Agent skill

Taskflow

by EvanWangZ in EvanWangZ/vela

A skill your agent uses when work should span one or more detached tasks but still behave like one job with a single owner context.

MITAuto-check passed

Install Taskflow

skills CLI
$ npx skills add EvanWangZ/vela --skill taskflow -a claude-code

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

GitHub CLI
$ gh skill install EvanWangZ/vela taskflow --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/EvanWangZ/vela.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/taskflow .claude/skills/taskflow && 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
taskflow
GitHub stars
110
Used in
2 other repos
Token cost
~1.3k tokens
SKILL.md length
410 words
Files
3
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when work should span one or more detached tasks but still behave like one job with a single owner context.

  • Works in 6 steps: createManaged(...) → runTask(...) → setWaiting(...) when waiting on a person… → …
  • Work should span one
  • SKILL.md covers When to use it, What TaskFlow owns, Current runtime shape and Design constraints, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Taskflow is an agent skill from EvanWangZ/vela. Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files.

The repository describes itself as: Velaclaw — control plane for team AI. The licence is MIT.

When your agent uses it

  • Work should span one
  • More detached tasks but still behave like one job with a single owner context

Example prompts

  • “/taskflow”

Workflow steps

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

  1. createManaged(...)
  2. runTask(...)
  3. setWaiting(...) when waiting on a person or an external system
  4. resume(...) when work can continue
  5. finish(...) or fail(...)
  6. requestCancel(...) or cancel(...) when the whole job should stop

What it can do on your machine

Read from SKILL.md and the folder at commit bd323cc. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

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

  • Network

    No URLs in SKILL.md.

    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

Taskflow loads about 1.3k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 410 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 EvanWangZ/vela at commit bd323cc, republished under its MIT licence (© EvanWangZ). 410 words, ~1,252 tokens.

Download SKILL.mdSave it as .claude/skills/taskflow/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
taskflow
description
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.

TaskFlow

Use TaskFlow when a job needs to outlive one prompt or one detached run, but you still want one owner session, one return context, and one place to inspect or resume the work.

When to use it

  • Multi-step background work with one owner
  • Work that waits on detached ACP or subagent tasks
  • Jobs that may need to emit one clear update back to the owner
  • Jobs that need small persisted state between steps
  • Plugin or tool work that must survive restarts and revision conflicts cleanly

What TaskFlow owns

  • flow identity
  • owner session and requester origin
  • currentStep, stateJson, and waitJson
  • linked child tasks and their parent flow id
  • finish, fail, cancel, waiting, and blocked state
  • revision tracking for conflict-safe mutations

It does not own branching or business logic. Put that in Lobster, acpx, or the calling code.

Current runtime shape

Canonical plugin/runtime entrypoint:

  • api.runtime.tasks.flow
  • api.runtime.taskFlow still exists as an alias, but api.runtime.tasks.flow is the canonical shape

Binding:

  • api.runtime.tasks.flow.fromToolContext(ctx) when you already have trusted tool context with sessionKey
  • api.runtime.tasks.flow.bindSession({ sessionKey, requesterOrigin }) when your binding layer already resolved the session and delivery context

Managed-flow lifecycle:

  1. createManaged(...)
  2. runTask(...)
  3. setWaiting(...) when waiting on a person or an external system
  4. resume(...) when work can continue
  5. finish(...) or fail(...)
  6. requestCancel(...) or cancel(...) when the whole job should stop
Show full SKILL.md (192 more words)Show less

Design constraints

  • Use managed TaskFlows when your code owns the orchestration.
  • One-task mirrored flows are created by core runtime for detached ACP/subagent work; this skill is mainly about managed flows.
  • Treat stateJson as the persisted state bag. There is no separate setFlowOutput or appendFlowOutput API.
  • Every mutating method after creation is revision-checked. Carry forward the latest flow.revision after each successful mutation.
  • runTask(...) links the child task to the flow. Use it instead of manually creating detached tasks when you want parent orchestration.

Example shape

ts
const taskFlow = api.runtime.tasks.flow.fromToolContext(ctx);

const created = taskFlow.createManaged({
  controllerId: "my-plugin/inbox-triage",
  goal: "triage inbox",
  currentStep: "classify",
  stateJson: {
    businessThreads: [],
    personalItems: [],
    eodSummary: [],
  },
});

const classify = taskFlow.runTask({
  flowId: created.flowId,
  runtime: "acp",
  childSessionKey: "agent:main:subagent:classifier",
  runId: "inbox-classify-1",
  task: "Classify inbox messages",
  status: "running",
  startedAt: Date.now(),
  lastEventAt: Date.now(),
});

if (!classify.created) {
  throw new Error(classify.reason);
}

const waiting = taskFlow.setWaiting({
  flowId: created.flowId,
  expectedRevision: created.revision,
  currentStep: "await_business_reply",
  stateJson: {
    businessThreads: ["slack:thread-1"],
    personalItems: [],
    eodSummary: [],
  },
  waitJson: {
    kind: "reply",
    channel: "slack",
    threadKey: "slack:thread-1",
  },
});

if (!waiting.applied) {
  throw new Error(waiting.code);
}

const resumed = taskFlow.resume({
  flowId: waiting.flow.flowId,
  expectedRevision: waiting.flow.revision,
  status: "running",
  currentStep: "finalize",
  stateJson: waiting.flow.stateJson,
});

if (!resumed.applied) {
  throw new Error(resumed.code);
}

taskFlow.finish({
  flowId: resumed.flow.flowId,
  expectedRevision: resumed.flow.revision,
  stateJson: resumed.flow.stateJson,
});

