change-plan
Draft or review a decision-ready change plan — impacts, staged rollout with acceptance and abort criteria, rollback or forward recovery, and required…
Skill by chandel-workspace
Chalk Labs
Need help deploying change-plan?
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.
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/chandel-workspace-change-plan-a33f73
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.
About
Use cases: devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
change-plan- Description
- Draft or review a decision-ready change plan — impacts, staged rollout with acceptance and abort criteria, rollback or forward recovery, and required approvals — for a proposed change, migration, deploy, or rollout. Use when asked to plan, de-risk, or review the plan for a change before it happens. Not for status summaries, executing migrations, casual edits, incident postmortems, or general programming.
- License
- MIT
- Instructions
- 64 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Change plan Prepare or review a decision-ready plan for a proposed change, migration, or rollout. It plans work; it does not execute it, create tickets, or post updates. ## Ground the plan Use supplied facts first, then local, in-scope evidence. Label every material statement as **known**, **assumed**, or **unknown**. Missing critical decisions keep the result a draft with one specific open question; never invent a person, threshold, date, owner, or approval. Approval status is **pending** unless evidence says otherwise. Cover the change and why; affected users, systems, data, and cost; dependencies; constraints; and material risks. Name evidence or its absence instead of converting uncertainty into confidence. ## Rollout and recovery Propose staged rollout steps. Each needs an observable acceptance check, abort criterion, and dependencies needed before it begins. Give rollback its own record: trigger, steps, owner (or **unassigned**), and recovery verification. Identify irreversible work explicitly; describe forward recovery rather than pretending rollback is possible. Do not imply permission to execute, create a ticket, deploy, migrate data, or send. ## Output Honor an explicit user format, length, or word limit before this default structure. Treat the limit as a hard delivery constraint: reserve a small margin, compress or combine sections, and use only the plan elements material to the decision. Before returning, count words with an available local means when a word limit was requested. When no stricter user format applies, use this concise structure as a menu rather than a mandatory expansion: 1. Change and decision status 2. Known / assumed / unknown facts 3. Impact and dependencies 4. Staged rollout with acceptance and abort criteria 5. Rollback or forward recovery 6. Required approvals and open decisions Omit or merge headings that have no material content; preserve critical uncertainty, approval, acceptance, abort, and recovery information in the available space. Optional communications may be supplied as clearly labelled drafts only; never send or post them. If the user explicitly requests a local plan file, create it in the requested location; otherwise reply in the conversation. ## Boundaries and handoffs This skill produces the planning record only. After separate implementation authorization, the available executor role (for example `fleetcraft:executor` in the plugin or a manually installed executor definition) is the delegation target for bounded implementation, per `fleet-orchestrator`. A plan approved here is **not** authorization to deploy, migrate, spend, post, or connect an account — that gate stays with the user. Where the change touches a user-facing visual surface, the ship decision still runs through `design-judge`; this skill does not substitute for it. Workflow design independently informed by Anthropic's [change-request skill](https://github.com/anthropics/knowledge-work-plugins/blob/1f517b9de47e827c80cd933ed364e16838072239/operations/skills/change-request/SKILL.md) (Apache-2.0 source observed); this skill does not reuse its template or connector behavior.
From chandel-workspace/fleetcraft, MIT.
More from chandel-workspace/fleetcraft
- 0.552score
fleet-orchestrator
chandel-workspace
Evidence-first orchestration for Claude Code: capability-matched delegation, concise agent briefs, independent verification, durable background-work routing…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
design-judge
chandel-workspace
Screenshot-first review for a UI, page, deck, or creative before shipping.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
change-plan
chandel-workspace
Draft or review a decision-ready change plan — impacts, staged rollout with acceptance and abort criteria, rollback or forward recovery, and required…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
debugging-and-error-recovery
chandel-workspace
Systematic root-cause debugging when something is broken — a failing test, a broken build, a runtime error, a flaky or non-reproducible bug, or behaviour that…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
performance-diagnosis
chandel-workspace
Diagnose and fix slow software with measurement, not guesswork — slow pages, slow API endpoints, slow SQL, N+1 queries, connection-pool exhaustion, cache…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
product-interface-craft
chandel-workspace
Build or redesign usable product interfaces with complete states and rendered desktop/mobile validation.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
growth-web-architect
chandel-workspace
Architect or audit acquisition pages for conversion, accessibility, responsive behavior, and proof integrity.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
incident-miner
chandel-workspace
Turn a resolved incident or hard-won fix into an evidence-backed lesson or skill proposal.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
doctor
chandel-workspace
Run Fleetcraft's read-only source or plugin preflight and report the observed result.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
image-to-code
chandel-workspace
Implement a supplied visual reference as an accessible interface and compare a rendered result at the reference viewport; not for inventing a design without a…
SkillBFreshness: B★ 1Claude Code +9 - 0.294score
project-handoff
chandel-workspace
No description from the publisher yet.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 7, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/chandel-workspace/fleetcraft
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from chandel-workspace
- 0.552score
fleet-orchestrator
chandel-workspace
Evidence-first orchestration for Claude Code: capability-matched delegation, concise agent briefs, independent verification, durable background-work routing…
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
design-judge
chandel-workspace
Screenshot-first review for a UI, page, deck, or creative before shipping.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
debugging-and-error-recovery
chandel-workspace
Systematic root-cause debugging when something is broken — a failing test, a broken build, a runtime error, a flaky or non-reproducible bug, or behaviour that…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
performance-diagnosis
chandel-workspace
Diagnose and fix slow software with measurement, not guesswork — slow pages, slow API endpoints, slow SQL, N+1 queries, connection-pool exhaustion, cache…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
change-plan
chandel-workspace
Draft or review a decision-ready change plan — impacts, staged rollout with acceptance and abort criteria, rollback or forward recovery, and required…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
product-interface-craft
chandel-workspace
Build or redesign usable product interfaces with complete states and rendered desktop/mobile validation.
SkillBFreshness: B★ 1Claude Code +9
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 change-plan 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.
Cite this page
change-plan skill. Agent Mart. https://agentmart.dev/skills/chandel-workspace-change-plan-a33f73 (last updated 2026-10-24)