Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Add or revise a script under examples/ in dmrgpy. An agent skill from joselado/dmrgpy.
Install New Example
$ npx skills add joselado/dmrgpy --skill new-example -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install joselado/dmrgpy new-example --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/joselado/dmrgpy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/new-example .claude/skills/new-example && 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 "new-example" agent skill from https://github.com/joselado/dmrgpy/tree/master/.claude/skills/new-example into .claude/skills/new-example/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-example", 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/joselado/dmrgpy/tree/master/.claude/skills/new-exampleType 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 joselado/dmrgpy --skill new-example -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install joselado/dmrgpy new-example --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joselado/dmrgpy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/new-example .agents/skills/new-example && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "new-example" agent skill from https://github.com/joselado/dmrgpy/tree/master/.claude/skills/new-example into .agents/skills/new-example/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-example", 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 joselado/dmrgpy --skill new-example -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install joselado/dmrgpy new-example --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joselado/dmrgpy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/new-example .cursor/skills/new-example && 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 "new-example" agent skill from https://github.com/joselado/dmrgpy/tree/master/.claude/skills/new-example into .cursor/skills/new-example/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-example", 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/joselado/dmrgpy.git --path .claude/skills/new-example--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 joselado/dmrgpy --skill new-example -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install joselado/dmrgpy new-example --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joselado/dmrgpy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/new-example .gemini/skills/new-example && 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 "new-example" agent skill from https://github.com/joselado/dmrgpy/tree/master/.claude/skills/new-example into .gemini/skills/new-example/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-example", 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 joselado/dmrgpy new-exampleInstalls 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 joselado/dmrgpy --skill new-example -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/joselado/dmrgpy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/new-example .github/skills/new-example && 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 "new-example" agent skill from https://github.com/joselado/dmrgpy/tree/master/.claude/skills/new-example into .github/skills/new-example/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-example", 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 joselado/dmrgpy --skill new-example -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install joselado/dmrgpy new-example --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joselado/dmrgpy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/new-example .opencode/skills/new-example && 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 "new-example" agent skill from https://github.com/joselado/dmrgpy/tree/master/.claude/skills/new-example into .opencode/skills/new-example/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-example", 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
new-example- GitHub stars
- 114
- Token cost
- ~1.2k tokens
- SKILL.md length
- 572 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Add or revise a script under examples/ in dmrgpy. An agent skill from joselado/dmrgpy.
- Asks for an example
- SKILL.md covers Where it goes, The script and Run it before declaring it done
- Calls python3 and python
- A script showing how to use a feature
What it does
New Example is an agent skill from joselado/dmrgpy. Add or revise a script under examples/ in dmrgpy. Use this whenever the user asks for an example, a demo, a script showing how to use a feature, a backend-versus-backend comparison, or a regression script in the spirit of tests/, and also when a new feature has just landed and an example for it is the natural next step. The examples tree has rules that are easy to miss (it must plot, it must pin its own sweep schedule, it must import this worktree and not site-packages) and an audit found 105 scripts that had…
Its SKILL.md is about 1.2k 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 Development, covering Git worktrees. The repository describes itself as: DMRGPy is a Python library to compute quasi-one-dimensional spin chains and fermionic systems using matrix product states with DMRG as implemented in ITensor. Most of the… The licence is GPL-3.0.
When your agent uses it
- Asks for an example
- A script showing how to use a feature
- A backend-versus-backend comparison
- A regression script in the spirit of tests/
Example prompts
- “/new-example”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 7373fce. 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
Shell commands in SKILL.md call:
python3python
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
New Example loads about 1.2k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 572 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 joselado/dmrgpy at commit 7373fce, republished under its GPL-3.0 licence (© joselado). 572 words, ~1,183 tokens.
Download SKILL.mdSave it as
.claude/skills/new-example/SKILL.md (or your agent's skills folder).- name
- new-example
- description
- Add or revise a script under examples/ in dmrgpy. Use this whenever the user asks for an example, a demo, a script showing how to use a feature, a backend-versus-backend comparison, or a regression script in the spirit of tests/, and also when a new feature has just landed and an example for it is the natural next step. The examples tree has rules that are easy to miss (it must plot, it must pin its own sweep schedule, it must import this worktree and not site-packages) and an audit found 105 scripts that had quietly broken the first of them.
Adding an example
examples/ is the second regression surface, and the thing that separates it
from tests/ is that a human is expected to look at the result. That is the
premise behind most of the rules below.
Where it goes
examples/<theme>/<name>/main.py, one self-contained script per folder. The
themes are groundstate, staticcorrelators, dynamical_correlator,
spin_models, fermion_models, boson_models, time_evolution,
excited_states, entanglement, topological, kondo, non_hermitian,
finite_temperature, magnetization, idmrg, backend_comparison,
algebra, parity, pyitensor, utilities and readme_examples. Pick the
one that matches the physics, not the backend, except for a script whose whole
point is comparing backends. A comparison of the two compiled backends is named
v2_VS_v3_<thing> and lives in its theme folder. A script that mirrors a
snippet from README.md goes in readme_examples/ and has to stay in step with
the README.
The script
Open with the path line the tree already uses, which is depth three:
# Add the root path of the dmrgpy library
import os ; import sys ; sys.path.append(os.getcwd()+'/../../../src')Then a short comment saying what the script demonstrates and, where the script is meant as a regression guard, what it is guarding. Build the smallest system that shows the effect, and put the physics before the mechanics.
