skills-workflows

Design multi-skill workflow systems with artifact-based state handoff. Use when building skill pipelines, sequenced workflows, or when workflow system, skill pipeline, state handoff, or artifacts are mentioned.

الانتقال إلى التثبيت

المستودع: outfitter-dev/outfitter
آخر نشاط في المصدر: ٢٤ فبراير ٢٠٢٦ في ٢٣:٠٩
لغة SKILL.md المكتشفة: الإنجليزية
النجوم: ٦
التفرعات: ١

خيارات التثبيت

يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.

مراجعة ملفات المصدر

اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.

العودة إلى البحث العودة إلى التثبيت

name	skills-workflows
description	Design multi-skill workflow systems with artifact-based state handoff. Use when building skill pipelines, sequenced workflows, or when workflow system, skill pipeline, state handoff, or artifacts are mentioned.
metadata	{"version":"1.0.1","related-skills":["skillcraft","claude-craft","codify"]}
allowed-tools	Read, Write, Edit, Grep, Glob, Bash, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion

Skills Workflows

Design skill systems that chain together with artifact-based state passing.

Steps

Load the skillcraft skill for base skill authoring
Apply workflow patterns from this skill
If Claude-specific features needed, load the claude-craft skill

<when_to_use>

Building multi-skill pipelines (triage → plan → implement → review)
Designing state handoff between workflow steps
Creating deterministic preprocessing with !command syntax
Setting up shared conventions (artifacts/, context.md)
Choosing fork vs inherit for workflow isolation

NOT for: single standalone skills, one-off commands, simple patterns

</when_to_use>

Shared Conventions

Every workflow system benefits from standard file locations:

.claude/
  skills/
    _shared/
      context.md       # Living summary of current task + decisions
      constraints.md   # Non-negotiables (security, style, perf budgets)
    triage/SKILL.md
    plan/SKILL.md
    implement/SKILL.md
    review/SKILL.md
artifacts/
  triage.md           # Output of /triage
  plan.md             # Output of /plan
  test-report.md      # Output of /test
  review-notes.md     # Output of /review
scripts/
  run-tests.sh
  security-check.sh

File	Purpose	Updated By
`context.md`	Task state, decisions made, current focus	Each skill as work progresses
`constraints.md`	Project invariants, security rules, style guide	Setup once, rarely changed
`artifacts/{step}.md`	Step outputs, consumed by next step	The skill that completes that step

/triage → writes artifacts/triage.md
    ↓
/plan reads artifacts/triage.md → writes artifacts/plan.md
    ↓
/implement reads artifacts/plan.md → updates context.md
    ↓
/test reads artifacts/plan.md → writes artifacts/test-report.md
    ↓
/review reads all → writes artifacts/review-notes.md

# Triage: {task description}

## Problem Statement

{clear definition}

## Scope

- Files: {list}
- Modules: {list}

## Acceptance Criteria

- [ ] {criterion 1}
- [ ] {criterion 2}

## Risks

- {risk 1}
- {risk 2}

---

Generated by /triage at {timestamp}

---
name: pr-summary
context: fork
agent: Explore
allowed-tools: Bash(gh:*)
---

## Pull Request Context
<!-- NOTE: The "!" must be placed in front of backticks for preprocessing to work. -->
- **Diff**: `gh pr diff`
- **Comments**: `gh pr view --comments`
- **Status**: `gh pr status`

Summarize changes and highlight risks.

---
name: triage
context: fork
agent: Explore
allowed-tools: Read, Grep, Glob
---

---
name: implement
# context: inherit is default
---

# triage, review, research skills
context: fork
agent: Explore
allowed-tools: Read, Grep, Glob

# plan, spec, architecture skills
context: fork
agent: Plan
allowed-tools: Read, Grep, Glob

# implement, fix, refactor skills
# No context/agent fields (inherit default)

# deploy, ship, commit skills
disable-model-invocation: true

Failure Mode	Mitigation
Context blowup	Keep analysis in `context: fork`; store results in artifacts
State lost between steps	All state in files, not conversation
Unsafe auto-execution	`disable-model-invocation: true` on side-effect skills
Tool permission creep	Explicit `allowed-tools` per skill, minimal set
Workflow step skipped	Artifacts serve as gates (next step reads previous)

---
name: {step-name}
description: {what this step does}. Use when {trigger conditions}.
context: fork           # or omit for inherit
agent: Explore          # if forked
allowed-tools: Read, Grep, Glob
disable-model-invocation: true  # if side-effectful
---

# Purpose

- Why this step exists
- What "done" looks like

# Inputs

- Read: artifacts/{previous-step}.md
- Read: .claude/skills/\_shared/constraints.md
- $ARGUMENTS: {expected input}

# Process

1. {step 1}
2. {step 2}
3. {step 3}

# Outputs

- Write: artifacts/{this-step}.md
- Update: .claude/skills/\_shared/context.md with decisions

# Constraints

- {constraint 1}
- {constraint 2}