Skip to content
Agentmart
Submit a tool

aligned-delivery

An agile operating + coaching skill for project/program managers and team leads, grounded in a delivery philosophy (리·기·도; the lenses "unexpectancy" and…

Skill by ahnbingbing

IndexedMIT
Write a review

Chalk Labs

Need help deploying aligned-delivery?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ahnbingbing-aligned-delivery

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

An agile operating + coaching skill for project/program managers and team leads, grounded in a delivery philosophy (리·기·도; the lenses "unexpectancy" and "proximity"). Coaches and interviews PMs; helps you lead, grow, and care for a product/engineering team (motivation, psychological safety, 1:1s, conflict resolution, burnout, key-person departures, team merges, self-management) and manage up to stakeholders and executives (stakeholder mapping, executive alignment, escalation/RAG reporting). Diagnoses delivery health from sprint/Jira + DORA analytics — scope/completion predictability, workload balance, ticket fragmentation, lead/cycle time, throughput, flow efficiency, deployment frequency, change-failure rate, MTTR (even without story points) — and forecasts completion dates probabilistically ("when will it be done"). Also helps you prioritize and sequence work (Cost of Delay, WSJF, RICE), make hard fast-vs-high-stakes decisions, run product discovery and validated learning (what to build, how to de-risk it), design team structure and fix silos/reorg (Team Topologies, Conway's law), introduce agile change/adoption, and design sprint cadences, retrospectives, and feedback loops. Use it whenever the user wants to coach a PM, lead/grow/repair a team, resolve conflict, manage up, run a health check, read delivery or DORA metrics, forecast a delivery date, prioritize or sequence work, make a hard call, decide what to build, restructure a team, drive an agile change, or fix an operating model — even if they never say "agile" or "scrum." Not for generic HR/comp, hiring logistics, individual career advice, pitch decks / go-to-market / business strategy, or pure coding. (Bilingual EN/KO. 프로젝트/프로덕트 매니저와 팀 리드를 위한 애자일 운영+코칭 스킬, 딜리버리 철학 (리·기·도; "불확정성"·"근접성" 렌즈)에 근거. PM 코칭/인터뷰; 팀을 이끌고·키우고·케어하기(동기부여· 심리적 안전감·1:1·갈등 해결·번아웃·핵심 인력 이탈·팀 병합·자기관리) 및 위로 관리(스테이크홀더 맵· 경영진 정렬·에스컬레이션/RAG). 스프린트/지라+DORA 분석으로 딜리버리 헬스 진단 — 스코프/완료 예측도· 업무량·티켓 파편화·리드/사이클 타임·처리량·흐름 효율·배포 빈도·변경 실패율·MTTR(스토리포인트 없이도) — 및 확률적 완료일 예측("언제 끝나나"). 또한 우선순위·시퀀싱(Cost of Delay·WSJF·RICE), 어려운 결정(빠른 결정 vs 중대 결정), 제품 발견·검증된 학습(무엇을 만들지·리스크 줄이기), 팀 구조·사일로/리오그 (Team Topologies·콘웨이 법칙), 애자일 변화 도입, 스프린트 케이던스·회고·피드백 루프 설계. 일반 HR/연봉, 채용 실무, 개인 커리어 조언, 피칭덱·시장진입·사업전략, 순수 코딩은 대상 아님.)

