Agent skill

Work Intake

by nicepkg in nicepkg/ai-workflow

Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills.

MITAuto-check passedAgent Workflows

Install Work Intake

skills CLI
$ npx skills add nicepkg/ai-workflow --skill work-intake -a claude-code

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

GitHub CLI
$ gh skill install nicepkg/ai-workflow work-intake --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/nicepkg/ai-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workflows/product-manager-workflow/.claude/skills/work-intake .claude/skills/work-intake && 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
work-intake
GitHub stars
285
Token cost
~3.4k tokens
SKILL.md length
692 words
Files
1
Skills in repo
61
Repo updated
First seen
Licence
MIT

At a glance

Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills.

  • Works in 4 steps: Project Board Readiness (GATE) → Clarifying Questions → Scope Assessment → …
  • Tasks that involve Requirements gathering
  • SKILL.md covers Overview, The Intake Flow, Step 0: Project Board… and Step 1: Clarifying Questions, plus 7 more sections
  • Calls git, gh and jq; reaches github.com

What it does

Work Intake is an agent skill from nicepkg/ai-workflow. Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills. Use this when receiving any new work request.

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 Requirements gathering. The repository describes itself as: 🚀 170+ pre-built skills for Claude Code, Cursor, Codex & 14+ AI tools. Stop re-teaching your AI the same things. One command → instant domain expertise. Marketing, SEO, Trading… The licence is MIT.

When your agent uses it

  • Tasks that involve Requirements gathering

Example prompts

  • “/work-intake”

Workflow steps

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

  1. Project Board Readiness (GATE)
  2. Clarifying Questions
  3. Scope Assessment
  4. Route to Appropriate Workflow

What it can do on your machine

Read from SKILL.md and the folder at commit d167b41. 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
    • gh
    • jq

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

Work Intake loads about 3.4k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
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 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 nicepkg/ai-workflow at commit d167b41, republished under its MIT licence (© nicepkg). 692 words, ~3,408 tokens.

Download SKILL.mdSave it as .claude/skills/work-intake/SKILL.md (or your agent's skills folder).
name
work-intake
description
Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills. Use this when receiving any new work request.

Work Intake

Overview

Every work request flows through intake. This skill determines scope, gathers requirements, and routes to the appropriate workflow.

Core principle: No work is too small to track, no work is too large to decompose.

Announce at start: "I'm using work-intake to understand and scope this request before beginning."

The Intake Flow

┌─────────────────────────────────────────────────────────────────────┐
│                        REQUEST RECEIVED                              │
└─────────────────────────────┬───────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────────┐
│               STEP 0: PROJECT BOARD READINESS (GATE)                │
│  Is GITHUB_PROJECT_NUM set?                                         │
│  Is project board accessible?                                       │
│  Are required fields configured?                                    │
└─────────────────────────────┬───────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────────┐
│                    CLARIFYING QUESTIONS                              │
│  What is the user trying to achieve?                                │
│  What does success look like?                                        │
│  What constraints exist?                                             │
└─────────────────────────────┬───────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────────┐
│                      SCOPE ASSESSMENT                                │
│  How much investigation is needed?                                   │
│  How many deliverables?                                              │
│  How many unknowns?                                                  │
└─────────────────────────────┬───────────────────────────────────────┘
                              │
              ┌───────────────┼───────────────┬───────────────┐
              ▼               ▼               ▼               ▼
         ┌────────┐     ┌──────────┐    ┌──────────┐    ┌──────────┐
         │TRIVIAL │     │  SMALL   │    │  LARGE   │    │ MASSIVE  │
         │        │     │          │    │          │    │          │
         │1 issue │     │1-3 issues│    │1 epic    │    │Initiative│
         │no unkn.│     │few unkn. │    │research  │    │multi-epic│
         └───┬────┘     └────┬─────┘    └────┬─────┘    └────┬─────┘
             │               │               │               │
             ▼               ▼               ▼               ▼
      issue-prerequisite  issue-prerequisite  epic-management  initiative-
      + project-board-    + decomposition    + research spikes  architecture
        enforcement       + project-board-  + project-board-  + project-board-
                           enforcement       enforcement       enforcement

Step 0: Project Board Readiness (GATE)

Before any work intake, verify project board infrastructure is ready.

