Twg logo

Twg

Organization
zenobi-us
twg

Root TWG CLI skill for Atlassian work-data tasks. Use typed commands for known anchors; use live `twg help` only when command shape or output contract is uncertain.

Overview

Publisherzenobi-us
Repositorydotfiles
Skill nametwg
Stars
67
Forks
6
Bundled files
3
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Twg AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/developer/skills/atlassian/twg .claude/skills/twg
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Twg in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Twg on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Twg is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

twg

TWG routing: use typed commands for anchors. If uncertain, inspect twg help <terms>, twg help describe <path>, or twg help discover-skills "<intent>".

Overview

Load the narrowest workflow skill:

  • twg-status-rollups for status, leadership, and decision-readiness; load it before twg-engineering-work for PR-based team/org rollups.
  • twg-context-discovery for deep dives, dependencies, graphs, repos, and catch-ups.
  • twg-agentic-search for fuzzy cross-product Rovo/company-knowledge research.
  • twg-responsibility-routing for owners, experts, approvers, authorities, and escalation.
  • twg-engineering-work for code search and navigation, PR status, reviews, contributors, and hot areas.
  • twg-jira-resolve-merged-work for stale Jira work backed by merged PRs.
  • twg-operational-health for handoffs, incidents, Assets, staffing, meetings, and risk.
  • twg-bench-lite for read-only single-prompt A/B comparisons.

Invocation And Output

Run twg <command>. On shell command not found, use $HOME/.local/bin/twg (macOS/Linux) / $env:LOCALAPPDATA\Programs\twg\bin\twg.exe (PowerShell), then tell user to add that directory to PATH. Do not treat auth or command errors as PATH failures.

Do not add per-command env prefixes unless requested; hosts may set TWG_AGENT_DEFAULTS=1.

Use stdout_inline first when present. Outside benchmark lanes, inspect output_files.compact only when inline evidence is incomplete; full stdout is the last resort.

In TWG-only benchmark lanes, run only twg commands. Never use shell utilities or pipelines (jq, rg, date) to transform evidence or calculate windows. Use compact/inline TWG output, the prompt's timezone and window, and report gaps. Match the intent to the narrowest companion skill before selecting a command. Let that skill determine the typed route; use at most one help call when command shape or output remains ambiguous.

Auth/Setup Guard

Do not run setup, login, install, update, upkeep, or credential commands unless explicitly requested for setup/auth/repair. Otherwise report remediation and wait for user direction.

Bounded Evidence Loop

Converge; prefer typed or product-native evidence.

  1. Classify the anchor: person, team, project, goal, workitem, page, repo, service, asset, or topic.
  2. Resolve once; fetch evidence that changes status, risk, decision, relationship, or action.
  3. Rank candidates, hydrate representative items, then synthesize.
  4. Stop after the first policy denial; stop after the same auth, ACL, contract, or backend error twice.

Command Discovery

  • Use typed commands for familiar families: resolve, search, user, org-tree, work query, work search, pull-requests, jira, confluence, docs, context, responsibility, goals, projects, assets, and trello.
  • Use twg search "<topic>" [--limit <n>] for top-K discovery; explicit --app preflights.
  • For fuzzy Trello discovery, use twg trello search "<query>" --limit 20; no workspace scope.
  • For Rovo connectors, use twg rovo list-apps -o json (list-connectors alias), then explicit twg rovo search ... --app <connector>; follow its auth action or twg rovo auth <app>.
  • Keep document relationship history and fuzzy discovery separate:
    • twg docs query --since <duration> [--account-id <id>] [--first <n>] is user activity history, not title/content search.
    • twg docs search "<topic>" [--limit <n>] is fuzzy Rovo discovery across Confluence and ready document connectors.
    • Never pass topic text to docs query; route that intent to docs search.
  • Keep user activity and fuzzy work discovery separate:
    • twg work query defaults to seven days of authored work; other activity requires --activity / --include-viewed.
    • twg work search "<topic>" is tenant-wide; use docs search for documents. Prefer it directly when fuzzy text reaches work query.
  • Use live help—twg help <terms> then twg help describe <path>—before guessing grammar; namespace help is not executable.
  • Resolve URLs, keys, ARIs, names, and people, then hydrate stable IDs.
  • Jira: jira workitem search <text...> for Jira fuzzy text, jira workitem query --jql <jql> for structured JQL, and search <text...> --app jira for semantic discovery.
  • Command shape guardrails:
    • Known Jira/Atlas keys are positional for jira workitem get, goals get, and projects get; --key is compatibility only.
    • work query is user activity (--scope me|user), never --scope global; use work search for topics and advertised filters such as --types.
    • assets search is shallow: inspect schemas/types, shortlist owners, then batch assets query/assets object query with --account-id.
  • Keep projection and product-native commands separate; do not borrow unadvertised flags. Use search-code for indexed code. Unless the user explicitly scopes a code host, omit --app so all available indexed SCM surfaces are searched; repeated --app values are supported for an explicit multi-host scope. Apply --workspace only when a known tenant boundary is useful, and --repo only as a discovery anchor rather than proof that the full implementation lives there. De-duplicate mirrors, widen after generated-doc or incomplete hits, then fetch selected source files.

Load The Narrowest Companion

Use a concrete key, URL, ARI, slug, account ID, name, topic, me, or window.

  • ../twg-jira/SKILL.md for Jira; ../twg-confluence/SKILL.md for Confluence edits.
  • ../twg-status-rollups/SKILL.md for status; ../twg-context-discovery/SKILL.md for context, dependencies, and graphs.
  • ../twg-agentic-search/SKILL.md for fuzzy Rovo/company-knowledge search.
  • ../twg-responsibility-routing/SKILL.md for ownership, approval, and escalation.
  • ../twg-engineering-work/SKILL.md for code search, PRs, and reviews; ../twg-jira-resolve-merged-work/SKILL.md for stale Jira work backed by merged PRs.
  • ../twg-operational-health/SKILL.md for handoffs, reliability, incidents, assets, staffing, and risk.

Rules

  • Never guess IDs, flags, slugs, ARIs, object IDs, or mutation contracts.
  • For product writes, load the product skill and follow live help.
  • Avoid local inspection, caches, schema probes, or diagnostics unless local state is requested.
  • For writes, read current state and state the mutation unless execution was requested.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Twg AI skill do?

Root TWG CLI skill for Atlassian work-data tasks. Use typed commands for known anchors; use live `twg help` only when command shape or output contract is uncertain.

Why use Twg on TypingMind?

Because you install it once and use it with any model. Twg is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Twg in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/developer/skills/atlassian/twg. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Twg?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Twg?

As many as you like. As long as a model supports skills, you can use Twg with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Twg AI skill free?

Yes. It is published on GitHub by zenobi-us under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
garrytan logo

Qa Only

garrytan
CommunityPopular

Report-only QA testing. (gstack)

19.9K
133.5K
1 files
View
garrytan logo

Setup Browser Cookies

garrytan
CommunityPopular

Import cookies from your real Chromium browser into the headless browse session. (gstack)

19.9K
133.5K
1 files
View
JuliusBrussee logo

Investigate First

JuliusBrussee
CommunityPopular

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

6.2K
106.3K
1 files
View
JuliusBrussee logo

Surgical Patch

JuliusBrussee
CommunityPopular

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

6.2K
106.3K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