Agent skill

Workflow

Starts and manages autonomous agent workflows. An agent skill from softspark/ai-toolkit.

Apache-2.0Auto-check: notesAgent Workflows

Install Workflow

skills CLI

$ npx skills add softspark/ai-toolkit --skill workflow -a claude-code

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

GitHub CLI

$ gh skill install softspark/ai-toolkit workflow --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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/workflow .claude/skills/workflow && 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/

Paste into Claude Code

Install the "workflow" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow into .claude/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add softspark/ai-toolkit --skill workflow -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install softspark/ai-toolkit workflow --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/skills/workflow .agents/skills/workflow && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "workflow" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow into .agents/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add softspark/ai-toolkit --skill workflow -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install softspark/ai-toolkit workflow --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/skills/workflow .cursor/skills/workflow && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "workflow" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow into .cursor/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/softspark/ai-toolkit.git --path app/skills/workflow

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add softspark/ai-toolkit --skill workflow -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install softspark/ai-toolkit workflow --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/skills/workflow .gemini/skills/workflow && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "workflow" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow into .gemini/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install softspark/ai-toolkit workflow

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add softspark/ai-toolkit --skill workflow -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/skills/workflow .github/skills/workflow && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "workflow" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow into .github/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add softspark/ai-toolkit --skill workflow -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install softspark/ai-toolkit workflow --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/skills/workflow .opencode/skills/workflow && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "workflow" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/workflow into .opencode/skills/workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: workflow
GitHub stars: 179
Token cost: ~3.4k tokens
SKILL.md length: 336 words
Files: 1
Skills in repo: 112
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Starts and manages autonomous agent workflows. An agent skill from softspark/ai-toolkit.

Works in 5 steps: Select workflow type → Define success criteria (MANDATORY) → Spawn agents via Agent tool → …
Tasks that involve Autonomous loops
SKILL.md covers Autonomous software delivery, Step 1 — Select workflow type, Step 2 — Define success… and Step 3 — Spawn agents via…, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Workflow is an agent skill from softspark/ai-toolkit. Starts and manages autonomous agent workflows. Triggers: workflow, start workflow, autonomous agents, agent pipeline.

Its SKILL.md is about 3.4k 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 Agent Workflows, covering Autonomous loops. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.

When your agent uses it

Tasks that involve Autonomous loops

Example prompts

“Use the workflow skill to start and manages autonomous agent workflows. An agent skill from softspark/ai-toolkit”
“/workflow”

Requirements

Docker
Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep, Agent, TeamCreate, TeamDelete, SendMessage, TaskCreate, TaskList, TaskUpdate, TaskGet, TaskOutput, TaskStop

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Select workflow type
Define success criteria (MANDATORY)
Spawn agents via Agent tool
Track status
Exit gate

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Bash
- Read
- Write
- Edit
- Glob
- Grep
- Agent
- TeamCreate
- TeamDelete
- SendMessage
…and 6 more on the same allowed-tools line.
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 yaml).
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

Workflow loads about 3.4k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 336 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~32
When it runs · the whole SKILL.md, loaded when a task matches: ~3.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, TeamCreate, TeamDelete, SendMessage, TaskCreate, TaskLis

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 softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 336 words, ~3,445 tokens.

Download SKILL.mdSave it as .claude/skills/workflow/SKILL.md (or your agent's skills folder).

name: workflow
description: Starts and manages autonomous agent workflows. Triggers: workflow, start workflow, autonomous agents, agent pipeline.
allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, TeamCreate, TeamDelete, SendMessage, TaskCreate, TaskList, TaskUpdate, TaskGet, TaskOutput, TaskStop
user-invocable: true
effort: high
argument-hint: [type] [task description]
context: fork
agent: orchestrator
model: opus

/workflow - Autonomous Agent Workflow

$ARGUMENTS

<!-- CLAUDE_CODE_ONLY_START -->

Only in Claude Code, apply the model-routing-patterns skill when choosing executors or creating agent definitions. Delegate to codex:codex-rescue only when its plugin is installed, enabled and callable in this session. Otherwise use the installed native agents and their configured models. A context without the Agent tool returns the dispatch decision to its supervisor; it does not invent a tool or bypass the client. Preserve explicit user choices and verify actual completion before accepting a delegated result.

