Agent skill

Pm Roadmap

by serejaris in serejaris/personal-corp-os

Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health…

MITAuto-check passedProduct & Project Management

Install Pm Roadmap

skills CLI
$ npx skills add serejaris/personal-corp-os --skill pm-roadmap -a claude-code

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

GitHub CLI
$ gh skill install serejaris/personal-corp-os pm-roadmap --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/serejaris/personal-corp-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pm-roadmap .claude/skills/pm-roadmap && 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
pm-roadmap
GitHub stars
229
Token cost
~2k tokens
SKILL.md length
810 words
Files
4 (incl. assets)
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health…

  • Works in 7 steps: Get current state → Iteration status summary → Milestone progress → …
  • Анализ задержек
  • SKILL.md covers Inputs, Step 1 — Get current state, Step 2 — Iteration status… and Step 3 — Milestone progress, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pm Roadmap is an agent skill from serejaris/personal-corp-os. Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do NOT auto-trigger. Triggers on /pm-roadmap, "обнови roadmap", "статус спринта", "анализ задержек", "update roadmap", "sprint status", "milestone progress", "delay analysis".

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including assets (for example `README.md` and `README.ru.md`).

It sits in Product & Project Management, covering Project management, Product roadmapping and Customer success. The repository describes itself as: Personal Corp OS — управление личной компанией через AI-агентов: задачи вне головы, отделы вместо памяти, недельное ретро. Открытые скиллы для Claude Code и Codex. The licence is MIT.

When your agent uses it

  • Анализ задержек
  • Milestone progress

Example prompts

  • “обнови roadmap”
  • “update roadmap”
  • “sprint status”
  • “/pm-roadmap”

Workflow steps

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

  1. Get current state
  2. Iteration status summary
  3. Milestone progress
  4. Priority change log
  5. Dependency tracking
  6. Forward-looking plan
  7. Output report

What it can do on your machine

Read from SKILL.md and the folder at commit 95e36c3. 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 (its code samples are markdown).

    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

Pm Roadmap loads about 2k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 810 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~115
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 serejaris/personal-corp-os at commit 95e36c3, republished under its MIT licence (© serejaris). 810 words, ~1,993 tokens.

Download SKILL.mdSave it as .claude/skills/pm-roadmap/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
pm-roadmap
description
Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do NOT auto-trigger. Triggers on /pm-roadmap, "обнови roadmap", "статус спринта", "анализ задержек", "update roadmap", "sprint status", "milestone progress", "delay analysis".

pm-roadmap — Roadmap update

Part of the Personal Corp framework — running a one-person business through AI agents. Aggregate current iteration status, evaluate milestone progress, track priority changes and dependencies, output a roadmap status overview and planning suggestions.

Inputs

FieldRequiredNotes
Iteration statusyesCurrent Sprint task list and statuses (manual or pulled from PM tool)
Roadmap horizonnoQuarter / half / year; default quarter
ChangesnoItems needing priority or timeline adjustment + reason
DependenciesnoCross-team / tech dependencies and current state

Step 1 — Get current state

If a PM tool integration is available, pull the current Sprint task list and bucket by status. Otherwise ask the user for the list in any format (table, screenshot, verbal).

Step 2 — Iteration status summary

FieldValue
Sprint name / period{Sprint X / date range}
Planned tasks{N}
Done{X} ({X/N%})
In progress{Y}
Not started{Z}
Blocked / delayed{W}
Estimated on-time delivery{%}

Delayed-task analysis:

TaskOriginal dueNew ETAReasonMilestone impact
{task}{date}{date}{cause}yes/no

Five-cause delay attribution:

CausePatternImprovement
Scope changeMid-development requirement edits, scope creepStrengthen requirement freeze; route changes through approval
Estimation gapActual effort far exceeds estimateCalibrate from history, add buffer
Tech riskApproach proves infeasible, perf wall, tech debt blockingPre-development tech-spike phase
Dependency blockWaiting on another team / third party / approval2-week-ahead dependency early-warning
Headcount changePTO, attrition, redirected20% capacity buffer in planning

If the same root cause appears 3+ times, escalate to a process-improvement item.

Step 3 — Milestone progress

MilestoneTarget dateKey deliverableProgressStatusRisks
{M1}{date}{deliverable}{X%}On-time / at-risk / delayed{risk}

Status criteria:

  • On-time: progress ≥ time elapsed; no blocking deps
  • At-risk: progress slightly behind, or unresolved dependency
  • Delayed: progress significantly behind, or critical dependency blocked

Step 4 — Priority change log

ItemChangeOld priorityNew priorityReasonImpact
{item}Up / down / new / removed{P0/P1/P2}{P0/P1/P2}{reason}{scope}

Change-reason categories:

  • User-feedback driven (from /pm-feedback)
  • Competitor driven (from /pm-competitive)
  • Data driven (from /pm-metrics)
  • Resource change (team capacity, tech approach change)
  • External (compliance, partner ask)

Step 5 — Dependency tracking

DependencyTypeOwner / consumerNeed-byStateRisk
{desc}Tech / team / external{who depends on whom}{date}Resolved / in progress / blockedHigh / medium / low

Dependency types:

  • Tech: infrastructure, APIs, services
  • Cross-team: other product lines, design, data team
  • External: third-party services, partners, approval flows

Step 6 — Forward-looking plan

Recommend the next 2-3 iterations.