Use cases: design, data, ml, sales

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/aligned-delivery

What's inside

Skill name
aligned-delivery
Description
An agile operating + coaching skill for project/program managers and team leads, grounded in a delivery philosophy (리·기·도; the lenses "unexpectancy" and "proximity"). Coaches and interviews PMs; helps you lead, grow, and care for a product/engineering team (motivation, psychological safety, 1:1s, conflict resolution, burnout, key-person departures, team merges, self-management) and manage up to stakeholders and executives (stakeholder mapping, executive alignment, escalation/RAG reporting). Diagnoses delivery health from sprint/Jira + DORA analytics — scope/completion predictability, workload balance, ticket fragmentation, lead/cycle time, throughput, flow efficiency, deployment frequency, change-failure rate, MTTR (even without story points) — and forecasts completion dates probabilistically ("when will it be done"). Also helps you prioritize and sequence work (Cost of Delay, WSJF, RICE), make hard fast-vs-high-stakes decisions, run product discovery and validated learning (what to build, how to de-risk it), design team structure and fix silos/reorg (Team Topologies, Conway's law), introduce agile change/adoption, and design sprint cadences, retrospectives, and feedback loops. Use it whenever the user wants to coach a PM, lead/grow/repair a team, resolve conflict, manage up, run a health check, read delivery or DORA metrics, forecast a delivery date, prioritize or sequence work, make a hard call, decide what to build, restructure a team, drive an agile change, or fix an operating model — even if they never say "agile" or "scrum." Not for generic HR/comp, hiring logistics, individual career advice, pitch decks / go-to-market / business strategy, or pure coding. (Bilingual EN/KO. 프로젝트/프로덕트 매니저와 팀 리드를 위한 애자일 운영+코칭 스킬, 딜리버리 철학 (리·기·도; "불확정성"·"근접성" 렌즈)에 근거. PM 코칭/인터뷰; 팀을 이끌고·키우고·케어하기(동기부여· 심리적 안전감·1:1·갈등 해결·번아웃·핵심 인력 이탈·팀 병합·자기관리) 및 위로 관리(스테이크홀더 맵· 경영진 정렬·에스컬레이션/RAG). 스프린트/지라+DORA 분석으로 딜리버리 헬스 진단 — 스코프/완료 예측도· 업무량·티켓 파편화·리드/사이클 타임·처리량·흐름 효율·배포 빈도·변경 실패율·MTTR(스토리포인트 없이도) — 및 확률적 완료일 예측("언제 끝나나"). 또한 우선순위·시퀀싱(Cost of Delay·WSJF·RICE), 어려운 결정(빠른 결정 vs 중대 결정), 제품 발견·검증된 학습(무엇을 만들지·리스크 줄이기), 팀 구조·사일로/리오그 (Team Topologies·콘웨이 법칙), 애자일 변화 도입, 스프린트 케이던스·회고·피드백 루프 설계. 일반 HR/연봉, 채용 실무, 개인 커리어 조언, 피칭덱·시장진입·사업전략, 순수 코딩은 대상 아님.)
License
MIT
Instructions
383 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • description: longer than 1024 characters
  • files: referenced but missing: scripts/draw_number.py, references/sanyeomjeom.md

Files (29)

  • plugin.json · .claude-plugin/
  • .gitignore
  • CHANGELOG.md
  • LICENSE
  • README.ko.md
  • README.md
  • SKILL.md
  • health_check_template.md · assets/
  • monthly_productivity_review_template.md · assets/
  • retro_kpt_template.md · assets/
  • sprint_report_template.md · assets/
  • demo.gif
  • demo.tape
  • evals.json · evals/
  • sprints.csv · evals/
  • coaching-questions.md · references/
  • manifesto.md · references/
  • operating-loops.md · references/
  • operating-rules.md · references/
  • principles.md · references/
  • flow_metrics.py · scripts/
  • forecast_montecarlo.py · scripts/
  • health_check_analyze.py · scripts/
  • sample_flow.csv · scripts/
  • sample_health_check.csv · scripts/
  • sample_throughput.csv · scripts/
  • sample_workload.csv · scripts/
  • sprint_predictability.py · scripts/
  • workload_fragmentation.py · scripts/

SKILL.md (first lines)

# Aligned Delivery (얼라인드 딜리버리)

A project-management operating method that treats belief as the load-bearing layer under
performance. It is grounded in **N2C (Neo²-Confucianism / Dynamic Resonance Ontology)** —
the philosophy lives *inside* this skill as its foundation; the full ontology is a separate
`life-reading` skill. Here we use only the parts that map cleanly to running a team.

> **KO.** 신념을 성과 아래 하중을 견디는 층(load-bearing layer)으로 다루는 프로젝트 관리
> 운영 방법론입니다. **N2C(네오² 유학 / 동적 공명 존재론)** 에 뿌리를 두며, 철학은 이 스킬의
> *토대*로서 내부에 존재합니다. 전체 존재론은 별도의 `life-reading` 스킬에 있고, 여기서는 팀 운영에
> 깔끔하게 매핑되는 부분만 사용합니다.

## What this skill is (이 스킬은 무엇인가)

Three sentences hold the whole method:

1. **Read 리·기·도.** Read any team on three layers — its latent structure (리), its live
   operating state (기), and its measurable footprint (도) — before judging it, and never
   from metrics alone.
2. **Move 응축 → 해산 → 창발 → 무위.** Run the real cycle beneath sprints: condense and
   diagnose a problem, dissolve fixed plans, let a new pattern emerge, then stabilize it
   with minimal force.
3. **Lead by minimal interference toward alignment.** Optimize for *alignment* — stable
   under many valid interpretations — rather than for the single "right" answer, because
   alignment is what produces stable, sustainable delivery. The *goal* of that minimal
   interference is a team **"managed without being managed"** — a self-driving system rooted in
   each person's self-management, where management is *caring* rather than control and the leader
   earns the step-back through attraction and trust (principles.md #4).

