Updated 1d ago
by kaisa-kucherenko
claude-code-flow
My working Claude Code setup: output styles, hooks, skills, agents
22 GitHub stars (22)
+2 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | +2 |
- 6 skills (6 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add kaisa-kucherenko/claude-code-flow
Asks which skills and agents to install. Just one: npx skills add kaisa-kucherenko/claude-code-flow --skill adr — add -g for every project.
Claude Code
git clone https://github.com/kaisa-kucherenko/claude-code-flowcp -r "claude-code-flow/skills/adr" ~/.claude/skills/
Copies the adr skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add kaisa-kucherenko/claude-code-flow
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
adr
Architecture Decision Record — structured approach to making architectural decisions for complex features. Use when: user needs to design a new feature that touches multiple layers (DB, API, frontend, security), user says '/adr', 'architectural decisions', 'decision tree', 'архітектурні рішення', 'давай продумаємо архітектуру', 'треба прийняти рішення по архітектурі', or when a feature is too com…
skills/adr/SKILL.md on GitHub (opens in a new tab) -
handoff
Create or update a session handoff file so a fresh session continues seamlessly where this one stopped. Triggers: "/handoff", "make a handoff", "update the handoff", "add to the handoff", "is the handoff current?", "зроби хендоф", "онови хендоф", "запиши в хендоф" (add triggers in your own language). Create ONLY on explicit request (never unprompted); once the file exists, keep it current through…
skills/handoff/SKILL.md on GitHub (opens in a new tab) -
implement
Runs ONE phase of a phase spec (written by /spec) through the full cycle: find the next phase from the live handoff, brief the user first, launch the implementer, freeze the tree, gate the diff against the phase's Acceptance, external review of the user's choice, local testing, commit, mark done, update the handoff. Triggers: "/implement" (next phase from the handoff), "/implement N", "фаза N", "…
skills/implement/SKILL.md on GitHub (opens in a new tab) -
pickup
Start a fresh session from a handoff file written by /handoff — find it, read it, verify it against current reality, and begin the NEXT step. Triggers: "/pickup", "pick up the handoff", "continue from the handoff", "підхопи хендоф", "продовжуй з хендофу" (add triggers in your own language), or a session opening with an @-mentioned HANDOFF file. Counterpart of /handoff.
skills/pickup/SKILL.md on GitHub (opens in a new tab) -
spec
Turns a closed ADR into a phase spec an LLM implementer executes phase by phase: cuts, orders and describes — decides nothing (the ADR did), implements nothing (the implementer agents do). Triggers: "/spec", "спека", "напиши спеку", "спека фаз", "нарізка фаз", "write the spec", "phase spec". Requires an ADR with no decision left PENDING (each DECIDED or DROPPED) and its review closed — without on…
skills/spec/SKILL.md on GitHub (opens in a new tab) -
twix
Two-reviewer pass on the current diff, then one merged verdict — the house rules for every review panel live here. Presets: "твікс" / "/twix" = Agatha (deep Claude) + Arthur (Codex); "твікс лайт" / "twix light" = Arthur + Dash (fast, no Fable). Names in the trigger override the preset ("твікс Агата і Деш"). For the full three-reviewer panel with synthesis use the precogs workflow — it follows the…
skills/twix/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.