This is a gate. Do not proceed to clarifying questions until this passes.

bash
# Derive defaults from GITHUB_PROJECT if provided
if [ -z "$GITHUB_PROJECT_NUM" ] && [ -n "$GITHUB_PROJECT" ]; then
  NUM_CANDIDATE=$(echo "$GITHUB_PROJECT" | sed -E 's#.*/projects/([0-9]+).*#\1#')
  if [ -n "$NUM_CANDIDATE" ] && [ "$NUM_CANDIDATE" != "$GITHUB_PROJECT" ]; then
    export GITHUB_PROJECT_NUM="$NUM_CANDIDATE"
    echo "Derived GITHUB_PROJECT_NUM=$GITHUB_PROJECT_NUM from GITHUB_PROJECT"
  fi
fi

if [ -z "$GH_PROJECT_OWNER" ] && [ -n "$GITHUB_OWNER" ]; then
  export GH_PROJECT_OWNER="$GITHUB_OWNER"
  echo "Derived GH_PROJECT_OWNER=$GH_PROJECT_OWNER from GITHUB_OWNER"
fi

if [ -z "$GH_PROJECT_OWNER" ] && [ -n "$GITHUB_PROJECT" ]; then
  OWNER_CANDIDATE=$(echo "$GITHUB_PROJECT" | sed -E 's#https://github.com/(orgs|users)/([^/]+)/projects/[0-9]+#\2#')
  if [ -n "$OWNER_CANDIDATE" ] && [ "$OWNER_CANDIDATE" != "$GITHUB_PROJECT" ]; then
    export GH_PROJECT_OWNER="$OWNER_CANDIDATE"
    echo "Derived GH_PROJECT_OWNER=$GH_PROJECT_OWNER from GITHUB_PROJECT"
  fi
fi

if [ -z "$GH_PROJECT_OWNER" ]; then
  REMOTE_URL=$(git remote get-url origin 2>/dev/null || true)
  OWNER_CANDIDATE=$(echo "$REMOTE_URL" | sed -E 's#(git@|https://)github.com[:/]+([^/]+)/[^/]+(\.git)?#\2#')
  if [ -n "$OWNER_CANDIDATE" ] && [ "$OWNER_CANDIDATE" != "$REMOTE_URL" ]; then
    export GH_PROJECT_OWNER="$OWNER_CANDIDATE"
    echo "Derived GH_PROJECT_OWNER=$GH_PROJECT_OWNER from git remote"
  fi
fi

# Verify environment variables are set
if [ -z "$GITHUB_PROJECT_NUM" ]; then
  echo "BLOCKED: GITHUB_PROJECT_NUM not set"
  echo "Set with: export GITHUB_PROJECT_NUM=<number>"
  exit 1
fi

if [ -z "$GH_PROJECT_OWNER" ]; then
  echo "BLOCKED: GH_PROJECT_OWNER not set"
  echo "Set with: export GH_PROJECT_OWNER=@me  # or org name"
  exit 1
fi

# Verify project is accessible
if ! gh project view "$GITHUB_PROJECT_NUM" --owner "$GH_PROJECT_OWNER" --format json > /dev/null 2>&1; then
  echo "BLOCKED: Cannot access project $GITHUB_PROJECT_NUM"
  echo "Verify project exists and you have access"
  exit 1
fi

# Verify required fields exist
FIELDS=$(gh project field-list "$GITHUB_PROJECT_NUM" --owner "$GH_PROJECT_OWNER" --format json | jq -r '.fields[].name')

for required in "Status" "Priority"; do
  if ! echo "$FIELDS" | grep -q "^$required$"; then
    echo "WARNING: Required field '$required' not found in project"
    echo "Consider adding this field for full tracking support"
  fi
done
if ! echo "$FIELDS" | grep -q "^Type$" && ! echo "$FIELDS" | grep -q "^Issue Type$"; then
  echo "WARNING: Required field 'Type' (or 'Issue Type') not found in project"
  echo "Consider adding this field for full tracking support"
fi

echo "Project board ready: $GITHUB_PROJECT_NUM"