<!-- CLAUDE_CODE_ONLY_END -->

Autonomous software delivery

For autonomous-development, or an explicit request to carry a brief, spec, issue or existing PR through implementation, review, QA and required CI, invoke /autonomous-dev with the original task. It owns the run, durable state and completion gate; do not also start the generic workflow below or initialize a second run. Preserve existing approvals and inherited model/permission settings. Use /autonomous-dev resume <run-id> for an interrupted run and /autonomous-dev status <run-id> for read-only progress.

Step 1 — Select workflow type

Is production DOWN?               → incident-response
Performance degraded >50%?        → performance-optimization
Bug spanning multiple layers?     → debugging
Warning / trend?                  → proactive-troubleshooting
Planned infra change?             → infrastructure-change
Planned app deploy?               → application-deploy
New feature (full stack)?         → feature-development
New feature (backend only)?       → backend-feature
New feature (frontend only)?      → frontend-feature
New API endpoint?                 → api-design
Schema / migration change?        → database-evolution
Boost test coverage?              → test-coverage
Security assessment?              → security-audit
Exploring unfamiliar codebase?    → codebase-onboarding
Technical research / spike?       → spike
Autonomous task-to-PR delivery?    → autonomous-development (autonomous-dev)

Step 2 — Define success criteria (MANDATORY)

Cannot proceed without:

yaml

Deliverables: [what outputs are expected]
Verification: [how to verify — tests, metrics, commands]
Definition of done: [quality bar]

Present to user and wait for approval.

Step 3 — Spawn agents via Agent tool

Launch agents in parallel where independent, sequentially where dependent. Use the Agent tool — never do the work inline.

Existing workflows

debugging

# Sequential diagnosis:
Agent(subagent_type="debugger",              prompt="Diagnose issue, 5 Whys, propose solution options. READ-ONLY.")
Agent(subagent_type="explorer-agent",        prompt="Trace call path across layers. READ-ONLY.")
# Parallel fix:
Agent(subagent_type="backend-specialist",    prompt="Implement fix. Own files: src/")
Agent(subagent_type="test-engineer",         prompt="Write regression test. Own files: tests/")
# Sequential:
Agent(subagent_type="documenter",            prompt="Document in kb/troubleshooting/ if recurring.")

incident-response

Agent(subagent_type="incident-responder",    prompt="Triage, root cause, immediate mitigation. READ-ONLY.")
# After triage:
Agent(subagent_type="backend-specialist",    prompt="Apply fix. Own files: src/")
Agent(subagent_type="documenter",            prompt="Write postmortem (MANDATORY). Own files: kb/")

performance-optimization

Agent(subagent_type="performance-optimizer", prompt="Profile, identify bottlenecks, propose fixes. READ-ONLY.")
Agent(subagent_type="backend-specialist",    prompt="Implement optimizations. Own files: src/")
Agent(subagent_type="test-engineer",         prompt="Benchmark before/after. Own files: tests/benchmarks/")
Agent(subagent_type="documenter",            prompt="Document baseline and results. Own files: kb/")

infrastructure-change

Agent(subagent_type="infrastructure-architect", prompt="Design change, create architecture note. Own files: docs/")
Agent(subagent_type="devops-implementer",       prompt="Implement infra changes. Own files: docker/, .github/, infra/")
Agent(subagent_type="security-auditor",         prompt="Review for security issues. READ-ONLY.")
Agent(subagent_type="test-engineer",            prompt="Smoke tests and health checks. Own files: tests/")
Agent(subagent_type="documenter",               prompt="Runbook + deployment docs. Own files: kb/")

application-deploy

Agent(subagent_type="devops-implementer",    prompt="Execute deployment. Own files: .github/, scripts/")
Agent(subagent_type="test-engineer",         prompt="Post-deploy smoke tests.")
Agent(subagent_type="documenter",            prompt="Release notes. Own files: kb/")

proactive-troubleshooting

Agent(subagent_type="debugger",              prompt="Investigate warning/trend, assess risk. READ-ONLY.")
Agent(subagent_type="performance-optimizer", prompt="Check performance metrics. READ-ONLY.")
Agent(subagent_type="backend-specialist",    prompt="Apply preventive fix if needed. Own files: src/")
Agent(subagent_type="documenter",            prompt="Update monitoring/alerting docs. Own files: kb/")

