executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
swiss-knifeUse when operating LingTai headless bots, checking saved presets, reporting token usage, preparing HTML deliverables or verifying academic evidence. Also routes to retained MiniMax, Xiaomi MiMo and Zhipu provider references.
Independent GitHub snapshot · Automated classification · Original documentation governs
Swiss Knife is a top-level router for small, focused utility references. Enter
through this file, choose exactly one nested reference from the catalog below,
then read that nested SKILL.md for the actual procedure, examples, scripts, and
assets.
nested_references:
- name: bash-cli-harnesses
# Virtual cross-skill redirect, not a local reference/<name>/SKILL.md file.
location: bash-manual reference/bash-*/SKILL.md
description: >
Coding-agent CLIs such as Claude Code, OpenAI Codex, OpenCode, Cursor
Agent, MiMo Code, Qwen Code, Oh-My-Pi, Gemini CLI, Aider, Goose,
OpenHands, and Crush are now owned by `bash-manual` because they run as
long-lived shell subprocesses. Read `bash-manual` and then the matching
nested `reference/bash-*/SKILL.md`; Swiss Knife only keeps non-bash utility
references.
- name: minimax-cli
location: reference/minimax-cli/SKILL.md
description: >
Nested swiss-knife reference for the MiniMax `mmx` CLI. Read this for
MiniMax-backed image, video, music, TTS, or ad-hoc shell vision tasks.
- name: academic-research
location: reference/academic-research/SKILL.md
description: >
Nested swiss-knife reference for citation and empirical evidence gates.
Verify sources before drafting and anchor claims to data and runner code;
no bundled paper-fetch scripts or API/pipeline cookbook.
- name: token-usage
location: reference/token-usage/SKILL.md
description: >
Nested swiss-knife reference for network-wide token, cost, cache, and tool-call/API-call trend reports. Read
this when the human asks about token usage, budget, model costs, spending, cache behavior, or tools per API call
across agent ledgers.
- name: html-report
location: reference/html-report/SKILL.md
description: >
Nested swiss-knife reference for standalone HTML deliverables. Read this
when the human asks for a polished browser-openable report, dashboard,
memo, comparison, or any HTML artifact with MathJax equations.
- name: xiaomi-mimo
location: reference/xiaomi-mimo/SKILL.md
description: >
Nested swiss-knife reference for Xiaomi MiMo provider discovery. Read this
when the human asks to use or configure Xiaomi MiMo / 小米MiMo, or when you
need to understand the MiMo model family and compatible endpoints.
- name: zhipu-coding-plan
location: reference/zhipu-coding-plan/SKILL.md
description: >
Nested swiss-knife reference for the Zhipu / Z.AI / BigModel coding-plan
subscription. Read this when the human asks about Zhipu credentials or the
plan's vision, web search, web-read, and zread MCP capabilities.
- name: headless-bot
location: reference/headless-bot/SKILL.md
description: >
Nested swiss-knife reference for creating and operating headless LingTai
bot projects from `lingtai-tui spawn`. The current helper provisions a
Telegram MCP bot, and the workflow also covers preset-policy replication,
addon wiring, secret hygiene, refresh/relaunch, and verification.
- name: preset-health
location: reference/preset-health/SKILL.md
description: >
Nested swiss-knife reference for read-only saved-preset health checks.
Read this when the human asks whether saved presets still work, which one
is expired or misconfigured, or why `system(action="presets")` shows a bad
connectivity status. It enumerates saved presets, classifies failures
(expired key, missing credentials, unreachable endpoint, invalid
model/config, connectivity failure), and reports actionable fixes without
printing or mutating any secret.
| Need | Read |
|---|---|
| Run or compare coding-agent CLIs such as Claude Code, Codex, OpenCode, Cursor Agent, MiMo Code, Qwen Code, Oh-My-Pi, Gemini CLI, Aider, Goose, OpenHands, or Crush | Load bash-manual, then the matching reference/bash-*/SKILL.md |
| Generate images, video, music, TTS, or MiniMax shell vision | reference/minimax-cli/SKILL.md |
| Verify citation-bearing writing or empirical manuscript claims | reference/academic-research/SKILL.md |
| Report token usage, model costs, cache rates, or tool-call/API-call trends | reference/token-usage/SKILL.md |
| Produce standalone HTML reports/dashboards/memos | reference/html-report/SKILL.md |
| Discover/configure Xiaomi MiMo provider/model access | reference/xiaomi-mimo/SKILL.md; for mimocode shell execution, load bash-manual → reference/bash-mimocode/SKILL.md |
| Discover/configure Zhipu / Z.AI coding-plan capabilities | reference/zhipu-coding-plan/SKILL.md; for shell CLI harness execution, load bash-manual first |
| Create or automate a headless LingTai bot project, including Telegram bots | reference/headless-bot/SKILL.md |
| Health-check saved presets (read-only): classify expired keys, missing credentials, unreachable endpoints, invalid model/config | reference/preset-health/SKILL.md |
location next to this parent
SKILL.md.Do not load every nested reference by default. Swiss Knife exists to avoid polluting working context with unrelated utility manuals.
reference/<name>/SKILL.md with normal skill frontmatter (name,
description, optional version/tags). The description should start with
the fact that it is a nested swiss-knife reference and should state when to
read it.scripts/, assets/, and extra files under the same
reference/<name>/ folder.nested_references YAML block and routing table above.lingtai-tui bootstrap, then agents call system(action="refresh")
or skills(action="info") to see the refreshed utility tree.swiss-knife/SKILL.md as its
top-level catalog entry; its bundled references are reached through that router
rather than promoted as sibling top-level utility skills or swiss-knife/<child>
skills.Found a bug or issue? If you encounter any problems with this skill, load the
lingtai-issue-reportskill and follow its instructions to report it.