Now / Next / Later view:

HorizonItemsPriorityConfidenceDependencies
Now (current iteration){in-flight work}LockedHigh{resolved}
Next (1-2 iterations out){planned work}Locked / TBDMedium-high{to follow up}
Later (3+ iterations out){directional plans}DirectionalLow-medium{to evaluate}

Capacity assessment:

  • Available capacity next iteration: {X} person-days
  • Allocation suggestion: 70% planned features + 20% tech debt + 10% buffer
  • Given current delays, prioritize next: {list}

Roadmap health score:

DimensionWeightScoringScore
On-time delivery rate30%> 80% = 5, 60-80% = 3, < 60% = 1{X}
Scope stability20%Change < 10% = 5, 10-30% = 3, > 30% = 1{X}
Dependency resolution20%> 90% = 5, 70-90% = 3, < 70% = 1{X}
OKR alignment15%All work traces to OKR = 5{X}
Team confidence15%Team confident on timely delivery = 5{X}

Composite: weighted total ≥ 4 healthy / 3-4 at-risk / < 3 needs urgent action.

Feature-cut decision framework (when capacity is short):

Cut firstReasonCondition
Nice-to-haveDoesn't affect core valueCut directly
Splittable feature's second halfMVP-firstConfirm MVP standalone usable
Polish / perfectionismFunctional > perfectNo irreversible tech debt introduced
Low-confidence requirementsUnvalidated hypothesesTag "deferred for validation"

Principle: cut scope > delay > add people (Brooks's Law: adding people to a late project makes it later).

Show full SKILL.md (228 more words)Show less

Step 7 — Output report

markdown
# Roadmap Update

**Date:** {date}
**Horizon:** {quarter / half}
**Current iteration:** {Sprint name / dates}

## 1. Current Iteration Status
Completion rate: {X%} ({done}/{total})
Blockers: {N}

## 2. Milestone Progress
| Milestone | Target | Progress | Status |
|---|---|---|---|

## 3. Priority Changes
| Item | Change | Reason |
|---|---|---|

## 4. Dependencies & Risks
- High-risk dependencies: {desc}
- Coordination needed: {desc}

## 5. Roadmap (Now / Next / Later)
(table)

## 6. Next-Step Recommendations
1. {recommendation 1}
2. {recommendation 2}
3. {recommendation 3}

Quality bar

  1. Status info accurate — delayed tasks have specific cause + new ETA
  2. Milestone evaluation evidenced — no "almost done" / "soon"
  3. Changes traceable — every priority change records reason and decider
  4. Risks raised proactively — not waiting for blow-up to report
  5. Recommendations actionable — owner-assignable
  6. Health score tracked over time to observe improvement trend

Roadmap-communication guide

Different audiences need different granularity:

AudienceFocusFormatCadence
CEO / VPStrategy, milestones, risksNow/Next/Later high-levelMonthly
EngineeringSprint tasks, deps, tech detailDetailed task list + dep graphDaily / weekly
Sales / CSCustomer-promised features, ETAsFeature timelineMonthly
External customersUpcoming capabilitiesQuarterly themes (no dates)Quarterly

Three rules:

  1. Don't promise specific dates externally — promise "Q2", not "April 15"
  2. Don't hide delays — early bad news beats late bad news
  3. Don't treat the roadmap as a contract — plans change

Red lines

  1. No hidden delays — report delays honestly
  2. No false promises — don't be over-optimistic on future timelines
  3. No ignored dependencies — cross-team dependencies are tracked explicitly

When input is incomplete

  • No task list → ask for at least milestones + key deliverables status
  • No priority changes recorded → output current state only, tag "recommend logging changes"
  • First use, no history → help build the baseline framework
  • /pm-prioritize — re-rank items in the roadmap
  • /pm-metrics — metric review feeds roadmap adjustments
  • /pm-brainstorm — explore innovation directions for the Later column

© serejaris, 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 (assets) in skills/pm-roadmap of serejaris/personal-corp-os.

  • SKILL.md
  • README.md
  • README.ru.md
  • assets/illustration.png

Open the folder on GitHubat commit 95e36c3

Compare with similar skills

Pm Roadmap 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.

Pm Roadmap compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pm Roadmap this skillserejaris/personal-corp-os229—~2kAutomated safety check: PassMIT
Product Roadmaptikalk/adlc-team-skills141—~3.1kAutomated safety check: PassMIT
Roadmap Timelinepnp/sharepoint-skills132—~2.2kAutomated safety check: PassMIT
Customer Statustechwolf-ai/ai-first-toolkit132—~1.2kAutomated safety check: PassMIT
Onboarding Playbook Creationseb1n/awesome-ai-agent-skills206—~2.4kAutomated safety check: PassMIT
LoopX PR Program Managerloopx-project/loopx6.2k—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Product Roadmap

    tikalk/adlc-team-skills

    A skill your agent uses when doing weekly progress checks or milestone validation — tracks decision, execution, evidence, and gate states across four layers of truth.