> **KO.** 세 문장이 방법론 전체를 담습니다. (1) **리·기·도를 읽어라** — 어떤 팀이든 잠재
> 구조(리), 살아 움직이는 운영 상태(기), 측정 가능한 흔적(도)의 세 층위로 읽되, 절대 지표
> 하나만으로 판단하지 않는다. (2) **응축 → 해산 → 창발 → 무위로 움직여라** — 스프린트 밑에
> 흐르는 진짜 사이클을 돌려라: 문제를 응축·진단하고, 고정된 계획을 해산하고, 옛 구조가 설명
> 못 하던 새 패턴이 창발하게 두고, 최소한의 힘으로 무위로 안정화한다. (3) **최소 간섭으로
> 정렬을 향해 이끌어라** — 단 하나의 '정답'이 아니라 여러 타당한 해석 아래에서도 안정적인
> *정렬(alignment)* 을 최적화하라. 안정적이고 지속가능한 딜리버리를 만드는 것은 정렬이다. 이 최소
> 간섭의 *목표*는 **'관리하지 않아도 관리되는'** 팀 — 개인의 자기관리에 뿌리내린 자율주행 체계 — 이며,
> 여기서 관리는 통제가 아니라 *케어*이고 리더는 매력과 신뢰로 물러설 권리를 얻는다(principles.md #4).

The thesis the whole skill embodies: *belief is the load-bearing layer under performance;
alignment (not the single right answer) creates stability; and real productivity comes from
stability, not heroic speed.*
(이 스킬이 체현하는 한 줄 명제: *신념은 성과 아래의 하중층이고, 정렬(정답이 아닌)이 안정성을
만들며, 진짜 생산성은 영웅적 속도가 아니라 안정성에서 나온다.*)

## The 리·기·도 diagnostic lens (리·기·도 진단 렌즈)

Before recommending anything, locate the situation on all three layers. Judging from one
layer alone — especially metrics — is the most common operating mistake.

- **Li 리 — latent structure (잠재 구조).** The de-facto structure the team actually runs on —
  team/role topology, backlog shape, dependencies, recurring failure modes — not the org chart
  or the documented process. Ask: *what does this system tend toward?* It's emergent: it shifts
  as the team's practices change. Read it from org/backlog structure and repeated incidents.
- **Gi 기 — operating state (운영 상태).** The live operating state: workload, capacity, morale,
  tension, delivery pressure — the team's real-time signal. Read it through health checks and
  1:1s. Structure tells you the design; only the operating state tells you how it's running now.
- **Do 도 — footprint / trajectory (흔적/궤적).** The measurable footprint and trajectory:
  predictability, velocity, fragmentation — the telemetry the team actually emitted and where the
  trend points. Read it through sprint analytics. Metrics are the trace — not the whole system.

> **KO.** 무엇을 권하기 전에 상황을 세 층위 모두에 위치시켜라. 한 층위(특히 지표)만으로
> 판단하는 것이 가장 흔한 운영 실수다. **리** 는 팀이 실제로 굴러가는 구조 — 팀·역할 토폴로지,
> 백로그 구조, 의존성, 반복되는 실패 모드 — 이며 조직도나 문서화된 프로세스가 아니다.
> *이 시스템은 무엇을 향해 기우는가?* 팀의 실천이 바뀌면 함께 바뀐다. **기** 는 살아 있는
> 운영 상태(업무량, 캐파, 사기, 긴장, 딜리버리 압력) — 팀의 실시간 신호 — 로 헬스체크와 1:1로
> 읽는다. 구조는 설계를 말해주지만, 지금 실제로 어떻게 돌아가는지는 운영 상태만 말해준다.
> **도** 는 측정 가능한 흔적과 궤적(예측도, 벨로시티, 파편화) — 팀이 실제로 남긴 텔레메트리와
> 추세 방향 — 으로 스프린트 분석으로 읽는다. 지표는 시스템 전체가 아니라 흔적일 뿐이다.

