New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Flow Context

by flowexec in flowexec/flow

This project uses flow for automation. An agent skill from flowexec/flow.

Apache-2.0Auto-check passedDevOps & Cloud

Install Flow Context

skills CLI
$ npx skills add flowexec/flow --skill flow-context -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install flowexec/flow flow-context --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/flowexec/flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/flow-context .claude/skills/flow-context && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
flow-context
GitHub stars
137
Token cost
~654 tokens
SKILL.md length
305 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

This project uses flow for automation. An agent skill from flowexec/flow.

  • Works in 5 steps: Named task? (build, test, lint,… → Arbitrary one-off command? (a git ...,… → One-off is Python? → mcpflowrun_python… → …
  • Tasks that involve Secrets management
  • SKILL.md covers Running work — pick the…, Key executables in this repo and Context & authoring
  • Calls git, go and python

What it does

Flow Context is an agent skill from flowexec/flow. This project uses flow for automation. When asked to build, test, run, deploy, lint, generate, or perform any dev task — or to run any one-off shell command — prefer the flow MCP tools over raw Bash so the work runs with workspace env/secrets and is recorded in flow's history.

Its SKILL.md is about 650 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Secrets management, MCP servers and Linting and formatting. It works with Bash, Model Context Protocol and Python. The repository describes itself as: Local-first CLI for defining and running your project's workflows. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Secrets management
  • Tasks that involve MCP servers
  • Tasks that involve Linting and formatting

Example prompts

  • “/flow-context”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Named task? (build, test, lint, validate, generate, deploy, …) → mcpflowlist_executables to find it, then mcpflowexecute with its verb +…
  2. Arbitrary one-off command? (a git ..., go test ./..., a script) → mcpflowrun_command with the command and a short label. This is preferred…
  3. One-off is Python? → mcpflowrun_python with code and a short label, rather than python -c or a scratch .py file. flow resolves the…
  4. Something richer than one command? (a serial/parallel batch, an HTTP request) → mcpflowrun_executable with an inline spec.
  5. Only fall back to Bash when a command genuinely shouldn't be recorded or flow isn't the right tool (e.g. interactive/TTY programs).

What it can do on your machine

Read from SKILL.md and the folder at commit 0583ac5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • go
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Flow Context loads about 654 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~654

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from flowexec/flow at commit 0583ac5, republished under its Apache-2.0 licence (© flowexec). 305 words, ~654 tokens.

Download SKILL.mdSave it as .claude/skills/flow-context/SKILL.md (or your agent's skills folder).
name
flow-context
description
This project uses flow for automation. When asked to build, test, run, deploy, lint, generate, or perform any dev task — or to run any one-off shell command — prefer the flow MCP tools over raw Bash so the work runs with workspace env/secrets and is recorded in flow's history.
user-invocable
false

This repository uses flow for all development automation. The mcp__flow__* MCP tools are available — prefer them over raw Bash for anything runnable, so it executes with the workspace's environment and secrets and is captured in flow's execution history.

Running work — pick the closest tool

  1. Named task? (build, test, lint, validate, generate, deploy, …) → mcp__flow__list_executables to find it, then mcp__flow__execute with its verb + name. Don't hand-roll a shell command a flow executable already covers.
  2. Arbitrary one-off command? (a git ..., go test ./..., a script) → mcp__flow__run_command with the command and a short label. This is preferred over raw Bash: it runs with workspace env/secrets and lands in flow logs with provenance. Pass commands (array) + mode (serial/parallel) to run several in one call.
  3. One-off is Python? → mcp__flow__run_python with code and a short label, rather than python -c or a scratch .py file. flow resolves the workspace's virtualenv, so imports see the project's dependencies, and tracebacks report real line numbers.
  4. Something richer than one command? (a serial/parallel batch, an HTTP request) → mcp__flow__run_executable with an inline spec.
  5. Only fall back to Bash when a command genuinely shouldn't be recorded or flow isn't the right tool (e.g. interactive/TTY programs).

Key executables in this repo

Common refs: test unit, test e2e, lint, validate, generate, build binary. Use mcp__flow__list_executables to discover current names — don't assume.

Context & authoring

  • Call mcp__flow__get_info at the start of a session, or when you need schema URLs to author .flow files.
  • Author or edit flow files with mcp__flow__write_flowfile (validates against the schema server-side) rather than writing YAML by hand.
  • Runs are scoped to the current workspace by default; run_command/run_python/run_executable accept an optional workspace to target another without switching the global current workspace.
  • To review what you've run this session, call mcp__flow__get_execution_logs with mine: true; source/session/status filter history more broadly (also flow logs --source mcp --session <id>).

© flowexec, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/flow-context of flowexec/flow.

