Resource
Markdown Output Prompt — Lock the Document Structure
The contract that stops AI documents from restructuring themselves: a pinned section skeleton, forced tables, and strict consistency rules.
Handoff Completeness Review Prompt — What's Missing Before You Continue
Review a project handoff or onboarding package for what's missing — decisions, files, assumptions, constraints, risks, and next actions — and return a completeness score and a ready / not-ready verdict.
Overview
A handoff that looks complete is the most dangerous kind: the gaps only surface once the new chat, model, or teammate is already stuck. This prompt reviews a handoff or onboarding package before that happens — it reads what was handed over and reports what's missing: an explicit missing-context checklist, the decisions that were made but not recorded, the files, systems, and dependencies not mentioned, the assumptions left unstated, the open risks, and the questions to ask before continuing. It ends with a completeness score, a ready / not-ready verdict, suggested additions, and a next-action checklist. It is a human-readable review, not an automated gate: it does not run code, execute tests, or validate a Workspace automatically, and it does not create the handoff — it checks one. It is the completeness gate that project-handoff and codebase-onboarding packages otherwise lack.
How to use this resource
-
Check against a complete checklist
The package is scored against the categories a good handoff covers, each marked present, partial, or missing.
-
Name the gaps, don't fill them
Missing decisions, files, assumptions, and risks are named explicitly — never invented to make the package look complete.
-
Give a clear verdict
A ready / not-ready call plus the questions and additions that would close the gaps, so continuing is a decision, not a gamble.
Why This Works
- Handoff gaps are invisible to the person who wrote the package — an outside completeness check is what surfaces them
- A ready / not-ready verdict turns "looks fine" into an explicit decision about whether to continue
- Naming gaps instead of inventing fills keeps the review honest and produces a real to-do list, not false confidence
Best for
- Checking a project handoff before a new chat or teammate continues
- Reviewing codebase onboarding context for gaps
- Finding missing decisions, files, and constraints in a handoff
- Preparing continuity packages for carrying work across sessions
Not for
- Creating the original handoff package — that's the Context Handoff Builder
- Summarizing a meeting — that's the meeting-notes resources
- Reviewing code quality — that's the Code Review tools
- Running automated project validation — this is a human-readable review, not an automated gate
Use cases
- Checking a project handoff before a new chat or teammate continues the work
- Reviewing a codebase onboarding package for missing decisions and constraints
- Producing a ready / not-ready verdict and a list of questions before resuming a project
FAQ
Will this handoff review invent the missing decisions to fill the gaps?
It names gaps rather than filling them. A Rules line is explicit: "never invent a decision, file, or fact to fill a gap — name the gap instead." So MISSING DECISIONS and MISSING FILES / SYSTEMS / DEPENDENCIES list what's absent and why each matters, and you take that to whoever wrote the handoff. The markdown-output-builder formats the prompt; the completeness judgment happens when you run it in your assistant.
What does the ready / not-ready verdict actually decide?
It states whether the next chat, model, or teammate can continue safely on the package as-is, plus the single most important reason. The prompt insists the verdict be honest — "a package that looks tidy but omits a load-bearing decision is NOT ready." It's a human-readable review, so this is a recommendation you weigh, not an automated gate; the prompt explicitly does not run code, execute tests, or validate anything.
Can I use this to build the handoff instead of checking one?
This checks an existing package; it doesn't author one. It reviews what was handed over against the MISSING CONTEXT CHECKLIST categories — goal, decisions, constraints, files/systems, risks — marking each present / partial / missing. It ends with SUGGESTED ADDITIONS and a NEXT-ACTION CHECKLIST telling you what to add, but you write those additions into the handoff yourself. Creating the original package is a separate task.
More resources from Markdown Output Builder
Resource
README Prompt Template
Overview, Installation, Usage, Examples, Configuration — the README skeleton with required, runnable code examples.
Resource
API Documentation Prompt
Overview, Authentication, Endpoints, Error Handling, Rate Limits — endpoint docs in an identical structure, with parameter tables and runnable examples forced.
Resources that pair well
Resource
Executive Summary Prompt
Summary, Why It Matters, What Happens Next — the executive summary contract for readers who will never open the source.
Resource
Force JSON Output from AI
Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.
Resource
Fix Invalid JSON from AI
The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.
Related tools
Tool
Markdown Output Builder
Build prompts that produce documents in a fixed structure — headings, sections, and tables.
Workflows that use this resource
Workflow
AI Project Handoff Workflow
Carry a project into a new chat, model, or teammate without the context evaporating — capture the state, distill what's worth keeping, and rebuild it as durable context on the other side.