A complete diagnosis names what you see on each layer, then reconciles them. When the
layers disagree (e.g. green metrics but a heavy operating state), trust the disagreement — it is the signal.
(완전한 진단은 각 층위에서 본 것을 명명한 뒤 서로 대조한다. 층위들이 어긋날 때 — 예: 지표는
초록인데 기가 무거울 때 — 그 어긋남을 신뢰하라. 그것이 곧 신호다.)

## When to use which capability (어떤 역량을 언제 쓰는가)

Route the request to one of three capabilities (요청을 세 역량 중 하나로 라우팅하라):

- **Coach / interview / assess a PM** → **Capability A** (PM 코칭·인터뷰·평가).
  Read `references/coaching-questions.md` and run the **staged coaching protocol** at its top —
  frame the mode, read 리·기·도, start with the **core-6 forcing questions**, then go deep one
  question at a time (STOP between). Answer in the philosophy's voice; tie every abstract point to
  one concrete, measurable move. (코칭 세션은 그 파일 상단의 단계형 프로토콜로 — 모드 확인 → 리·기·도
  → 코어 6문항 → 한 번에 한 문항씩 심화(사이에 STOP). 추상 원칙은 측정 가능한 한 수로 착지.)
- **Diagnose a team / read its health or sprint data** → **Capability B** (팀 진단·데이터 해석).
  Read `references/operating-loops.md`, then run the relevant script in `scripts/` on the
  user's data and interpret the output — leading indicators first, lagging second. For a
  whole-team monthly write-up, populate `assets/monthly_productivity_review_template.md`;
  for a per-sprint one, `assets/sprint_report_template.md`. (월간 전사 리포트는 월간 생산성
  리뷰 템플릿, 스프린트별은 스프린트 리포트 템플릿으로.)
- **Design cadence / retro / feedback loops / guardrails** → **Capability C** (운영 루프 설계).
  Read `references/operating-loops.md` and design the ceremonies around the
  응축→해산→창발→무위 cycle and 무위 (minimal-interference) leadership.

Many real requests touch two or three. Read 리·기·도 first; it tells you which capability
leads. (실제 요청은 둘셋을 함께 건드린다. 먼저 리·기·도를 읽어라 — 어느 역량이 주도할지를
그것이 알려준다.)

> **Step-change in tooling or process (e.g., adopting an AI coding assistant) → B then C.**
> A sudden velocity jump is lagging and the estimation unit may have broken — don't read it at
> face value. First verify with leading indicators and the **per-person distribution** (B):
> scope predictability, fragmentation, ops ratio, cost-per-output, and whether *everyone* rose
> or only some (coach anyone left behind). Then design the recovery as an operating loop (C):
> baseline reset → ~3-month capacity-finding push → health check → ±5–10% capacity → ~80% steady
> state. See operating rules #8–#9 and coaching Q48.
> (KO. 도구·프로세스 계단식 변화(예: AI 코딩 어시스턴트 도입) → B로 검증한 뒤 C로 설계. velocity
> 급등은 후행이고 추정 단위가 깨졌을 수 있으니 액면대로 읽지 마라. 먼저 선행지표와 **개인별
> 분포**(B)로 검증 — 예측도·파편화·운영비중·비용당 산출, 그리고 전원이 올랐는지 일부만인지(뒤처진
> 인력은 코칭). 그다음 회복을 운영 루프(C)로 설계 — 베이스라인 리셋 → ~3개월 캐파 탐색 →
> 헬스체크 → ±5~10% 캐파 → ~80% 정상상태. 운영 경험칙 #8–#9, 코칭 Q48 참고.)

> **Merging two teams → B then C.** Day 1, diagnose from each team's history *yourself* before
> engaging people; keep each team's own way until a joint method is agreed; converge on one simple
> shared unit (don't re-platform mid-merge); measure per-cohort leading indicators (incl.
> distribution match) and never judge by velocity (it drops first). See `operating-loops.md` §6
> and operating rule #7 (false-normal confidence). (두 팀 병합 → B 후 C. Day 1에 사람 만나기 전
> 각 팀 이력으로 *스스로* 진단; 합의 전까진 각자 방식 유지; 단순 공유 단위로 수렴; 코호트별
> 선행지표(분포 매칭 포함) 측정, velocity로 판단 금지. operating-loops §6, 규칙 #7 참고.)

From ahnbingbing/aligned-delivery, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Jun 28, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get aligned-delivery running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying aligned-delivery?

CallGet help
Cite this page

aligned-delivery skill. Agent Mart. https://agentmart.dev/skills/ahnbingbing-aligned-delivery (last updated 2026-10-24)