New workflows

feature-development — full stack feature, plan → implement → test → ship

# Sequential planning:
Agent(subagent_type="project-planner",       prompt="Requirements, acceptance criteria, task breakdown. Own files: docs/")
Agent(subagent_type="explorer-agent",        prompt="Find integration points in codebase. READ-ONLY.")
# Parallel implementation:
Agent(subagent_type="backend-specialist",    prompt="API routes, business logic, data layer. Own files: src/api/, src/services/")
Agent(subagent_type="frontend-specialist",   prompt="UI components, state management. Own files: src/components/, src/pages/")
Agent(subagent_type="database-architect",    prompt="Schema changes + migrations if needed. Own files: migrations/")
# Parallel validation:
Agent(subagent_type="test-engineer",         prompt="Unit + integration tests. Own files: tests/")
Agent(subagent_type="security-auditor",      prompt="Security review of new attack surface. READ-ONLY.")
# Sequential finalization:
Agent(subagent_type="documenter",            prompt="API docs, KB update, changelog. Own files: kb/, docs/")

backend-feature — backend only: API + logic + tests

Agent(subagent_type="explorer-agent",        prompt="Find integration points and patterns. READ-ONLY.")
Agent(subagent_type="backend-specialist",    prompt="Implement endpoint + business logic. Own files: src/")
Agent(subagent_type="database-architect",    prompt="Schema/query changes if needed. Own files: migrations/")
Agent(subagent_type="test-engineer",         prompt="Unit + integration tests. Own files: tests/")
Agent(subagent_type="security-auditor",      prompt="Auth/authz, input validation review. READ-ONLY.")

frontend-feature — UI feature: component + state + tests

Agent(subagent_type="explorer-agent",        prompt="Find existing components and patterns. READ-ONLY.")
Agent(subagent_type="frontend-specialist",   prompt="Build component, state, routing. Own files: src/components/, src/pages/")
Agent(subagent_type="test-engineer",         prompt="Component tests, E2E if needed. Own files: tests/")
Agent(subagent_type="documenter",            prompt="Component docs / Storybook if applicable.")

api-design — design + implement + test + document a new API

# Sequential design:
Agent(subagent_type="tech-lead",             prompt="API contract, versioning, error format. Own files: docs/api-spec.md")
Agent(subagent_type="database-architect",    prompt="Data model for new resources. Own files: migrations/")
# Parallel implementation + validation:
Agent(subagent_type="backend-specialist",    prompt="Implement endpoint, validation, business logic. Own files: src/")
Agent(subagent_type="test-engineer",         prompt="Contract tests, integration tests. Own files: tests/")
Agent(subagent_type="security-auditor",      prompt="Auth/authz, rate limiting, input validation. READ-ONLY.")
Agent(subagent_type="performance-optimizer", prompt="Response time benchmark. READ-ONLY.")
# Sequential:
Agent(subagent_type="documenter",            prompt="OpenAPI spec, API reference docs. Own files: docs/")

database-evolution — schema change: design + migrate + update code + validate

# Sequential analysis:
Agent(subagent_type="database-architect",    prompt="Design schema change, migration + rollback plan. Own files: migrations/")
Agent(subagent_type="explorer-agent",        prompt="Find all code referencing affected tables/columns. READ-ONLY.")
# Parallel implementation:
Agent(subagent_type="backend-specialist",    prompt="Update ORM models, queries, data access layer. Own files: src/")
Agent(subagent_type="test-engineer",         prompt="Migration tests, data integrity checks. Own files: tests/")
# Parallel validation:
Agent(subagent_type="performance-optimizer", prompt="EXPLAIN ANALYZE on new queries, index efficiency. READ-ONLY.")
Agent(subagent_type="security-auditor",      prompt="SQL injection vectors in new query patterns. READ-ONLY.")
# Sequential:
Agent(subagent_type="documenter",            prompt="Update schema docs, migration changelog. Own files: kb/")

