Markdown Article Formatter
JimLiu/baoyu-skills
Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.
Fetch the Birkholz & Schlegel 2016 paper and its supporting information — the "standard method" (SM) that PyBerny's optimization algorithm follows — plus the papers it cites.
Install Standard Method
$ npx skills add pyberny/pyberny --skill standard-method -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pyberny/pyberny standard-method --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/pyberny/pyberny.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/standard-method .claude/skills/standard-method && 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 "standard-method" agent skill from https://github.com/pyberny/pyberny/tree/master/.claude/skills/standard-method into .claude/skills/standard-method/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "standard-method", 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/pyberny/pyberny/tree/master/.claude/skills/standard-methodType 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 pyberny/pyberny --skill standard-method -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pyberny/pyberny standard-method --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pyberny/pyberny.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/standard-method .agents/skills/standard-method && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "standard-method" agent skill from https://github.com/pyberny/pyberny/tree/master/.claude/skills/standard-method into .agents/skills/standard-method/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "standard-method", 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 pyberny/pyberny --skill standard-method -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pyberny/pyberny standard-method --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pyberny/pyberny.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/standard-method .cursor/skills/standard-method && 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 "standard-method" agent skill from https://github.com/pyberny/pyberny/tree/master/.claude/skills/standard-method into .cursor/skills/standard-method/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "standard-method", 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/pyberny/pyberny.git --path .claude/skills/standard-method--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 pyberny/pyberny --skill standard-method -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pyberny/pyberny standard-method --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pyberny/pyberny.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/standard-method .gemini/skills/standard-method && 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 "standard-method" agent skill from https://github.com/pyberny/pyberny/tree/master/.claude/skills/standard-method into .gemini/skills/standard-method/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "standard-method", 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 pyberny/pyberny standard-methodInstalls 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 pyberny/pyberny --skill standard-method -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pyberny/pyberny.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/standard-method .github/skills/standard-method && 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 "standard-method" agent skill from https://github.com/pyberny/pyberny/tree/master/.claude/skills/standard-method into .github/skills/standard-method/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "standard-method", 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 pyberny/pyberny --skill standard-method -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pyberny/pyberny standard-method --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pyberny/pyberny.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/standard-method .opencode/skills/standard-method && 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 "standard-method" agent skill from https://github.com/pyberny/pyberny/tree/master/.claude/skills/standard-method into .opencode/skills/standard-method/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "standard-method", 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
standard-method- GitHub stars
- 133
- Token cost
- ~1.4k tokens
- SKILL.md length
- 647 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MPL-2.0
At a glance
Fetch the Birkholz & Schlegel 2016 paper and its supporting information — the "standard method" (SM) that PyBerny's optimization algorithm follows — plus the papers it cites.
- The user references the SM
- SKILL.md covers How to access, Bundle contents (under…, When to consult which paper and Notes for reviewing /…
- Calls wget
- Asks about algorithm details/equations/convergence criteria
What it does
Standard Method is an agent skill from pyberny/pyberny. Fetch the Birkholz & Schlegel 2016 paper and its supporting information — the "standard method" (SM) that PyBerny's optimization algorithm follows — plus the papers it cites. Use when the user references the SM, asks about algorithm details/equations/convergence criteria, asks for test structures, asks about any of the SM's cited references (RFO, BFGS/SR1/PSB/Bofill, trust region, redundant internal coordinates, etc.), or asks anything that would be answered by reading [BirkholzTCA16] (cited in doc/algorithm.rst).
Its SKILL.md is about 1.4k 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 Documents & Office. The repository describes itself as: Molecular structure optimizer. The licence is MPL-2.0.
When your agent uses it
- The user references the SM
- Asks about algorithm details/equations/convergence criteria
- Asks for test structures
- Asks about any of the SMs cited references (RFO
Example prompts
- “standard method”
- “/standard-method”
What it can do on your machine
Read from SKILL.md and the folder at commit 2c73223. 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:
wget
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):
dx.doi.org
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
Standard Method loads about 1.4k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 647 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 pyberny/pyberny at commit 2c73223, republished under its MPL-2.0 licence (© pyberny). 647 words, ~1,438 tokens.
Download SKILL.mdSave it as
.claude/skills/standard-method/SKILL.md (or your agent's skills folder).- name
- standard-method
- description
- Fetch the Birkholz & Schlegel 2016 paper and its supporting information — the "standard method" (SM) that PyBerny's optimization algorithm follows — plus the papers it cites. Use when the user references the SM, asks about algorithm details/equations/convergence criteria, asks for test structures, asks about any of the SM's cited references (RFO, BFGS/SR1/PSB/Bofill, trust region, redundant internal coordinates, etc.), or asks anything that would be answered by reading [BirkholzTCA16] (cited in `doc/algorithm.rst`).