If gate fails:

  1. Configure missing environment variables
  2. Create project board if needed
  3. Add required fields (Status, Type, Priority)
  4. Re-run readiness check

Skill: project-board-enforcement


Step 1: Clarifying Questions

Before scoping, understand the request.

Do not ask questions that can be answered from the repo. First inspect:

  • README.md, FEATURES.md, BRANDING.md, docs/, Storybook, and existing routes/pages
  • Existing GitHub issues and project board items

Only ask the user for information that is still missing after reviewing the repo.

Essential Questions
QuestionPurpose
"What are you trying to achieve?"Understand the goal, not just the task
"What does success look like?"Define acceptance criteria
"Who/what is affected?"Identify scope of impact
"Are there constraints I should know about?"Time, tech, compatibility
"Is this part of something larger?"Link to existing initiatives
Discovery Questions (for unclear requests)
QuestionReveals
"Can you walk me through how this would be used?"User journey, edge cases
"What exists today?"Starting point, migration needs
"What have you already tried?"Failed approaches, constraints
"Is there prior art or examples?"Design direction

Step 2: Scope Assessment

Evaluate the request against these criteria:

Scope Matrix
FactorTrivialSmallLargeMassive
UnknownsNoneFew, answerableMany, need researchExtensive, need spikes
Deliverables1 thing2-5 things6-20 things20+ things
Code areas1-2 files3-10 files10+ filesMultiple systems
DependenciesNoneInternal onlyExternal servicesNew infrastructure
Duration< 1 session1-3 sessions1-2 weeksWeeks to months
Criteria1-23-56-1515+
Scope Decision
IF unknowns == none AND deliverables <= 2:
  → TRIVIAL: Use issue-prerequisite directly

IF unknowns == few AND deliverables <= 5:
  → SMALL: Use issue-prerequisite, maybe issue-decomposition

IF unknowns == many OR deliverables > 5:
  → LARGE: Use epic-management with research spikes

IF unknowns == extensive OR deliverables > 20 OR new_infrastructure:
  → MASSIVE: Use initiative-architecture

Step 3: Route to Appropriate Workflow

Trivial Scope
markdown
**Assessment:** This is a trivial request (single deliverable, no unknowns).

**Next step:** Creating a single issue using `issue-prerequisite`.

Route to: issue-prerequisite

Small Scope
markdown
**Assessment:** This is a small request (few deliverables, minimal unknowns).

**Plan:**
1. Create parent issue for the request
2. If needed, decompose into 2-3 sub-issues
3. Begin implementation

**Next step:** Creating issue structure using `issue-prerequisite`.

Route to: issue-prerequisite → maybe issue-decomposition

Large Scope
markdown
**Assessment:** This is a large request requiring structured planning.

**Unknowns identified:**
- [ ] Unknown 1 - needs investigation
- [ ] Unknown 2 - needs research spike

**High-level deliverables:**
1. Deliverable A
2. Deliverable B
...

**Next step:** Creating epic structure using `epic-management`.

Route to: epic-management (which will create research spikes as needed)

Massive Scope
markdown
**Assessment:** This is a massive request requiring full initiative architecture.

