AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Growth Change Management

skill-krillinai-growee-skills-growth-change-management · by krillinai

Use when a team needs to build, audit, or refresh a cross-functional growth change involving participant impact, readiness, communications, enablement, migration, rollout, adoption, cutover, rollback, support, decommissioning, or benefits realization across products, processes, data, systems, customers, teams, or markets.

— No reviews yet
0 installs
26 views
0.0% view→install

Install

$ agentstack add skill-krillinai-growee-skills-growth-change-management

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-krillinai-growee-skills-growth-change-management)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Growth Change Management? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Growth Change Management

Turn an approved or proposed growth change into a traceable path from current state to durable operating state. Preserve the distinction between a proposal, decision, authorization, communication, enablement, migration, rollout, adoption, outcome, and causal effect; none proves the next.

Read [change-contract-and-impact.md](references/change-contract-and-impact.md) before accepting scope, current and target states, sources, roles, authority, impact, dependencies, capacity, or sequencing. Read [readiness-migration-and-adoption.md](references/readiness-migration-and-adoption.md) before assigning readiness, communications, enablement, migration, cutover, rollout, adoption, support, decommissioning, or benefits. Read [governance-market-and-actions.md](references/governance-market-and-actions.md) before reconciling versions, handling people or markets, routing specialist work, or specifying external actions. Read [output-contract.md](references/output-contract.md) before delivery. Use [playbook-sources.md](references/playbook-sources.md) for the pinned Growth Playbook basis.

Select One Mode

| Mode | Use | | --- | --- | | build | Create a bounded change contract and evidence-pending adoption path from supplied decisions and artifacts | | audit | Test an existing change for scope, impact, readiness, migration, adoption, governance, or completion gaps | | refresh | Version a change after its decision, evidence, scope, participant impact, readiness, rollout, outcome, or context changes |

Name one mode and state draft, evidence-pending, decision-ready, approval-pending, authorized-record, readiness-pending, ready-with-conditions, blocked, staged-record, active-record, paused-record, rollback-record, recovery-record, adoption-review, decommission-pending, closed-record, superseded, or expired. A record state does not prove approval, authorization, migration, rollout, adoption, benefit, causal impact, or completion.

Use exactly verified, inferred, unavailable, or not applicable for evidence-bearing claims. Keep source artifact, observation, interpretation, recommendation, decision, approval, authorization, assignment, execution, verification, adoption, outcome, and causal estimate separate. Do not invent scope, owners, authority, users, readiness, scores, dates, capacity, communications, training, migration, adoption, risks, benefits, or completion.

Gate Commitments And State Changes

Populate owners, sponsors, champions, readiness or resistance ratings, dates, targets, communications, training, support, migrations, rollout, adoption, decommissioning, completion, or benefits only from attributable evidence for the exact scope, authority, accepted responsibility, capacity, conditions, population, period, and version. A locally authored plan is not an approved organizational change.

When readiness is missing, keep the record draft or evidence-pending and unsupported fields unavailable. Preserve requested percentages, scores, roles, relative dates, deadlines, 30/60/90 phases, training, notifications, system changes, acknowledgements, adoption, closure, and benefits only as exact reported requests with unsupported status. Do not calculate dates, create proposed assignments or commitments, reserve unnamed roles, invent thresholds, or treat urgency and executive preference as authorization.

Preserve Specialist Ownership

This Skill owns change orchestration across an already bounded change: the canonical change contract, participant impact, readiness, dependencies, capacity, communication, enablement, migration, rollout, adoption, support, cutover, rollback, recovery, decommissioning, and benefits-verification handoff.

It does not redesign the underlying product, price, package, tracking, metric, CRM, organization, infrastructure, risk control, market entry, experiment, or initiative. Route those objects to their owning Skills, preserve returned artifact versions, and track only their effect on the change. Route the source decision to growth-operations, execution plan to growth-operations, portfolio risk to growth-operations, recurring review to growth-operations, reusable learning to growth-operations, and retrospective analysis to growth-operations.

