use-bms
Build and drive the yaBMS `c/bms` CLI on Linux — expand a Bashicu Matrix by a bracket, check whether a matrix is standard, compare two matrices, and search…
Skill by koteitan
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/koteitan-use-bms
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/use-bms
What's inside
- Skill name
use-bms- Description
- Build and drive the yaBMS `c/bms` CLI on Linux — expand a Bashicu Matrix by a bracket, check whether a matrix is standard, compare two matrices, and search for expansion loops, across BMS versions 4 / 3.3 / 2 / 1.1 / DBMS. Use whenever a task involves expanding, comparing, standard-checking, or loop-hunting Bashicu Matrices, or asks to run yaBMS.
- License
- MIT
- Instructions
- 190 lines in SKILL.md · view on GitHub
Files (3)
- README-ja.md
- README.md
- SKILL.md
SKILL.md (first lines)
[← Back](../../README.md) | [English](README.md) | [Japanese](README-ja.md) # use-bms Drive the `bms` C command in `c/` of the yaBMS repository. Target: Linux (also WSL). The MCP server in `mcp/` is a separate, optional path — do not use it for these tasks. ## Locate the repository All paths below are relative to a yaBMS checkout. Find it in this order: 1. the current working directory, if it contains `c/bms.c`; 2. `~/code/yaBMS`; 3. otherwise clone it — `git clone https://github.com/koteitan/yaBMS.git`. This skill is mirrored in `~/my-skills`, so it may be active outside the yaBMS tree. Never assume the skill directory sits inside the checkout. ## Build first `bms` is not committed; it must be compiled before any use. ```bash cd <repo>/c make # gcc -O0 -g -std=c99 -o bms bms.c ``` Requires `gcc` only — no libraries beyond libc. Re-run `make` after editing `bms.c` / `bms.h`. `make clean` removes the binary. Check that the binary exists before running anything; if `./bms` is missing, run `make` rather than reporting a failure. ## Input syntax A Bashicu Matrix is written as consecutive parenthesised columns, optionally followed by brackets: ``` (0,0,0)(1,1,1)(2,1,0)(1,1,1)[2] \_____ columns _____________/ \_ bracket ``` - Each `(...)` is one **column**; the numbers inside are the rows. - **Every column must have the same number of rows.** A mismatch prints `error:ys mismatch` and then segfaults. - `[n]` is the expansion count. Multiple brackets `[2][1]` are allowed and are consumed left to right (see `-r`). - Always quote the argument in the shell — parentheses are shell metacharacters. ## Commands All forms take the matrix as the last positional argument(s). | Task | Command | |------|---------| | Expand | `./bms [-e] [-d] [-r] [-v ver] "<bm>"` | | Standard check | `./bms -s [-d] [-v ver] "<bm>"` | | Compare | `./bms -c [-d] "<bm0>" "<bm1>"` | | Loop check (single) | `./bms -l [-d] [-v ver] "<bm>"` | | Loop search (range) | `./bms -lr [-d] [-v ver] "<bm0>" "<bm1>" [<depth>]` | | Help | `./bms -h` (add `-d` for copyright) | Options combine into one token (`-sd`, `-lrd`, `-ed`, `-lrdv 1.1`). ### Expand — `-e` (default) Expansion is the default when no command flag is given, so `-e` is optional. ```bash $ ./bms "(0,0,0)(1,1,1)(2,1,0)(1,1,1)[2]" (0,0,0)(1,1,1)(2,1,0)(1,1,0)(2,2,1)(3,2,0)(2,2,0)(3,3,1)(4,3,0) ``` `-r` keeps expanding while brackets remain, printing every intermediate step: ```bash $ ./bms -r "(0)(1)(2)(3)[1][1][1][1]" (0)(1)(2)(2)[1][1][1] (0)(1)(2)(1)(2)[1][1] (0)(1)(2)(1)(1)[1] (0)(1)(2)(1)(0)(1)(2)(1) ``` `-d` prints the internal decomposition (parent index matrix, good/bad part, bad root, `lnz`, delta, ascension matrix) before the result. ### Standard check — `-s` Prints `1` if the matrix is standard, `0` otherwise. With `-d`, prints the comparison trace and `standard.` / `non-standard.` instead. ```bash $ ./bms -s "(0)(1)" 1 $ ./bms -s "(1)" 0 ``` ### Compare — `-c` Prints `1` / `0` / `-1` for `bm0 > bm1` / `==` / `<`. Brackets are ignored, and so is `-v` (comparison is version-independent). ```bash $ ./bms -c "(0,0)(1,1)(2,0)" "(0,0)(1,1)(1,1)" 1 $ ./bms -cd "(0,0)(1,1)(2,0)" "(0,0)(1,1)(1,1)" (0,0)(1,1)(2,0) > (0,0)(1,1)(1,1) ``` ### Loop finding — `-l`, `-lr` `-l <bm>` first expands the matrix until no brackets remain, then reports `1` if the result loops (gets no smaller under a further expansion), `0` otherwise. `-lr <bm0> <bm1> [depth]` searches for a loop from `bm1` down to `bm0` within `depth` expansions (default `3`). Detection is heuristic and may miss loops.