Keep conditionals above the runtime

Use the flow runtime for state and task linkage. Keep decisions in the authoring layer:

  • business → post to Slack and wait
  • personal → notify the owner now
  • later → append to an end-of-day summary bucket

Operational pattern

  • Store only the minimum state needed to resume.
  • Put human-readable wait reasons in blockedSummary or structured wait metadata in waitJson.
  • Use getTaskSummary(flowId) when the orchestrator needs a compact health view of child work.
  • Use requestCancel(...) when a caller wants the flow to stop scheduling immediately.
  • Use cancel(...) when you also want active linked child tasks cancelled.

Examples

  • See skills/taskflow/examples/inbox-triage.lobster
  • See skills/taskflow/examples/pr-intake.lobster
  • See skills/taskflow-inbox-triage/SKILL.md for a concrete routing pattern

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

Files

SKILL.md and 2 other files in skills/taskflow of EvanWangZ/vela.

  • SKILL.md
  • examples/inbox-triage.lobster
  • examples/pr-intake.lobster

Open the folder on GitHubat commit bd323cc

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in EvanWangZ/vela, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Taskflow 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.

Taskflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Taskflow this skillEvanWangZ/vela1102 repos~1.3kAutomated safety check: PassMIT
TaskflowLeoYeAI/openclaw-master-skills2.2k—~6.5kAutomated safety check: PassMIT
TaskflowMelbourneDeveloper/dart_node113—~327Automated safety check: NotesNone
Span File Exportforcedotcom/salesforcedx-vscode1k—~2.2kAutomated safety check: PassBSD-3-Clause
Taskflow Inbox TriageKevin100202/Rocket-Design-and-Manufacturing-Automation-Program-from-Shenzhen22highschool1701 repos~642Automated safety check: PassNone
Otel Span Events To Logs Migrationollygarden/opentelemetry-agent-skills106—~1.8kAutomated safety check: PassApache-2.0

Similar skills

  • Taskflow

    LeoYeAI/openclaw-master-skills

    Structured project/task management for OpenClaw agents — markdown-first authoring, SQLite-backed querying, bidirectional sync, CLI, Apple Notes integration.

    2.2k GitHub stars~6.5k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Taskflow

    MelbourneDeveloper/dart_node

    Build and run the full TaskFlow demo stack (Express backend + React frontend + mobile)

    113 GitHub stars~327 tokensUpdated 23 days ago
    MobileAuto-check: notes
  • Span File Export

    forcedotcom/salesforcedx-vscode

    Use file-based span/log export for AI consumption. An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~2.2k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Taskflow Inbox Triage

    Kevin100202/Rocket-Design-and-Manufacturing-Automation-Program-from-Shenzhen22highschool

    Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.

    170 GitHub starsUsed in 1 repo~642 tokens
    Productivity & AutomationAuto-check passed
  • Otel Span Events To Logs Migration

    ollygarden/opentelemetry-agent-skills

    Migrate OpenTelemetry Span Events (AddEvent, RecordException, and language equivalents) to the Logs API following the accepted OTEP 4430 migration plan.

    106 GitHub stars~1.8k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed
  • Backend Conventions

    getsentry/sentry

    Official

    Sentry backend conventions for logging, tracing/spans, span/tag attribute naming, metrics tags, and the options system.

    45k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

More from EvanWangZ/vela

  • Wiki Maintainer

    EvanWangZ/vela

    Maintain the Velaclaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.

    110 GitHub stars~440 tokensUpdated 2 mo ago
    Auto-check passed
  • Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

    110 GitHub stars~269 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Taskflow

What does Taskflow do?

A skill your agent uses when work should span one or more detached tasks but still behave like one job with a single owner context. Taskflow is an agent skill from EvanWangZ/vela. Use when work should span one or more detached tasks but still behave like one job with a single owner context.

When should I use Taskflow?

Taskflow fits situations like: work should span one; more detached tasks but still behave like one job with a single owner context.

How do I install Taskflow in Claude Code?

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

How do I install Taskflow in Codex?

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

Can I use Taskflow 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 EvanWangZ/vela --skill taskflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/taskflow, .gemini/skills/taskflow, .github/skills/taskflow and .opencode/skills/taskflow in your project.

What does Taskflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Taskflow is instructions for the agent only.

Does Taskflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Taskflow 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 Taskflow use?

Taskflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Taskflow use?

About 1.3k tokens (SKILL.md is roughly 5k 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 Taskflow?

Skills that share tags, products or a category with Taskflow: Taskflow (LeoYeAI/openclaw-master-skills, 2.2k stars), Taskflow (MelbourneDeveloper/dart_node, 113 stars), Span File Export (forcedotcom/salesforcedx-vscode, 1k stars) and Taskflow Inbox Triage (Kevin100202/Rocket-Design-and-Manufacturing-Automation-Program-from-Shenzhen22highschool, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Taskflow?

EvanWangZ (a GitHub user) maintains it in EvanWangZ/vela, which has 110 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 21, 2026.

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