Freeze The Change Contract

Record change ID and version, mode and state, decision and intended outcome, source decisions and artifacts, current and target states, scope and exclusions, products and business models, customers and participant roles, markets and locales, systems and data, processes and policies, metrics and versions, periods and cutoff, decision owner, approver, authorizer, change owner, operating owners, affected owners, review and expiry, and external-action boundary.

Split materially different changes by decision, authority, affected population, system, market, owner, reversibility, migration, cutover, rollback, or outcome. A parent program may reconcile dependencies and shared capacity but does not erase child contracts. Do not hide a pricing migration, event-schema replacement, CRM rebuild, platform switch, reorganization, market launch, and product redesign inside one generic transformation.

Preserve the current operating state until decision, authority, readiness, migration, support, stop, rollback, and verification conditions are explicit. An announced date, executive preference, ticket status, or favorable score cannot authorize a change.

Map Participants And Impact

Map customer, user, administrator, buyer, payer, approver, operator, support, partner, employee, manager, and nonparticipant roles separately when applicable. For each role record entity, current workflow, target workflow, value, burden, access, authority, dependency, risk, exclusion, communication, enablement, support, feedback, adoption evidence, and protection.

Separate sponsor, decision owner, approver, authorizer, change owner, manager, operator, and affected participant. Seniority, attendance, silence, message opens, or system use does not establish authority, consent, comprehension, acceptance, competence, or adoption. Preserve direct, indirect, temporary, displaced, and downstream impact as well as customer and nonparticipant protections.

Reconcile Readiness, Dependencies, And Load

Assess decision, product, data, system, people, operations, support, market, and governance readiness as distinct gates. Every gate needs a requirement, evidence, owner, dependency, state, limitation, exception, expiry, and accountable go, hold, stage, or stop authority. Do not invent or average scores; enthusiasm cannot offset security, privacy, legal, customer-harm, or hard operational blockers.

Map prerequisite, coupled, conflicting, shared-resource, external, and residual dependencies. Record available, committed, protected, unavailable, and contingent capacity by role, period, and owner. Reconcile participant attention, context switching, peak periods, support demand, blackout windows, maintenance, incidents, contractual obligations, and concurrent changes before sequencing. When capacity or evidence is insufficient, reduce, stage, resequence, defer, pause, stop, or request an accountable decision.

Separate Communication From Capability

For communications, separate creation, approval, delivery, viewability, awareness, comprehension, feedback, acceptance, acknowledgement, and action. Define each audience's need, sender, source, claim, timing, permitted channel, call to action, accessibility, localization, questions, dissent, correction, suppression, expiry, and retirement. Delivery, opens, silence, or repetition are not understanding, consent, compliance, or adoption.

For enablement, separate asset availability, enrollment, attendance, completion, comprehension, representative practice, competence, operating behavior, adoption, and outcome. Define role tasks, prerequisites, environment, assessment, support, refresh, remediation, accessibility, privacy, retention, and appeal. A deck, webinar, or quiz does not prove correct production behavior or customer value.

Design Migration And Cutover

Version source and target entities, schemas, definitions, identities, permissions, contracts, prices, events, history, systems, owners, periods, and authority. Define eligibility, exclusions, cohorts, sequence, mapping, backups, idempotency, trial migration, dual run, reconciliation, exceptions, failed records, acceptance, support, monitoring, stop, rollback, fallback, recovery, audit, and correction.

Treat technical deployment, data migration, operational readiness, participant exposure, workflow adoption, and outcome as separate states. Preserve the prior system until exit criteria, residual obligations, retention, archive, independent verification, and decommissioning gates pass. A smoke test cannot verify complete workflows, reconciled data, support readiness, or customer safety.

Measure Rollout, Adoption, And Benefits

Separate eligibility, assignment, access, enablement, render, viewability, exposure, interaction, first use, competent use, repeated use, workflow adoption, retention, customer outcome, business outcome, and causal effect. Define entity, numerator, denominator, identity, source, version, cohort, period, window, maturity, exclusions, late data, suppression, and valid-zero rules for every rate.

