Agent skill

Roadmap Backcast

by nicepkg in nicepkg/ai-workflow

A skill your agent uses when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying…

MITAuto-check passedProduct & Project Management

Install Roadmap Backcast

skills CLI
$ npx skills add nicepkg/ai-workflow --skill roadmap-backcast -a claude-code

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

GitHub CLI
$ gh skill install nicepkg/ai-workflow roadmap-backcast --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/roadmap-backcast .claude/skills/roadmap-backcast && 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
roadmap-backcast
GitHub stars
285
Token cost
~2.5k tokens
SKILL.md length
1,117 words
Files
4
Skills in repo
61
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying…

  • Works in 9 steps: Purpose → When to Use → What Is It → …
  • Planning with fixed deadline
  • SKILL.md covers Table of Contents, Purpose, When to Use and What Is It, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Roadmap Backcast is an agent skill from nicepkg/ai-workflow. Use when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying what must happen when, planning product launches with hard dates, multi-year strategic roadmaps, event planning, transformation initiatives, or when user mentions "backcast", "work backward from", "reverse planning", "we need to launch by", "target date is", or "what needs to happen to reach".

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `resources/evaluators/rubric_roadmap_backcast.json`, `resources/methodology.md` and `resources/template.md`).

It sits in Product & Project Management, covering Project management and Product launch strategy. 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

  • Planning with fixed deadline
  • Working backward from future goal to present
  • Defining milestones and dependencies
  • Mapping critical path

Example prompts

  • “backcast”
  • “work backward from”
  • “reverse planning”
  • “/roadmap-backcast”

Workflow steps

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

  1. Purpose
  2. When to Use
  3. What Is It
  4. Workflow
  5. Dependency Mapping
  6. Critical Path Analysis
  7. Common Patterns
  8. Guardrails
  9. Quick Reference

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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Roadmap Backcast loads about 2.5k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 1,117 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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). 1,117 words, ~2,487 tokens.

Download SKILL.mdSave it as .claude/skills/roadmap-backcast/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
roadmap-backcast
description
Use when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying what must happen when, planning product launches with hard dates, multi-year strategic roadmaps, event planning, transformation initiatives, or when user mentions "backcast", "work backward from", "reverse planning", "we need to launch by", "target date is", or "what needs to happen to reach".

Roadmap Backcast

Table of Contents

  1. Purpose
  2. When to Use
  3. What Is It
  4. Workflow
  5. Dependency Mapping
  6. Critical Path Analysis
  7. Common Patterns
  8. Guardrails
  9. Quick Reference

Purpose

Roadmap Backcast helps you plan backward from a fixed goal or deadline to the present, identifying required milestones, dependencies, critical path, and feasibility constraints. It transforms aspirational targets into actionable, sequenced plans.

When to Use

Invoke this skill when you need to:

  • Plan toward a fixed deadline (product launch, event, compliance date)
  • Work backward from strategic goal to present steps
  • Map dependencies and sequencing for complex initiatives
  • Identify critical path (longest sequence that determines timeline)
  • Assess feasibility of ambitious timeline
  • Coordinate cross-functional work toward shared milestone
  • Plan multi-year transformation with interim checkpoints
  • Sequence initiatives that build on each other
  • Allocate resources across dependent workstreams

User phrases that trigger this skill:

  • "We need to launch by [date]"
  • "Work backward from the goal"
  • "What needs to happen to reach [outcome]?"
  • "Reverse plan from target"
  • "Fixed deadline, what's feasible?"
  • "Backcast from [future state]"
  • "Critical path to delivery"

What Is It

A backcasting roadmap that:

  1. Defines end state (specific, measurable target outcome and date)
  2. Works backward (what must be true one step before? And before that?)
  3. Identifies milestones (key checkpoints with clear deliverables)
  4. Maps dependencies (what depends on what, what can be parallel)
  5. Finds critical path (longest chain that determines minimum timeline)
  6. Assesses feasibility (can we realistically achieve by target date?)

Quick example (Product Launch by Q1 2025):

  • Target: Product live in production for 1000 customers by Jan 31, 2025
  • T-4 weeks (Jan 3): Beta testing with 50 customers complete, critical bugs fixed
  • T-8 weeks (Dec 6): Feature complete, internal QA passed
  • T-12 weeks (Nov 8): MVP built, core features working
  • T-16 weeks (Oct 11): Design finalized, API contracts defined
  • T-20 weeks (Sep 13): Requirements locked, team staffed
  • Today (Sep 1): Feasible if no scope creep and 20% time buffer included

Workflow

Copy this checklist and track your progress:

Roadmap Backcast Progress:
- [ ] Step 1: Define target outcome precisely
- [ ] Step 2: Work backward to identify milestones
- [ ] Step 3: Map dependencies and sequencing
- [ ] Step 4: Identify critical path
- [ ] Step 5: Assess feasibility and adjust

Step 1: Define target outcome precisely

State specific outcome (not vague goal), target date, success criteria. See Common Patterns for outcome definition examples. For straightforward backcasts → Use resources/template.md.