From koteitan/my-skills, MIT.
More from koteitan/my-skills
- 0.587score
heart-beat
koteitan
Keep working autonomously until the proof is complete, with a CronCreate heartbeat that wakes the session whenever it has been idle for X minutes.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
manim-tts
koteitan
Building narrated explainer videos with manim + VOICEVOX TTS — hard-won pitfalls that produce silently broken output.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
nostr
koteitan
koteitan's Nostr hub — relay discovery (bootstrap → kind:10002 → kind:3 → fallback), NIP-19 bech32 encode/decode (naddr/nevent/npub, DIY, no nostr-tools), CLI…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
github-math-check
koteitan
Verify that math in a Markdown file actually renders on GitHub.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
my-github-md-rule
koteitan
Apply the user's selected README language and navigation-link convention.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
autonomy-stat
koteitan
Measure a Claude Code agent's autonomy (self-running time) from a session JSONL and render it as an interactive HTML chart.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
webapp-defaults
koteitan
The standing defaults when scaffolding a small vanilla web app (index.html + main.js + style.css) — dark mode ON by default and persisted to localStorage, a…
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
check-usage
koteitan
Report the Claude Code 5-hour and weekly (Max plan) rate-limit state — percent used, reset time, and the exhaustion forecast at the current pace.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
get-context
koteitan
Report the current Claude Code session's context-window usage percentage, computed locally from the session JSONL usage metadata
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
mermaid
koteitan
Rules for drawing Mermaid diagrams — no node fill colors, no diamond nodes, short captions without parentheses
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
sessiondb
koteitan
Index Claude Code session JSONL logs into a SQLite + FTS5 database with Japanese-aware tokenization, and search them
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
compact-unfreeze
koteitan
Before the user runs /compact from the remote client, arm a one-shot Monitor so its firing flushes the post-compact frozen remote input queue
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 8, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/koteitan/my-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from koteitan
- 0.587score
heart-beat
koteitan
Keep working autonomously until the proof is complete, with a CronCreate heartbeat that wakes the session whenever it has been idle for X minutes.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
manim-tts
koteitan
Building narrated explainer videos with manim + VOICEVOX TTS — hard-won pitfalls that produce silently broken output.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
my-github-md-rule
koteitan
Apply the user's selected README language and navigation-link convention.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
nostr
koteitan
koteitan's Nostr hub — relay discovery (bootstrap → kind:10002 → kind:3 → fallback), NIP-19 bech32 encode/decode (naddr/nevent/npub, DIY, no nostr-tools), CLI…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
github-math-check
koteitan
Verify that math in a Markdown file actually renders on GitHub.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
autonomy-stat
koteitan
Measure a Claude Code agent's autonomy (self-running time) from a session JSONL and render it as an interactive HTML chart.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
use-bms skill. Agent Mart. https://agentmart.dev/skills/koteitan-use-bms (last updated 2026-10-24)