocking data, no silently swallowing errors, no
try/except: value = 0 - Understanding over fitting — a model that doesn't converge is evidence, not failure
- Know when to stop — hard round limits, conflict detection, degenerate problem reports
- Templates, not implementations — no concrete numbers in prompts, use
<PLACEHOLDER>syntax - Uncertainty, not point estimates — always report intervals, distinguish model vs structural uncertainty
- Recommendations must be computed — no napkin math, multiple scenarios, realistic actions
- Document everything — including failures, two reports (business + technical)
Load references/agent-design.md for the full methodology guide.
References
Load these as needed — don't read all upfront:
references/agent-design.md— Full methodology: anti-fabrication, retry protocol, epistemic humility, conflict detection, prompt design, parallel exploration, degenerate problems, agent prompt structure, runtime directory layout, YAML configreferences/create-dpack.md— Programmatic decision-pack creation:generate_dpack()API, config keys, package managers, permissions, Modal integrationreferences/create-dpack-interactive.md— Interactive wizard guide: how to interview a user and callgenerate_dpack()with the right configreferences/run-analyzer.md— Session analysis: directory layout, log format (NDJSON events), how to navigate parallel runs, what to look for
© pymc-labs, 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 4 other files (references) in skills/dlab-cli of pymc-labs/decision-lab.
- SKILL.md
- references/agent-design.md
- references/create-dpack-interactive.md
- references/create-dpack.md
- references/run-analyzer.md
Open the folder on GitHubat commit a68f132
Compare with similar skills
Dlab CLI 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 |
|---|---|---|---|---|---|---|
| Dlab CLI this skillpymc-labs/decision-lab | 199 | — | ~957 | Automated safety check: Pass | Apache-2.0 | |
| Project Healthjezweb/claude-skills | 1.1k | 1 repos | ~3k | Automated safety check: Pass | MIT | |
| Agent Buildertestdouble/han | 279 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Skill Buildertestdouble/han | 279 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Harnessharnessworks/harness-starter-kit | 114 | — | ~490 | Automated safety check: Pass | MIT | |
| Qwen Agentthananon/9arm-skills | 3.2k | — | ~1.5k | Automated safety check: Pass | None |
Similar skills
Agent Builder
testdouble/han
Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the agent's design tree decision-by-decision — entity fit, domain focus and…
Skill Builder
testdouble/han
Builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design tree decision-by-decision — entity fit, use cases, name, description…
Harness
harnessworks/harness-starter-kit
Route Harness Starter Kit workflows. An agent skill from harnessworks/harness-starter-kit.
Qwen Agent
thananon/9arm-skills
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the claude-9arm command instead of burning Claude tokens/quota.
Antigravity
yuting0624/antigravity-for-claude-code
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.
More from pymc-labs/decision-lab
Dlab Figure Style
pymc-labs/decision-lab
decision-lab house figure style for matplotlib. An agent skill from pymc-labs/decision-lab.
Event Forecasting
pymc-labs/decision-lab
Methodology for probabilistic forecasting of when and whether a future event will occur.
Related
Categories
Questions about Dlab CLI
What does Dlab CLI do?
Complete reference for decision-lab (dlab). An agent skill from pymc-labs/decision-lab. Dlab CLI is an agent skill from pymc-labs/decision-lab. Complete reference for decision-lab (dlab).
When should I use Dlab CLI?
Dlab CLI fits situations like: the user asks about creating decision-packs; designing data science agents; running sessions; analyzing results.
How do I install Dlab CLI in Claude Code?
Run `npx skills add pymc-labs/decision-lab --skill dlab-cli -a claude-code`. Or copy the skill folder (skills/dlab-cli in pymc-labs/decision-lab) into .claude/skills/dlab-cli in your project. Claude Code loads it when a task matches its description.
How do I install Dlab CLI in Codex?
Run `npx skills add pymc-labs/decision-lab --skill dlab-cli -a codex`. Or copy the skill folder (skills/dlab-cli in pymc-labs/decision-lab) into .agents/skills/dlab-cli in your project. Codex loads it when a task matches its description.
Can I use Dlab CLI 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 pymc-labs/decision-lab --skill dlab-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dlab-cli, .gemini/skills/dlab-cli, .github/skills/dlab-cli and .opencode/skills/dlab-cli in your project.
What does Dlab CLI need to run?
SKILL.md names no scripts, command-line tools or credentials: Dlab CLI is instructions for the agent only. Our summary lists: Docker.
Does Dlab CLI 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 Dlab CLI 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 Dlab CLI use?
Dlab CLI 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 Dlab CLI use?
About 957 tokens (SKILL.md is roughly 3.8k 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 11k tokens, read only when the agent opens those files.
What are the alternatives to Dlab CLI?
Skills that share tags, products or a category with Dlab CLI: Project Health (jezweb/claude-skills, 1.1k stars), Agent Builder (testdouble/han, 279 stars), Skill Builder (testdouble/han, 279 stars) and Harness (harnessworks/harness-starter-kit, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dlab CLI?
pymc-labs (a GitHub organization) maintains it in pymc-labs/decision-lab, which has 199 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 25, 2026.
Source: pymc-labs/decision-lab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.