mcpbeat Sign in

Roadmap Communicator Skill for Claude

> Translate one internal roadmap into audience-appropriate formats with confidence-band discipline. Use when preparing a roadmap readout, tailoring it for an exec, customer, eng, or sales audience, or auditing over-promise risk.

13k tokens
context cost
the whole folder, loaded on every use
7
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
447
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/borghei/Claude-Skills --skill roadmap-communicator

What comes with it

42 806 bytes besides the instruction
references/audience-specific-formats.md
references/now-next-later-and-themes.md
references/roadmap-communication-patterns.md
scripts/confidence_band_generator.py
scripts/roadmap_audience_translator.py
scripts/roadmap_diff_reporter.py

The instruction itself

20 sections, as written by the author

Roadmap Communicator

A skill focused on communicating the roadmap — different audiences

need different formats and confidence levels. Distinct from product-strategist

(which builds the strategy) and agile-product-owner (which manages sprint

execution).

When to use this skill

  • Preparing a roadmap readout for execs, board, customers, or sales
  • Translating a single internal roadmap to multiple audience formats
  • Auditing roadmap commitments for over-promise risk
  • Building a now-next-later view of priorities
  • Communicating roadmap changes to stakeholders
  • Preparing a what-changed/what's-next memo

Inputs the advisor expects

  • The internal roadmap (themes, initiatives, target dates, confidence)
  • Target audience(s) for the communication
  • Recent roadmap changes (added, removed, slipped)
  • Cross-functional commitments (engineering, sales, marketing)

Clarify First

Before generating the roadmap communication, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • [ ] Target audience — board/exec, customer, sales, or engineering (selects the audience-format matrix row and granularity)
  • [ ] Confidence band per item — commit, plan, aspire, or strategic intent (drives the language and over-promise guardrails)
  • [ ] Recent changes — what was added, removed, or slipped since the last readout (drives the what-changed diff memo)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Workflows

Workflow 1 — Translate roadmap for a specific audience

  • Capture the master roadmap with confidence bands.
  • Run roadmap_audience_translator.py with target audience.
  • Review the audience-specific output; tune language.
python3 roadmap-communicator/scripts/roadmap_audience_translator.py \
  --input roadmap.json --audience customer --format markdown

Workflow 2 — Apply confidence bands to commitments

  • List proposed roadmap items.
  • Run confidence_band_generator.py with team velocity history + estimation context.
  • Adjust item commitments based on output (commit / aspire / explore).
python3 roadmap-communicator/scripts/confidence_band_generator.py \
  --input items.json --format markdown

Workflow 3 — Generate a roadmap diff report

  • Capture previous roadmap snapshot + current roadmap.
  • Run roadmap_diff_reporter.py to produce what-changed memo.
python3 roadmap-communicator/scripts/roadmap_diff_reporter.py \
  --previous roadmap_q1.json --current roadmap_q2.json --format markdown

Decision frameworks

Audience-format matrix

| Audience | Right format | Wrong format |

|----------|--------------|--------------|

| Board / exec | Themes + bets + KPIs (1 page) | Feature list |

| Customers / public | What's new + what's next (themes; no dates) | Internal commit list |

| Sales | Themes + competitive positioning + customer-ask coverage | Engineering jargon |

| Engineering | Themes + quarter commitments + scoped detail | Vague aspirations |

| Internal company | Themes + progress + asks | Confidential strategy |

| Partner / integrator | API-relevant changes + breaking-change calendar | All-up roadmap |

Same roadmap; different formats. Don't send the engineering commit list to customers.

Confidence bands

Apply per item:

| Band | Language | Audience expectation |

|------|----------|----------------------|

| Commit | "Will ship" with target date | Hold us to this |

| Plan | "Plan to ship" with target window | Confident but conditional |

| Aspire | "Investigating" / "Exploring" | Don't depend on this |

| Strategic intent | "We believe X matters" | Direction, not deliverable |

Common errors:

  • Treating "plan" as "commit" — sets up disappointment
  • Communicating "commit" as "plan" — under-delivers excitement
  • No confidence band — every line read as commit

Now-next-later structure

A useful skeleton across audiences:

  • Now (in progress, < 1 quarter): commit-level items
  • Next (1-2 quarters out): plan-level items
  • Later (2-4 quarters): aspire-level items
  • Strategic intent (>4 quarters): direction only

This protects confidence: the closer in time, the firmer the commitment.

Themes vs features

Communicate at the right granularity:

  • External / strategic: themes ("better collaboration")
  • Customer-specific: outcomes ("you'll be able to X")
  • Internal: features + tickets

Telling a customer "we're adding X in Q3" makes a commitment that may

not be precise enough. Telling the team "we're going to improve

collaboration somehow" is too vague.

Common engagements

"Help me write the customer roadmap section"

  • Start with what they care about (outcomes, not features).
  • Use themes + outcomes; avoid specific dates beyond the current quarter.
  • Group: launching soon, in development, exploring.
  • Avoid: features that depend on uncertain technical bets.
  • Always include a "we'd love your input" hook.

"Help me prep the board roadmap section"

  • Start with strategic themes (3-5).
  • For each theme: what's shipped, what's coming, what's the bet.
  • Tie to business outcomes (NRR impact, new revenue, cost saving).
  • Surface 1-2 strategic risks transparently.
  • End with 2-3 specific asks.

"Our customer is asking 'when will X ship?'"

  • First check: is X actually committed? (Probably plan or aspire.)
  • If commit: give a target window with caveats.
  • If plan: "We're planning to ship in [window]; we'll know more by [date]."
  • If aspire: "We're exploring; not in our committed roadmap."
  • Document the customer asks; feed them back into prioritization.

Anti-patterns to avoid

  • One-size-fits-all roadmap. Different audiences get over- or under-served.
  • Date-only roadmap. Dates without confidence bands set up over-promise.
  • Public commitments engineering didn't sign off on. Trust breaks.
  • Roadmap that never changes. Reality changes; roadmap must.
  • Roadmap silence between updates. Customers / sales speculate.
  • Hiding strategic risks. Boards prefer honest risks over surprise misses.
  • Big bang annual roadmap with no quarterly delta. Misses change cycles.
  • Feature names instead of outcomes. "Notifications v2" tells the customer nothing.

References

  • references/roadmap-communication-patterns.md — format catalog + when to use
  • references/audience-specific-formats.md — per-audience templates
  • references/now-next-later-and-themes.md — structural patterns
  • product-team/product-strategist — strategy upstream of roadmap
  • product-team/agile-product-owner — sprint-level execution
  • product-team/product-manager-toolkit — broader PM tooling
  • c-level-advisor/cpo-advisor — CPO partnership
  • c-level-advisor/ceo-advisor — CEO / board alignment
  • business-growth/customer-success-manager — customer comms
  • marketing/ skills — external messaging alignment

Other skills for the same job

different authors, same section of the catalogue
Doc Coauthoring
by anthropics
vendor ×10

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

4k tokens
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Test Driven Development
by w95
×7

Use when implementing any feature or bugfix, before writing implementation code

2k tokens
Writing Plans
by ZhanlinCui
×4

Use when you have a spec or requirements for a multi-step task, before touching code

816 tokens
Writing Skills
by ZhanlinCui
×4

Use when creating new skills, editing existing skills, or verifying skills work before deployment

26k tokens scripts
Crafting Effective Readmes
by softaworks
×3

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

15k tokens
Humanizer
by softaworks
×3

| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

6k tokens
Opentrons Integration
by christophacham
×3

Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.

9k tokens scripts

How to use it

Copy the folder

Take borghei/roadmap-communicator from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.