test-coverage — systematically boost test coverage for a module

# Sequential analysis:
Agent(subagent_type="explorer-agent",        prompt="Map untested code paths, find coverage gaps. READ-ONLY.")
# Parallel writing:
Agent(subagent_type="test-engineer",         prompt="Write unit tests for uncovered functions. Own files: tests/unit/")
Agent(subagent_type="backend-specialist",    prompt="Add integration test fixtures, mock external services. Own files: tests/integration/")
# Sequential review:
Agent(subagent_type="code-reviewer",         prompt="Review test quality — no false positives, deterministic. READ-ONLY.")

security-audit — comprehensive multi-vector security assessment

# Sequential recon:
Agent(subagent_type="explorer-agent",        prompt="Map attack surface, entry points, data flows. READ-ONLY.")
# Parallel audit:
Agent(subagent_type="security-auditor",      prompt="Run /cve-scan first, then OWASP Top 10, injection, auth review. READ-ONLY.")
Agent(subagent_type="code-reviewer",         prompt="Secrets in code, error handling, logging gaps. READ-ONLY.")
Agent(subagent_type="devops-implementer",    prompt="Infra misconfig, Docker hardening, network. READ-ONLY.")
Agent(subagent_type="database-architect",    prompt="SQL injection vectors, access controls, encryption. READ-ONLY.")
# Sequential:
Agent(subagent_type="tech-lead",             prompt="Prioritize findings including CVE scan results, assign severity (CVSS).")
Agent(subagent_type="documenter",            prompt="Security audit report + CVE inventory + remediation checklist. Own files: kb/")

codebase-onboarding — understand an unfamiliar codebase fast (READ-ONLY)

# Parallel discovery:
Agent(subagent_type="explorer-agent",        prompt="Project structure, tech stack, entry points. READ-ONLY.")
Agent(subagent_type="tech-lead",             prompt="Architecture patterns, design decisions, conventions. READ-ONLY.")
Agent(subagent_type="database-architect",    prompt="Data model, relationships, migration history. READ-ONLY.")
# Parallel analysis:
Agent(subagent_type="test-engineer",         prompt="Test coverage, test patterns, CI pipeline. READ-ONLY.")
Agent(subagent_type="security-auditor",      prompt="Current security posture, credential management. READ-ONLY.")
# Sequential synthesis:
Agent(subagent_type="documenter",            prompt="Write onboarding guide + architecture overview. Own files: docs/ONBOARDING.md")

spike — time-boxed technical research to inform a decision

# Parallel research:
Agent(subagent_type="explorer-agent",        prompt="Existing codebase patterns relevant to decision. READ-ONLY.")
Agent(subagent_type="tech-lead",             prompt="Architecture implications, trade-off analysis. READ-ONLY.")
Agent(subagent_type="backend-specialist",    prompt="Implementation feasibility, proof of concept.")
# Sequential evaluation:
Agent(subagent_type="security-auditor",      prompt="Security implications of each option. READ-ONLY.")
Agent(subagent_type="performance-optimizer", prompt="Performance implications of each option. READ-ONLY.")
# Sequential decision:
Agent(subagent_type="tech-lead",             prompt="Comparison matrix, recommendation.")
Agent(subagent_type="documenter",            prompt="Write architecture note + spike findings. Own files: kb/reference/")

Step 4 — Track status

Event	Action
Agent started	`TaskUpdate(status="in_progress")`
Agent complete	`TaskUpdate(status="completed")`
Blocked	Document blocker, reassign or escalate

Step 5 — Exit gate

Workflow is NOT done until:

Tests pass
Documentation updated in kb/
Postmortem written (incident-response only)
Plan archived to kb/history/completed/

Devil's Advocate (workflows >1h)

Before implementation:

What could go wrong?
Hidden costs / tech debt?
At least 3 alternatives considered?

Files

Just SKILL.md in app/skills/workflow of softspark/ai-toolkit.

Open the folder on GitHubat commit d64db2b

Compare with similar skills

Workflow 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.

