Multi-Skill Slash Command Workflows
Build one Claude Code slash command that chains installed skills with checked handoffs, context isolation, and safe restarts.
Before & after
Same prompt, same agent — the only difference is the skill.
Multi-step workflows are tedious to run manually. You could use a chaining approach to run several skills in sequence—market research first, then sales copy, then email drafts, social posts, and finally compile everything into a PDF. Each skill passes data to the next, so outputs connect. It requires some orchestration to set up. You'd need to define the data flow and make sure outputs from one skill feed into the next cleanly. What's your product and target audience?
SKILL CHAINING ORCHESTRATION SINGLE COMMAND: /launch-campaign product-name EXECUTION SEQUENCE (automatic) STEP 1: Market Research (research skill) → Analyze target audience, competitor landscape, pain points → Output: Customer persona JSON + market sizing + opportunity gaps → Time: 8 minutes STEP 2: Sales Copy (copywriting skill) → Consume research output → Write headline, subheading, feature bullets, CTA → Output: Polished copy blocks (JSON) + tone notes → Time: 4 minutes STEP 3: Email Sequence (email skill) → Consume research + copy output → Generate 3-email launch sequence: awareness, value, urgency → Output: Draft subject lines + email bodies → Time: 3 minutes STEP 4: Social Posts (social skill) → Consume research + copy → Generate 5 social posts (LinkedIn, Twitter, Instagram hooks) → Output: Platform-specific posts + hashtags → Time: 2 minutes STEP 5: PDF Compilation (PDF builder) → Consume all previous outputs → Compile into branded 1-pager: Product overview + pricing + testimonial section → Output: Launch-one-pager.pdf → Time: 3 minutes TOTAL EXECUTION TIME: 20 minutes (5 steps, automatic data flow) DELIVERABLES GENERATED ✓ Customer persona document ✓ Competitive analysis summary ✓ Sales copy ready to use ✓ 3-email launch sequence ✓ 5 social media posts ✓ PDF one-pager ✓ Tone + strategy notes All outputs linked in shared folder. Ready for launch Tuesday morning.
About this skill
Your research skill finishes, but the copy skill loses the sources, the email step invents an offer, and restarting means doing everything again. Build a single Claude Code command that passes validated artifacts between installed skills and makes failures recoverable.
What it does
- Maps a workflow into ordered stages with explicit skill assignments and dependencies.
- Defines exactly what each stage receives, produces, and must pass before work continues.
- Checks whether the host supports skill invocation and isolated execution instead of assuming slash commands can call one another.
- Keeps shared constraints and source evidence in compact handoffs without forwarding entire conversations.
- Adds bounded repair attempts, versioned outputs, and restart rules that preserve valid work.
- Separates content generation from sending, publishing, and other actions that need authorization.
What you get
A paste-ready orchestrator SKILL.md, a compact stage contract, and acceptance checks tailored to your workflow. When execution is requested and the required capabilities are available, you also get the resulting artifacts and a record of completed, failed, and unverified stages.
Best for
Claude Code users combining existing research, writing, analysis, formatting, or development skills into a repeatable command without building a separate workflow service.
SKILL.md preview
---
name: multi-skill-slash-command-workflows
description: Build and troubleshoot Claude Code workflows that invoke installed skills in dependency order, pass compact artifact contracts, validate outputs, and resume from failures. Use when the user says "chain these skills", "make one slash command for this workflow", "pass research into my copy skill", "my chained command keeps losing context", "give each stage a fresh context", "restart from the failed step", or "review this orchestrator SKILL.md".
---
# Multi-Skill Slash Command Workflows
… (sign up to view the full skill)Featured in
More ai & agents skills
View all AI & Agents skills →New Skill Scaffolder
Create a new Claude Code skill correctly: right mechanism, valid name and folder, a triggering description, and a smoke test.
Skill Library Lint and Overlap Report
Lint every skill in a repo at once: frontmatter, name-folder match, weak descriptions, overlapping triggers, broken refs, plus a CI script.
Self-Verifying Agent Loop: Plan, Check, Retry, Close
Turns a goal into a task plan with machine-run checks, executes with retry caps, escalates, and refuses to close until verified.
Skill Test Runner (Trigger and A/B)
Test a skill in fresh sessions: ready-to-run prompts, commands, and rubric for trigger recall, false triggers, and blind A/B.