Measure workflow completion, time to competence, repeated value, workarounds, exceptions, errors, support burden, accessibility, trust, retention, economics, and customer harm. Emails sent, documents viewed, training attendance, accounts enabled, logins, clicks, and tickets closed are activity signals, not adoption or benefits.

Record benefit hypotheses, baselines, intended mechanisms, exposed and unaffected populations, outcome maturity, guardrails, alternative explanations, disconfirming evidence, attribution limits, and next evidence. Route experiments and causal analysis to their owning Skills. Do not attribute revenue or another outcome to communication, training, or adoption merely because it followed the change.

Govern Versions, Markets, People, And Actions

Preserve every artifact's owner, authority, scope, definition, version, effective period, acknowledgement, exception, conflict, correction, supersession, and archive. Reconcile exact conflicts; never let teams choose the easiest procedure or mix old and new states indefinitely without bounded coexistence and retirement rules.

Treat every market as a new evidence and operating boundary. Revalidate customers, roles, products, channels, systems, vendors, platforms, data, metrics, capacity, timing, communications, enablement, support, readiness, migration, risks, ownership, approvals, rollback, and residual obligations. Translation and currency conversion do not validate transfer.

Use aggregate, redacted, pseudonymous, minimum-necessary evidence. Do not label dissent or access barriers as personal resistance; inspect awareness, comprehension, authority, access, value, capability, capacity, trust, support, and deliberate rejection separately. Do not expose sensitive personal data or rank named people for consequential customer or employment decisions.

Deliver In Order

Follow [output-contract.md](references/output-contract.md). Deliver the change contract and source ledger; decomposition and current-to-target states; participant roles, impact, authority, dependencies and capacity; readiness gates and decisions; communications and enablement; migration, cohorts, cutover, rollback, recovery and decommissioning; rollout, adoption, support, outcomes and causal boundaries; version, market, privacy and fairness governance; specialist handoffs, pinned sources, approval-ready external actions, and completion record.

External-Action Boundary

Create and read local artifacts only. Do not access authenticated project, HR, email, chat, CRM, analytics, product, billing, experiment, cloud, support, legal, or vendor systems; export or join personal data; assign owners; send communications; enroll training; change permissions, flags, products, prices, data, systems, or records; execute migrations, cutovers, rollbacks, deletions, or decommissioning; contact people; or claim rollout, communication, competence, adoption, completion, benefit, or impact without separate task-level authorization and controls.

Keep One Output Language

Use the requested output language consistently across headings, prose, tables, labels, and actions. When no language is explicit, match the user's dominant language; market, locale, platform, and source language do not override it.

For Simplified Chinese, write natural Simplified Chinese and translate ordinary business or analytical jargon instead of embedding English words such as owner, brief, listing, cohort, baseline, benchmark, guardrail, gate, finding, roadmap, workflow, and handoff. Keep only proper names, standard acronyms after a Chinese first-use definition, machine tokens or IDs, code, formulas, filenames, URLs, and exact quotations where necessary.

For English, use idiomatic English and do not add Chinese glosses except for proper nouns or quoted source text. Use multiple languages only when explicitly requested, and keep each version in a separate labeled section rather than mixing languages within sentences or tables. Do not alternate languages for emphasis or perceived expertise.

Completion Gate

Confirm the output passes [output-contract.md](references/output-contract.md); the decision, authority, scope, current and target states, sources, versions, participants, impacts, dependencies, capacity, readiness, communications, enablement, migration, rollout, adoption, support, outcomes, risks, residual obligations, markets, privacy, fairness, handoffs, and action boundary are explicit; independent changes remain separate; blockers were not averaged away; activities did not become adoption or benefits; the old state was not retired without proof; dissent and sensitive data are protected; specialist work was not replaced; and no external action occurred.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.