Step 2: Work backward to identify milestones

Start at end, ask "what must be true just before this?" iteratively. Create 5-10 major milestones. For complex multi-year roadmaps → Study resources/methodology.md.

Step 3: Map dependencies and sequencing

Identify what depends on what, what can run in parallel. See Dependency Mapping for techniques.

Step 4: Identify critical path

Find longest sequence of dependent tasks (this determines minimum timeline). See Critical Path Analysis.

Step 5: Assess feasibility and adjust

Compare required timeline to available time. Add buffers (20-30%), identify risks, adjust scope or date if needed. Self-check using resources/evaluators/rubric_roadmap_backcast.json before finalizing. Minimum standard: Average score ≥ 3.5.

Dependency Mapping

Dependency types:

Sequential (A → B): B cannot start until A completes

  • Example: Design must complete before engineering starts
  • Critical path impact: Extends timeline
  • Mitigation: Start A as early as possible, parallelize where safe

Parallel (A ∥ B): A and B can happen simultaneously

  • Example: Backend and frontend development
  • Critical path impact: None (if resourced)
  • Benefit: Reduces overall timeline

Converging (A, B → C): C requires both A and B to complete

  • Example: Testing requires both code complete AND test environment ready
  • Critical path impact: C waits for slower of A or B
  • Mitigation: Monitor both paths, accelerate slower one

Diverging (A → B, C): A enables both B and C

  • Example: API contract defined enables frontend AND backend work
  • Critical path impact: Delays in A delay everything downstream
  • Mitigation: Prioritize A, ensure high quality to avoid rework

Critical Path Analysis

Critical path: Longest sequence of dependent tasks (determines minimum project duration)

Finding critical path:

  1. List all milestones with durations
  2. Draw dependency graph (arrows from prerequisite to dependent)
  3. Calculate earliest start/finish for each milestone (forward pass)
  4. Calculate latest start/finish for each milestone (backward pass)
  5. Milestones with zero slack (earliest = latest) are on critical path

Example:

Milestone A (4 weeks) → Milestone B (6 weeks) → Milestone D (2 weeks) = 12 weeks (critical path)
Milestone A (4 weeks) → Milestone C (3 weeks) → Milestone D (2 weeks) = 9 weeks (non-critical, 3 weeks slack)

Critical path is 12 weeks (A→B→D path)

Managing critical path:

  • Monitor closely: Delays on critical path directly delay project
  • Add buffer: 20-30% to critical path tasks (Murphy's Law)
  • Resource priority: Staff critical path first
  • Fast-track: Can non-critical work be delayed to help critical path?
  • Crash: Add resources to shorten critical path (diminishing returns, Brook's Law applies)
Show full SKILL.md (399 more words)Show less

Common Patterns

Pattern 1: Product Launch with Fixed Date

  • Target: Product live by date, serving customers
  • Key milestones (backward): GA launch, beta testing, feature freeze, alpha testing, MVP, design complete, requirements locked
  • Critical path: Usually design → engineering → testing (sequential)
  • Buffer: 20-30% on engineering (unknowns), 20% on testing (bugs)

Pattern 2: Compliance Deadline (Regulatory)

  • Target: Compliant by regulatory deadline (cannot slip)
  • Key milestones: Audit passed, controls implemented, policies updated, gap analysis complete
  • Critical path: Gap analysis → remediation → validation
  • Buffer: 40%+ (regulatory risk intolerant, build extra time)

Pattern 3: Strategic Transformation (Multi-Year)

  • Target: Future state vision (e.g., "Cloud-native architecture by 2027")
  • Key milestones (annual): Year 3 (full migration), Year 2 (50% migrated), Year 1 (pilot complete), Year 0 (strategy approved)
  • Critical path: Foundation work (pilot, learnings) enables scale
  • Buffer: 30%+ per phase (unknowns compound over time)

Pattern 4: Event Planning (Conference, Launch Event)

  • Target: Event happens on date, attendees have great experience
  • Key milestones: Event day, rehearsal, content ready, speakers confirmed, venue booked, date announced
  • Critical path: Venue booking (long lead time) often on critical path
  • Buffer: 10-20% (events have hard deadlines, less flexible)

Guardrails

Feasibility checks:

  • Available time ≥ required time: If backward timeline reaches before today, goal is infeasible
  • Buffer included: Add 20-30% to estimates (Hofstadter's Law: "It always takes longer than you expect, even when you account for Hofstadter's Law")
  • Dependencies realistic: Can dependent work actually be done in sequence (handoff time, rework)?
  • Resource constraints: Do we have people/budget to parallelize where needed?

