Install
$ agentstack add skill-atlassian-twg-cli-twg ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
twg
TWG routing: use typed commands for anchors. If uncertain, inspect twg help , twg help describe , or twg help discover-skills "".
Overview
Load the narrowest workflow skill:
twg-status-rollupsfor status and decision-readiness; load it before
twg-engineering-work for PR rollups.
twg-context-discoveryfor dependencies, graphs, repos, and catch-ups.twg-agentic-searchfor fuzzy cross-product Rovo/company-knowledge research.twg-responsibility-routingfor owners, experts, approvers, and escalation.twg-engineering-workfor code search, PRs, contributors, and hot areas.twg-jira-resolve-merged-workfor stale Jira work backed by merged PRs.twg-operational-healthfor handoffs, incidents, Assets, staffing, meetings, and risk.twg-bench-litefor read-only single-prompt A/B comparisons.
Invocation And Output
Run twg . 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. Never use shell utilities or pipelines (jq, rg, date). Use compact/inline output, the prompt's timezone and window, and report gaps. Match the intent to the narrowest companion skill. Let that skill determine the typed route.
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.
Sandboxed Pipeline Logs
Pipeline logs can redirect to S3. If a sandboxed twg bb pipeline get, wait, grep, or tail log request has a network-blocked message, S3 hostname, or log-only HTTP 403 while metadata succeeds, treat it as a sandbox restriction, not an authentication failure.
Request an approved unsandboxed retry of that command only. If unavailable, give the user the exact terminal command; never request credentials or tokens.
Bounded Evidence Loop
Converge; prefer typed or product-native evidence.
- Classify the anchor: person, team, project, goal, workitem, page, repo, service, asset, or topic.
- Resolve once; fetch evidence that changes status, risk, decision, relationship, or action.
- Rank candidates, hydrate representative items, then synthesize.
- Stop after the first policy denial; stop after the same auth, ACL, contract, or backend error twice.
Command Discovery
- Use familiar command families:
resolve,rovo search,
user, org-tree, work query, work search, pull-requests, jira, confluence, docs, context, responsibility, goals, projects, assets, and trello.
- Use
twg rovo search "" [--limit ]for top-K discovery; explicit--apppreflights. - For fuzzy Trello discovery, use
twg trello search "" --limit 20; no workspace scope. - For Rovo connectors, use
twg rovo list-apps -o json(list-connectorsalias), then explicittwg rovo search ... --app; follow its auth action ortwg rovo auth. - Keep document relationship history and fuzzy discovery separate:
twg docs query --since [--account-id ] [--first ]is user activity history, not title/content search.twg docs search "" [--limit ]is fuzzy Rovo discovery across Confluence and ready document connectors.- Never pass topic text to
docs query; route that intent todocs search. - Keep user activity and fuzzy work discovery separate:
twg work querydefaults to seven days of authored work; other activity requires--activity/--include-viewed.twg work search ""is tenant-wide; usedocs searchfor documents. Prefer it directly when fuzzy text reacheswork query.- Use live help—
twg helpthentwg help describe—before guessing grammar; namespace help is not executable. - Resolve URLs, keys, ARIs, names, and people, then hydrate stable IDs.
- Jira:
jira workitem searchfor Jira fuzzy text,jira workitem query --jqlfor structured JQL, androvo search --app jirafor semantic discovery. - Command shape guardrails:
- Known Jira/Atlas keys are positional for
jira workitem get,goals get, andprojects get;--keyis compatibility only. work queryis user activity (--scope me|user), never--scope global; usework searchfor topics and advertised filters such as--types.- For inferred teams (
ari:cloud:graph::jiraTeam/...orari:cloud:graph-store::inferred-team/...), seereferences/inferred-teams.mdand use explicit--include-inferred. - Use
search-code; omit--appso all available indexed SCM surfaces are searched; use--repoonly as a discovery anchor; widen after generated-doc or incomplete hits.
Assets / CMDB graph
Traversal (object↔owner/team, Jira↔object) → assets graph; see references/ASSETS_GRAPH.md. No hop → assets search / assets query --aql / assets object get.
Load The Narrowest Companion
Use a concrete key, URL, ARI, slug, account ID, name, topic, me, or window.
../twg-jira/SKILL.mdfor Jira;../twg-confluence/SKILL.mdfor Confluence edits.../twg-status-rollups/SKILL.mdfor status;../twg-context-discovery/SKILL.md
for context, dependencies, and graphs.
../twg-agentic-search/SKILL.mdfor fuzzy Rovo/company-knowledge search.../twg-responsibility-routing/SKILL.mdfor ownership, approval, and escalation.../twg-engineering-work/SKILL.mdfor code search, PRs, and reviews;
../twg-jira-resolve-merged-work/SKILL.md for stale Jira work backed by merged PRs.
../twg-operational-health/SKILL.mdfor 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.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: atlassian
- Source: atlassian/twg-cli
- License: Apache-2.0
- Homepage: https://teamwork-graph.atlassian.com/cli/install
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.