**Why massive:**
- [Reason: extensive unknowns / new infrastructure / multi-system / etc.]

**Initial unknowns:**
- [ ] Does X exist?
- [ ] How does Y work?
- [ ] What are constraints of Z?

**Potential scope:**
- Multiple epics likely
- New capabilities needed
- Significant research required

**Next step:** Beginning initiative architecture using `initiative-architecture`.

Route to: initiative-architecture

Resumability Checkpoint

Before routing, document the intake in memory:

bash
# Store intake assessment
mcp__memory__create_entities([{
  "name": "Intake-[DATE]-[SHORT_DESC]",
  "entityType": "WorkIntake",
  "observations": [
    "Request: [Original request]",
    "Scope: [Trivial/Small/Large/Massive]",
    "Unknowns: [List]",
    "Route: [Target skill]",
    "Status: [Routing/In Progress/Complete]"
  ]
}])

Examples

Example: Trivial

Request: "Make the login page button a little lighter."

Intake:

  • Goal: Adjust button color
  • Success: Button is lighter
  • Unknowns: None (CSS change)
  • Deliverables: 1 (color change)
  • Scope: TRIVIAL

→ Route to issue-prerequisite

Show full SKILL.md (286 more words)Show less
Example: Large

Request: "Add dark mode to the application."

Intake:

  • Goal: Theme switching capability
  • Success: Users can toggle dark/light mode
  • Unknowns:
    • Current theming approach?
    • Component library support?
    • Persistence mechanism?
  • Deliverables: ~10 (theme tokens, components, toggle, persistence, etc.)
  • Scope: LARGE

→ Route to epic-management

Example: Massive

Request: "Add the ability for users to log in by clicking on a popup in their phone."

Intake:

  • Goal: Mobile push notification login
  • Success: User receives push, taps, logged in
  • Unknowns:
    • Is there a mobile app? → Research spike
    • Push notification infrastructure? → Research spike
    • Authentication flow design? → Research spike
    • Security requirements? → Research spike
  • Deliverables: 30+ (app work, backend, auth, notifications, etc.)
  • Scope: MASSIVE

→ Route to initiative-architecture

Red Flags That Indicate Larger Scope

Watch for these phrases that suggest the request is larger than it appears:

PhraseLikely Scope
"Just add..." + new capabilityLarge (new capability = infrastructure)
"Users should be able to..."Large (user-facing = full stack)
"Integrate with..."Large (external = API, auth, error handling)
"Like [other product]..."Massive (feature parity = extensive)
"Mobile/app/notification"Massive (unless app exists)
"Real-time/sync/live"Large (infrastructure)

Never Turn Away Work

No matter how massive the request:

  1. Acknowledge the goal - "I understand you want X"
  2. Explain the process - "This will require structured planning"
  3. Begin investigation - Start with what we don't know
  4. Document everything - Every decision, every finding
  5. Break it down - Until we have tractable pieces

The path from "massive request" to "implementation" is:

Massive Request
    → Initiative Architecture (document unknowns, create research spikes)
    → Research Spikes (answer unknowns)
    → Epic Structure (group deliverables)
    → Issue Decomposition (create tractable tasks)
    → Implementation (one issue at a time)

Checklist

  • Project board readiness verified (Step 0 gate passed)
  • GITHUB_PROJECT_NUM and GH_PROJECT_OWNER set
  • Asked clarifying questions
  • Understood the goal (not just the task)
  • Identified unknowns
  • Counted deliverables
  • Assessed scope (Trivial/Small/Large/Massive)
  • Documented intake in memory
  • Routed to appropriate skill (with project-board-enforcement)

Skill: project-board-enforcement

Gate: Cannot proceed to any downstream skill without project board readiness verified.

© nicepkg, MIT. 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 workflows/product-manager-workflow/.claude/skills/work-intake of nicepkg/ai-workflow.

Open the folder on GitHubat commit d167b41

Compare with similar skills

Work Intake 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.

Work Intake compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Work Intake this skillnicepkg/ai-workflow285—~3.4kAutomated safety check: PassMIT
Using Superpowersfarm-fe/farm5.6k34 repos~1.4kAutomated safety check: PassMIT
Interview Meaddyosmani/agent-skills102k6 repos~3.8kAutomated safety check: PassMIT
Grillingbestofjs/bestofjs3.1k30 repos~464Automated safety check: PassMIT
Agentic Workflow Designerdotnet/Open-XML-SDK4.6k2 repos~3.5kAutomated safety check: PassMIT
Ask User QuestionMemTensor/MemOS12k—~1kAutomated safety check: PassApache-2.0

Similar skills

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 34 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    102k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed
  • Grilling

    bestofjs/bestofjs

    Grill the user relentlessly about a plan, decision, or idea.