Pin the sweep schedule. Set nsweeps, maxm and any tolerance explicitly
rather than inheriting the library defaults, and assert at a tolerance the
pinned schedule actually reaches. boson_models/v2_VS_v3_boson inherited the
defaults and its assert then fired non-deterministically on a clean tree, in
two runs of five for one reader and five of seven for another: the two backends
were converging to the same answer, just not far enough to be compared where it
compared them. It now pins nsweeps=80, maxm=100 and asserts at 1e-5.
Plot what you computed. Any script that produces a sequence of values ends
with a matplotlib figure of it: a quantity against time, site, frequency or a
coupling; two backends overlaid; an error or timing curve. Save it next to
main.py under the folder's own name and then show it:
plt.savefig("<folder_name>.png",dpi=150)
plt.show()A script whose entire output is one scalar is the single exception, and it is a last resort rather than a default: before taking it, look for the cheap axis that is almost always already there, such as chain length, a field or coupling, time, bond dimension, site index, or ED against DMRG. The audit that found 105 print-only scripts found that most of them had already computed the array and simply never drew it.
Show full SKILL.md (182 more words)Show less
Assert where the script is a regression guard. Several examples carry real
asserts and are meant as tests in the same spirit as tests/, for instance
time_evolution/tdvp_VS_ED_time_evolution,
backend_comparison/backend_switch_consistency,
staticcorrelators/static_correlator_VS_ED and
entanglement/entanglement_entropy_VS_ED. Those are the templates to copy. The
assert stays as the pass or fail guard and the plot goes in after it, so the one
script serves as an automated check and as a visual sanity check when run by
hand.
Run it before declaring it done
From the example's own directory, with threads pinned, this worktree's src
forced onto the path, and a non-interactive backend so plt.show() does not
block:
cd examples/<theme>/<name>
MKL_NUM_THREADS=1 OMP_NUM_THREADS=1 MPLBACKEND=Agg \
PYTHONPATH=<this worktree>/src python3 main.pyThe PYTHONPATH is not belt and braces. The script's own line appends to
sys.path, and site-packages/dmrgpy is typically a symlink into one specific
checkout, so a plain python3 main.py from another worktree silently exercises
the wrong code with no error at all.
Afterwards run python clean.py from the repo root, which removes the generated
working directories and stray ERROR/*.OUT files the run leaves behind.
Say what the numbers came out as when you report back, not just that it ran.
© joselado, GPL-3.0. 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 .claude/skills/new-example of joselado/dmrgpy.
Open the folder on GitHubat commit 7373fce
Compare with similar skills
New Example 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 |
|---|---|---|---|---|---|---|
| New Example this skilljoselado/dmrgpy | 114 | — | ~1.2k | Automated safety check: Pass | GPL-3.0 | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Migrate Core Code to Submodulestinyhumansai/openhuman | 42k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Finishing A Development Branchfarm-fe/farm | 5.6k | 34 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence | |
| Keep Codex Fastvibeforge1111/keep-codex-fast | 1.6k | — | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
Finishing A Development Branch
farm-fe/farm
A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
Keep Codex Fast
vibeforge1111/keep-codex-fast
A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.
Pre-Release PR Triage
jamiepine/voicebox
Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.
More from joselado/dmrgpy
Docs Sync
joselado/dmrgpy
Update docs/userguide.{md,tex} and docs/documentation.{md,tex} together after a change to dmrgpy, keeping the Markdown and LaTeX versions of each in step and verifying the .tex still compiles under…
Hole Hunt
joselado/dmrgpy
Run a multi-lens hole hunt (audit) of the dmrgpy Python layer, or add a lens, a finding or a fix cluster to an existing one.
Related
Categories
Questions about New Example
What does New Example do?
Add or revise a script under examples/ in dmrgpy. An agent skill from joselado/dmrgpy. New Example is an agent skill from joselado/dmrgpy. Add or revise a script under examples/ in dmrgpy.
When should I use New Example?
New Example fits situations like: asks for an example; A script showing how to use a feature; A backend-versus-backend comparison; A regression script in the spirit of tests/.
How do I install New Example in Claude Code?
Run `npx skills add joselado/dmrgpy --skill new-example -a claude-code`. Or copy the skill folder (.claude/skills/new-example in joselado/dmrgpy) into .claude/skills/new-example in your project. Claude Code loads it when a task matches its description.
How do I install New Example in Codex?
Run `npx skills add joselado/dmrgpy --skill new-example -a codex`. Or copy the skill folder (.claude/skills/new-example in joselado/dmrgpy) into .agents/skills/new-example in your project. Codex loads it when a task matches its description.
Can I use New Example 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 joselado/dmrgpy --skill new-example -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/new-example, .gemini/skills/new-example, .github/skills/new-example and .opencode/skills/new-example in your project.
What does New Example need to run?
Going by SKILL.md and its folder, New Example needs the command-line tools its instructions call (python3 and python). Our summary lists: Python 3.
Does New Example 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 New Example 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 New Example use?
New Example is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does New Example use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 New Example?
Skills that share tags, products or a category with New Example: Finishing a Development Branch (obra/superpowers, 296k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains New Example?
joselado (a GitHub user) maintains it in joselado/dmrgpy, which has 114 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 26, 2026.
Source: joselado/dmrgpy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.