    141 GitHub stars~3.1k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Roadmap Timeline

    pnp/sharepoint-skills

    Generates a polished, self-contained HTML roadmap or milestone timeline from any project data — SharePoint lists, pasted tables, or a verbal description.

    132 GitHub stars~2.2k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Customer Status

    techwolf-ai/ai-first-toolkit

    Synthesised view of account health and activity for managers overseeing customer-facing teams (Sales, CS, Professional Services, Presales).

    132 GitHub stars~1.2k tokensUpdated 10 days ago
    Sales & SupportAuto-check passed
  • Onboarding Playbook Creation

    seb1n/awesome-ai-agent-skills

    Design structured customer onboarding workflows with phased checklists, email templates, success milestones, and ownership assignments.

    206 GitHub stars~2.4k tokensUpdated 2 mo ago
    Sales & SupportAuto-check passed
  • LoopX PR Program Manager

    loopx-project/loopx

    Tracks a group of pull or merge requests across repositories as durable LoopX state: inventory, reconcile changes, keep priorities and a roadmap, and monitor over time.

    6.2k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Ceos Calendar

    bradfeld/ceos

    A skill your agent uses when managing the rolling market calendar - conferences, launches, fundraising milestones, partner events, and team constraints

    156 GitHub stars~2k tokensUpdated 26 days ago
    Business, Finance & HRAuto-check passed

More from serejaris/personal-corp-os

All 36 skills in this repo
  • Weekly Planning

    serejaris/personal-corp-os

    A skill your agent uses when the user is transitioning from a completed retro into a weekly plan, choosing weekly outcomes, scheduling a full ISO week, or asking for "план на неделю", "weekly…

    229 GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Gh Issues

    serejaris/personal-corp-os

    A skill your agent uses when creating, searching, updating, or managing GitHub issues via CLI.

    229 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed
  • Product Data Audit

    serejaris/personal-corp-os

    A skill your agent uses when auditing a product, business, or project ecosystem — analyzing data sources, decision loops, bottlenecks, and implementation contours.

    229 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed
  • Tg Bot Ops

    serejaris/personal-corp-os

    A skill your agent uses when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway.

    229 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check: notes
  • Audit Agent Rules

    serejaris/personal-corp-os

    Audits the agent rules in the current folder (AGENTS.md, nested AGENTS.md files) and the skill descriptions the agent sees at start, then reports what to cut, move or rewrite and edits only after…

    229 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Make Landing

    serejaris/personal-corp-os

    Создаёт несколько вариантов дизайна 2D-поверхности (лендинг, герой, обложка, слайды): свой визуальный референс и автор на вариант, полный design.md с UTC/SHA-256 до кода, проверка в браузере…

    229 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed

Questions about Pm Roadmap

What does Pm Roadmap do?

Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health…. Pm Roadmap is an agent skill from serejaris/personal-corp-os. Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов.

When should I use Pm Roadmap?

Pm Roadmap fits situations like: Анализ задержек; milestone progress.

How do I install Pm Roadmap in Claude Code?

Run `npx skills add serejaris/personal-corp-os --skill pm-roadmap -a claude-code`. Or copy the skill folder (skills/pm-roadmap in serejaris/personal-corp-os) into .claude/skills/pm-roadmap in your project. Claude Code loads it when a task matches its description.

How do I install Pm Roadmap in Codex?

Run `npx skills add serejaris/personal-corp-os --skill pm-roadmap -a codex`. Or copy the skill folder (skills/pm-roadmap in serejaris/personal-corp-os) into .agents/skills/pm-roadmap in your project. Codex loads it when a task matches its description.

Can I use Pm Roadmap 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 serejaris/personal-corp-os --skill pm-roadmap -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pm-roadmap, .gemini/skills/pm-roadmap, .github/skills/pm-roadmap and .opencode/skills/pm-roadmap in your project.

What does Pm Roadmap need to run?

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

Does Pm Roadmap 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 Pm Roadmap 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 Pm Roadmap use?

Pm Roadmap 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 Pm Roadmap use?

About 2k tokens (SKILL.md is roughly 8k 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 Pm Roadmap?

Skills that share tags, products or a category with Pm Roadmap: Product Roadmap (tikalk/adlc-team-skills, 141 stars), Roadmap Timeline (pnp/sharepoint-skills, 132 stars), Customer Status (techwolf-ai/ai-first-toolkit, 132 stars) and Onboarding Playbook Creation (seb1n/awesome-ai-agent-skills, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pm Roadmap?

serejaris (a GitHub user) maintains it in serejaris/personal-corp-os, which has 229 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 7, 2026.

Source: serejaris/personal-corp-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.