Standard method paper (Birkholz & Schlegel 2016) and supporting literature
doc/algorithm.rst notes that PyBerny "loosely follows" the standard method (SM) described in the appendix of:
Birkholz, A. B. & Schlegel, H. B. Exploration of some refinements to geometry optimization methods. Theor. Chem. Acc. 135, (2016). DOI: 10.1007/s00214-016-1847-3
The SM appendix is self-contained for headline formulas but defers several pieces to other papers (RFO derivation, trust-region details, Bofill MSP, pRFO/EF for TS) or omits them entirely (initial Hessian, bond detection, B-matrix derivatives, coordinate formulas). The bundle therefore also includes those cited / canonical sources.
None of these papers are checked into the repo (copyright). They are downloaded from PAPERS_URL.
How to access
The container is ephemeral, so re-download as needed:
wget -q "$PAPERS_URL" -O /tmp/standard-method.zip
unzip -o /tmp/standard-method.zip -d /tmp/The Read tool renders PDFs visually (via poppler-utils) — equations, bold matrices, subscripts and fractions all come through cleanly. Always pass a pages range for multi-page PDFs.
Bundle contents (under /tmp/standard-method/)
Primary
390.pdf— Birkholz & Schlegel 2016, 12 pp. Appendix "Standard method" (pp. 8–12) is what PyBerny implements. Numbered Eqs. 14–33 cover B-matrix, generalised inverse, back-transformation, RFO, trust region, BFGS/SR1/PSB/MSP, convergence.214_2016_1847_MOESM1_ESM.txt— SI. Plain-text XYZ coordinates (Å) for the 20 test molecules (Artemisinin, Aspartame, …), each preceded by name andcharge multiplicity.
SM appendix's explicit deferrals (see Ref. [X])
Banerjee, Adams, Simons - 1985 - Search for Stationary Points on Surfaces.pdf— SM ref [26]. RFO derivation and pRFO for transition states. The Banerjee article begins a few pages into the PDF (the journal-issue layout puts a different article first).baker1996.pdf— SM ref [17]. Baker & Chan 1996, eigenvector-following for TS optimization (referenced alongside [26] for pRFO).Dennis, Numerical Methods for Unconstrained Optimization and Nonlinear Equations.pdf— SM ref [27]. Dennis & Schnabel textbook, 395 pp. Adaptive trust-region material is in chapter 6.bofill1994.pdf— SM ref [14]. Bofill 1994, J. Comput. Chem. 15(1):1. Source of the MSP / "Bofill" Hessian update (Eqs. 8–13 of that paper define the φ-mixed family that the SM cites as Eqs. 32–33).
Show full SKILL.md (334 more words)Show less
SM appendix's implicit / canonical-source references
peng1996.pdf— SM ref [16]. Peng, Ayala, Schlegel & Frisch 1996. The RIC machinery PyBerny implements (bond-detection rule, recursive dihedrals through linear atoms, projector + α(1−P) penalty in Eq. 9 with α = 1000 au — this is the source of PyBerny's hard-coded1000·(I − proj)inberny.py:191, not an ad-hoc constant). Iterative back-transformation is Eq. 11.1992_Pulay_2856.pdf— SM ref [3]. Pulay & Fogarasi 1992, J. Chem. Phys. 96:2856. Generalised inverse, projector approach (basis for SM Eqs. 18–21).Schlegel - 1984 - Estimating the Hessian for gradient-type geometry optimizations.pdf— SM ref [7]. Analytic B-matrix derivatives for stretch/bend/torsion coordinates (the SM doesn't write these out; PyBerny'scoord.eval(..., grad=True)implements them).Schlegel11_Geometry_optimization.pdf— SM ref [1]. Schlegel 2011 WIREs Comput. Mol. Sci. review. Useful overview context, especially for line searches (not in the SM but used by PyBerny).Swart, Bickelhaupt - 2006 - Optimization of Strong and Weak Coordinates.pdf—[SwartIJQC06]fromdoc/algorithm.rst. The Lindh-style diagonal initial Hessian PyBerny uses; fills the gap the SM leaves silent.