Common pitfalls:

  • Optimistic sequencing: Assuming perfect handoffs, no rework, no blockers
  • Ignoring dependencies: "We can start everything at once" → actually highly sequential
  • No buffer: Plans with 0% slack fail on first hiccup
  • Scope creep: Target outcome expands during execution, invalidates backcast
  • Sunk cost fallacy: When backcast shows infeasibility, adjust scope or date (don't plow ahead)

Quality standards:

  • Milestones have clear deliverables (not "working on X")
  • Dependencies explicitly mapped (not assumed)
  • Critical path identified (know what determines timeline)
  • Feasibility assessed honestly (not wishful thinking)
  • Risks documented (what could extend timeline?)
  • Owners assigned to each milestone (accountability)

Quick Reference

Resources:

5-Step Process: Define Target → Work Backward → Map Dependencies → Find Critical Path → Assess Feasibility

Dependency types: Sequential (A→B) | Parallel (A∥B) | Converging (A,B→C) | Diverging (A→B,C)

Critical path: Longest dependent sequence = minimum project duration

Buffer rule: Add 20-30% to estimates, 40%+ for high-uncertainty work

Feasibility test: Required time ≤ Available time (with buffer)

© 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

SKILL.md and 3 other files in workflows/product-manager-workflow/.claude/skills/roadmap-backcast of nicepkg/ai-workflow.

  • SKILL.md
  • resources/evaluators/rubric_roadmap_backcast.json
  • resources/methodology.md
  • resources/template.md

Open the folder on GitHubat commit d167b41

Compare with similar skills

Roadmap Backcast 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.

Roadmap Backcast compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Roadmap Backcast this skillnicepkg/ai-workflow285—~2.5kAutomated safety check: PassMIT
Sealeap Amazon New Product Launch Planxjli360/sealeap-amazon-skills240—~548Automated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Uvastral-sh/claude-code-plugins3132 repos~980Automated safety check: PassApache-2.0
Project Managementkunchenguid/firstmate7.7k—~2.1kAutomated safety check: PassMIT
Hivemind Goalsactiveloopai/hivemind1.6k—~1.7kAutomated safety check: NotesApache-2.0

Similar skills

  • Sealeap Amazon New Product Launch Plan

    xjli360/sealeap-amazon-skills

    Create a quantified Amazon new-product launch plan by translating a sales target into comparable-product benchmarks, keyword economics, budget scenarios, milestones, and stop-loss rules.

    240 GitHub stars~548 tokensUpdated 10 days ago
    Product & Project ManagementAuto-check passed
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Uv

    astral-sh/claude-code-plugins

    Official

    Guide for using uv, the Python package and project manager. An agent skill from astral-sh/claude-code-plugins.

    313 GitHub starsUsed in 2 repos~980 tokens
    Product & Project ManagementAuto-check passed
  • Project Management

    kunchenguid/firstmate

    Agent-only procedure for Firstmate project management. An agent skill from kunchenguid/firstmate.

    7.7k GitHub stars~2.1k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Hivemind Goals

    activeloopai/hivemind

    Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/.

    1.6k GitHub stars~1.7k tokensUpdated 10 days ago
    Product & Project ManagementAuto-check: notes
  • Ichartjs

    wanghetommy/ichartjs

    Plan, validate, render, explain, and safely edit iChart.js visualizations from tabular, project, or diagram data.

    352 GitHub stars~4.2k tokensUpdated today
    Product & Project ManagementAuto-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

Questions about Roadmap Backcast

What does Roadmap Backcast do?

A skill your agent uses when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying…. Roadmap Backcast is an agent skill from nicepkg/ai-workflow. Use when planning with fixed deadline or target outcome, working backward from future goal to present, defining milestones and dependencies, mapping critical path, identifying what must happen when, planning product launches with hard dates, multi-year strategic roadmaps, event planning, transformation initiatives, or when user mentions "backcast", "work backward from", "reverse planning", "we need to launch by", "target date is", or "what needs to happen to reach".

When should I use Roadmap Backcast?

Roadmap Backcast fits situations like: planning with fixed deadline; working backward from future goal to present; defining milestones and dependencies; mapping critical path.

How do I install Roadmap Backcast in Claude Code?

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

How do I install Roadmap Backcast in Codex?

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

Can I use Roadmap Backcast 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 roadmap-backcast -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/roadmap-backcast, .gemini/skills/roadmap-backcast, .github/skills/roadmap-backcast and .opencode/skills/roadmap-backcast in your project.

What does Roadmap Backcast need to run?

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

Does Roadmap Backcast 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 Roadmap Backcast 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 Roadmap Backcast use?

Roadmap Backcast 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 Roadmap Backcast use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 Roadmap Backcast?

Skills that share tags, products or a category with Roadmap Backcast: Sealeap Amazon New Product Launch Plan (xjli360/sealeap-amazon-skills, 240 stars), CCPM Project Management (automazeio/ccpm, 8.4k stars), Uv (astral-sh/claude-code-plugins, 313 stars) and Project Management (kunchenguid/firstmate, 7.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Roadmap Backcast?

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.