    3.1k GitHub starsUsed in 30 repos~464 tokens
    Agent WorkflowsAuto-check passed
  • Agentic Workflow Designer

    dotnet/Open-XML-SDK

    Official

    Interviews you one question at a time about goal, trigger, permissions and data needs, then drafts a single agentic workflow markdown file.

    4.6k GitHub starsUsed in 2 repos~3.5k tokens
    Agent WorkflowsAuto-check passed
  • Ask User Question

    MemTensor/MemOS

    Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.

    12k GitHub stars~1k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from nicepkg/ai-workflow

All 61 skills in this repo
  • Capture Triage

    nicepkg/ai-workflow

    Processes Drafts Pro captures from the Inbox folder. An agent skill from nicepkg/ai-workflow.

    285 GitHub stars~3k tokensUpdated 8 mo ago
    Auto-check passed
  • Legacy To AI Ready

    nicepkg/ai-workflow

    Transform legacy codebases into AI-ready projects with Claude Code configurations.

    285 GitHub stars~2.2k tokensUpdated 8 mo ago
    Auto-check: notes
  • Newsletter Coach

    nicepkg/ai-workflow

    Writing coach that extracts educational content from your daily experiences and turns it into publish-ready newsletter drafts.

    285 GitHub stars~3.7k tokensUpdated 8 mo ago
    Auto-check passed
  • Webfluence

    nicepkg/ai-workflow

    Content web architecture framework. An agent skill from nicepkg/ai-workflow.

    285 GitHub stars~1.4k tokensUpdated 8 mo ago
    Auto-check passed
  • Workflow Creator

    nicepkg/ai-workflow

    Create complete Claude Code workflow directories with curated skills.

    285 GitHub stars~2.6k tokensUpdated 8 mo ago
    Auto-check passed
  • Media Processing

    nicepkg/ai-workflow

    Video/audio/image processing with FFmpeg and ImageMagick. An agent skill from nicepkg/ai-workflow.

    285 GitHub stars~2.4k tokensUpdated 8 mo ago
    Auto-check: notes

Categories

Questions about Work Intake

What does Work Intake do?

Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills. Work Intake is an agent skill from nicepkg/ai-workflow. Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills.

When should I use Work Intake?

Work Intake fits situations like: tasks that involve Requirements gathering.

How do I install Work Intake in Claude Code?

Run `npx skills add nicepkg/ai-workflow --skill work-intake -a claude-code`. Or copy the skill folder (workflows/product-manager-workflow/.claude/skills/work-intake in nicepkg/ai-workflow) into .claude/skills/work-intake in your project. Claude Code loads it when a task matches its description.

How do I install Work Intake in Codex?

Run `npx skills add nicepkg/ai-workflow --skill work-intake -a codex`. Or copy the skill folder (workflows/product-manager-workflow/.claude/skills/work-intake in nicepkg/ai-workflow) into .agents/skills/work-intake in your project. Codex loads it when a task matches its description.

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

What does Work Intake need to run?

Going by SKILL.md and its folder, Work Intake needs the command-line tools its instructions call (git, gh and jq).

Does Work Intake access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Work Intake 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 Work Intake use?

Work Intake 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 Work Intake 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 Work Intake?

Skills that share tags, products or a category with Work Intake: Using Superpowers (farm-fe/farm, 5.6k stars), Interview Me (addyosmani/agent-skills, 102k stars), Grilling (bestofjs/bestofjs, 3.1k stars) and Agentic Workflow Designer (dotnet/Open-XML-SDK, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Work Intake?

nicepkg (a GitHub organization) maintains it in nicepkg/ai-workflow, which has 285 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on January 20, 2026.

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