When to consult which paper
| Need | File |
|---|---|
| Exact SM convergence criteria, sketch of full algorithm | 390.pdf appendix |
| Test geometries to reproduce results / build test cases | 214_…_MOESM1_ESM.txt |
| Why the augmented-Hessian eigenvector gives the RFO step | Banerjee 1985 |
| pRFO / eigenvector-following for TS | Banerjee 1985, Baker 1996 |
| Trust-region update theory & convergence guarantees | Dennis & Schnabel, ch. 6 |
| Bofill / MSP update derivation | Bofill 1994 |
RIC construction details (bonds, dihedrals through linears, α(1−P) penalty, iterative back-transformation) | Peng 1996 |
| Generalised inverse + projector formulation | Pulay-Fogarasi 1992 |
| Analytic B-matrix derivatives | Schlegel 1984 |
| Background, line-search rationale, overall context | Schlegel 2011 |
| Initial Hessian model | Swart-Bickelhaupt 2006 |
Notes for reviewing / extending PyBerny against the SM
- PyBerny's
1000·(I − proj)penalty inberny.py:191comes from Peng 1996 Eq. 9 (α = 1000 au) — not ad-hoc. - The SM omits the initial Hessian, bond detection, and B-matrix derivatives — those are PyBerny's own choices, sourced from Swart-Bickelhaupt, Peng et al., and Schlegel 1984 respectively.
- Issue #29 ("fully conform to the SM") and issue #30 (linear bends with dummy atoms) are the open TODOs.
If PAPERS_URL is unset, ask the user — do not invent a URL.
© pyberny, MPL-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 .claude/skills/standard-method of pyberny/pyberny.
Open the folder on GitHubat commit 2c73223
Compare with similar skills
Standard Method 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 |
|---|---|---|---|---|---|---|
| Standard Method this skillpyberny/pyberny | 133 | — | ~1.4k | Automated safety check: Pass | MPL-2.0 | |
| Markdown Article FormatterJimLiu/baoyu-skills | 27k | 6 repos | ~3.5k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Obsidian MarkdownAtmosphere/atmosphere | 3.8k | 20 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| DOCXrvdbreemen/OTGW-firmware | 207 | 33 repos | ~4.3k | Automated safety check: Pass | Proprietary | |
| Word Document Reader and WriterHKUDS/DeepTutor | 41k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Obsidian Markdown
Atmosphere/atmosphere
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.
DOCX
rvdbreemen/OTGW-firmware
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).
Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
Crossposting
wasp-lang/wasp
Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.
Related
Categories
Questions about Standard Method
What does Standard Method do?
Fetch the Birkholz & Schlegel 2016 paper and its supporting information — the "standard method" (SM) that PyBerny's optimization algorithm follows — plus the papers it cites. Standard Method is an agent skill from pyberny/pyberny. Fetch the Birkholz & Schlegel 2016 paper and its supporting information — the "standard method" (SM) that PyBerny's optimization algorithm follows — plus the papers it cites.
When should I use Standard Method?
Standard Method fits situations like: the user references the SM; asks about algorithm details/equations/convergence criteria; asks for test structures; asks about any of the SMs cited references (RFO.
How do I install Standard Method in Claude Code?
Run `npx skills add pyberny/pyberny --skill standard-method -a claude-code`. Or copy the skill folder (.claude/skills/standard-method in pyberny/pyberny) into .claude/skills/standard-method in your project. Claude Code loads it when a task matches its description.
How do I install Standard Method in Codex?
Run `npx skills add pyberny/pyberny --skill standard-method -a codex`. Or copy the skill folder (.claude/skills/standard-method in pyberny/pyberny) into .agents/skills/standard-method in your project. Codex loads it when a task matches its description.
Can I use Standard Method 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 pyberny/pyberny --skill standard-method -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/standard-method, .gemini/skills/standard-method, .github/skills/standard-method and .opencode/skills/standard-method in your project.
What does Standard Method need to run?
Going by SKILL.md and its folder, Standard Method needs the command-line tools its instructions call (wget).
Does Standard Method access the network?
SKILL.md names 1 domain. As links in the text: dx.doi.org. This is read from the text; nothing was executed.
Is Standard Method 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 Standard Method use?
Standard Method is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Standard Method use?
About 1.4k tokens (SKILL.md is roughly 5.8k 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 Standard Method?
Skills that share tags, products or a category with Standard Method: Markdown Article Formatter (JimLiu/baoyu-skills, 27k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Standard Method?
pyberny (a GitHub organization) maintains it in pyberny/pyberny, which has 133 GitHub stars. The repository was last updated on July 18, 2026.
Source: pyberny/pyberny on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.