Install
$ agentstack add skill-lkim0402-agent-teamflow-teamflow-help ✓ 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
teamflow-help
Read AGENTS.md, then follow the workflow below. This workflow does not require .agent-teamflow; it works in any repo. Treat the user's remaining request text as $ARGUMENTS.
Print a digest of all agent-teamflow workflows. Run when a teammate has just installed agent-teamflow and forgot what's in it, or whenever someone asks "what does this give me?"
This skill is a static print — no file I/O, no config, no remote calls. It must be kept in sync manually when new commands are added (see CONTRIBUTING.md). The list below is the source of truth.
Run in the main conversation — this is interactive feedback for the user. Do not delegate this workflow.
Execution
Step 1. Print the digest verbatim
Output the block below exactly. Preserve column alignment so it renders cleanly in a terminal.
agent-teamflow — 9 workflows
Setup
/teamflow-init Bootstrap this repo (writes .agent-teamflow, optionally
creates personal integration branches on origin)
/teamflow-update Pull the latest agent-teamflow and re-register commands
/teamflow-help Print this list
Issue lifecycle
/issue Draft one or more branch-sized issues from a brain dump
/dispatch Split a brain dump across teammates, write a workflow log
/resolve Pick up your assigned issues, implement each in a
parallel worktree, batch-merge when done
/git-auto-merge Commit + push + merge into your lane + open PR to staging
/post-merge After a PR merges to staging, label linked issues as
"done in staging"
Review
/prod-check Pre-production diff review for impact, contracts, auth,
stability, and regressions
Docs: https://github.com/lkim0402/agent-teamflow
Quick start: README.md
Troubleshooting: SETUP.md (Troubleshooting + FAQ sections)
Contributing: CONTRIBUTING.md
Step 2. Add a contextual hint if relevant
After printing the digest, check whether .agent-teamflow exists at the repo root via test -f .agent-teamflow.
- If it does NOT exist: append one line —
Tip: this repo is not configured yet. Run /teamflow-init first. - If it DOES exist: append one line —
Tip: this repo is configured. Try /issue, /dispatch, or /resolve to start work.
That's the whole skill.
Hard rules
- Static output — do not invent workflows, do not omit workflows, do not reorder. The list reflects what
setupregisters user-scope; anything else would mislead. - No emojis.
- No file modifications. This skill is read-only.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: lkim0402
- Source: lkim0402/agent-teamflow
- License: MIT
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.