Workflow compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Workflow this skillsoftspark/ai-toolkit	179	—	~3.4k	Automated safety check: Notes	Apache-2.0	today
Show Me Your Work Decision Logcursor/plugins	10k	9 repos	~1.6k	Automated safety check: Pass	None	today
Autoresearch Iteration Loopuditgoenka/autoresearch	6.5k	1 repos	~2k	Automated safety check: Pass	MIT	1 mo ago
AutopilotYeachan-Heo/oh-my-claudecode	40k	1 repos	~4.4k	Automated safety check: Pass	MIT	today
Install Loop Engineeringcobusgreyling/loop-engineering	11k	1 repos	~648	Automated safety check: Pass	MIT	today
LoopyForward-Future/loopy	3.2k	—	~3.9k	Automated safety check: Pass	MIT	26 days ago

Similar skills

Show Me Your Work Decision Log
cursor/plugins
Official
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
10k GitHub starsUsed in 9 repos~1.6k tokens
Agent WorkflowsAuto-check passed
Autoresearch Iteration Loop
uditgoenka/autoresearch
Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.
6.5k GitHub starsUsed in 1 repo~2k tokens
Agent WorkflowsAuto-check passed
Autopilot
Yeachan-Heo/oh-my-claudecode
Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.
40k GitHub starsUsed in 1 repo~4.4k tokens
Agent WorkflowsAuto-check passed
Install Loop Engineering
cobusgreyling/loop-engineering
Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.
11k GitHub starsUsed in 1 repo~648 tokens
Agent WorkflowsAuto-check passed
Loopy
Forward-Future/loopy
Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication.
3.2k GitHub stars~3.9k tokensUpdated 26 days ago
Agent WorkflowsAuto-check passed
AI Performance Improvement Plan
tanweai/pua
Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.
20k GitHub starsUsed in 2 repos~6.9k tokens
Agent WorkflowsAuto-check passed

Questions about Workflow

What does Workflow do?

Starts and manages autonomous agent workflows. An agent skill from softspark/ai-toolkit. Workflow is an agent skill from softspark/ai-toolkit. Starts and manages autonomous agent workflows.

When should I use Workflow?

Workflow fits situations like: tasks that involve Autonomous loops.

How do I install Workflow in Claude Code?

Run `npx skills add softspark/ai-toolkit --skill workflow -a claude-code`. Or copy the skill folder (app/skills/workflow in softspark/ai-toolkit) into .claude/skills/workflow in your project. Claude Code loads it when a task matches its description.

How do I install Workflow in Codex?

Run `npx skills add softspark/ai-toolkit --skill workflow -a codex`. Or copy the skill folder (app/skills/workflow in softspark/ai-toolkit) into .agents/skills/workflow in your project. Codex loads it when a task matches its description.

Can I use Workflow 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 softspark/ai-toolkit --skill workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workflow, .gemini/skills/workflow, .github/skills/workflow and .opencode/skills/workflow in your project.

What does Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Workflow is instructions for the agent only. Our summary lists: Docker. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Glob, Grep, Agent, TeamCreate, TeamDelete, SendMessage, TaskCreate, TaskList, TaskUpdate, TaskGet, TaskOutput, TaskStop.

Does Workflow 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 Workflow safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Workflow use?

Workflow 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 Workflow use?

About 3.4k tokens (SKILL.md is roughly 14k 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 Workflow?

Skills that share tags, products or a category with Workflow: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Autoresearch Iteration Loop (uditgoenka/autoresearch, 6.5k stars), Autopilot (Yeachan-Heo/oh-my-claudecode, 40k stars) and Install Loop Engineering (cobusgreyling/loop-engineering, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workflow?

softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Workflow

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

/workflow - Autonomous Agent Workflow

Autonomous software delivery

Step 1 — Select workflow type

Step 2 — Define success criteria (MANDATORY)

Step 3 — Spawn agents via Agent tool

Existing workflows

New workflows

Step 4 — Track status

Step 5 — Exit gate

Devil's Advocate (workflows >1h)

Files

Compare with similar skills

Similar skills

More from softspark/ai-toolkit

Related

Questions about Workflow