Open the folder on GitHubat commit 0583ac5

Compare with similar skills

Flow Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Flow Context compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flow Context this skillflowexec/flow137—~654Automated safety check: PassApache-2.0
Agent Observability Eval Bootstrapdatadog-labs/agent-skills177—~25kAutomated safety check: PassMIT
Ue Code AuthoringJasonMa0012/MooaToon749—~1.9kAutomated safety check: NotesCustom licence
Ue Live DebuggingJasonMa0012/MooaToon749—~2.9kAutomated safety check: NotesCustom licence
Unraiddinglebear-ai/unraid135—~5.4kAutomated safety check: NotesMIT
Zizkadb ReleaseZIZKA-AI-SL/ZizkaDB124—~399Automated safety check: PassCustom licence

Similar skills

  • Agent Observability Eval Bootstrap

    datadog-labs/agent-skills

    Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit…

    177 GitHub stars~25k tokensUpdated 5 days ago
    DevOps & CloudAuto-check passed

  • Ue Code Authoring

    JasonMa0012/MooaToon

    A skill your agent uses when writing or modifying UE C++ (classes, actors, components, subsystems, interfaces, function libraries) with Rider MCP available.

    749 GitHub stars~1.9k tokensUpdated 19 days ago
    DevelopmentAuto-check: notes

  • Ue Live Debugging

    JasonMa0012/MooaToon

    A skill your agent uses when debugging UE C++ crashes, runtime bugs, or unexpected behavior with Rider MCP available.

    749 GitHub stars~2.9k tokensUpdated 19 days ago
    DevelopmentAuto-check: notes

  • Unraid

    dinglebear-ai/unraid

    This skill should be used when the user mentions Unraid, asks to check server health, monitor array or disk status, list or restart Docker containers, start or stop VMs, read system logs, check…

    135 GitHub stars~5.4k tokensUpdated 3 days ago
    DevOps & CloudAuto-check: notes

  • Zizkadb Release

    ZIZKA-AI-SL/ZizkaDB

    Bumps versions, runs pre-push verification, and publishes ZizkaDB SDK and MCP packages.

    124 GitHub stars~399 tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Zizkadb Test

    ZIZKA-AI-SL/ZizkaDB

    Run the full ZizkaDB test suite across all layers — lint, Python unit tests, SDK tests, MCP tests, TypeScript tests, and dashboard build verification.

    124 GitHub stars~358 tokensUpdated yesterday
    Testing & QAAuto-check passed

More from flowexec/flow

  • New Command

    flowexec/flow

    Scaffold a new Cobra CLI command following the project's patterns.

    137 GitHub stars~404 tokensUpdated 6 days ago
    Auto-check passed

  • New Exec Type

    flowexec/flow

    Add a new executable type to the flow runner (a new kind of automation block users can define in .flow files).

    137 GitHub stars~462 tokensUpdated 6 days ago
    Auto-check passed

  • PR Ready

    flowexec/flow

    Run a pre-PR readiness check and report READY or NOT READY. An agent skill from flowexec/flow.

    137 GitHub stars~384 tokensUpdated 6 days ago
    Auto-check passed

  • Validate

    flowexec/flow

    Run flow validate and fix any failures. An agent skill from flowexec/flow.

    137 GitHub stars~375 tokensUpdated 6 days ago
    Auto-check passed

Works with

Categories

Questions about Flow Context

What does Flow Context do?

This project uses flow for automation. An agent skill from flowexec/flow. Flow Context is an agent skill from flowexec/flow. This project uses flow for automation.

When should I use Flow Context?

Flow Context fits situations like: tasks that involve Secrets management; tasks that involve MCP servers; tasks that involve Linting and formatting.

How do I install Flow Context in Claude Code?

Run `npx skills add flowexec/flow --skill flow-context -a claude-code`. Or copy the skill folder (.claude/skills/flow-context in flowexec/flow) into .claude/skills/flow-context in your project. Claude Code loads it when a task matches its description.

How do I install Flow Context in Codex?

Run `npx skills add flowexec/flow --skill flow-context -a codex`. Or copy the skill folder (.claude/skills/flow-context in flowexec/flow) into .agents/skills/flow-context in your project. Codex loads it when a task matches its description.

Can I use Flow Context in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add flowexec/flow --skill flow-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flow-context, .gemini/skills/flow-context, .github/skills/flow-context and .opencode/skills/flow-context in your project.

What does Flow Context need to run?

Going by SKILL.md and its folder, Flow Context needs the command-line tools its instructions call (git, go and python). Our summary lists: Python 3.

Does Flow Context access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Flow Context safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Flow Context use?

Flow Context is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flow Context use?

About 654 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Flow Context?

Skills that share tags, products or a category with Flow Context: Agent Observability Eval Bootstrap (datadog-labs/agent-skills, 177 stars), Ue Code Authoring (JasonMa0012/MooaToon, 749 stars), Ue Live Debugging (JasonMa0012/MooaToon, 749 stars) and Unraid (dinglebear-ai/unraid, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flow Context?

flowexec (a GitHub organization) maintains it in flowexec/flow, which has 137 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 1, 2026.

Source: flowexec/flow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.