dotnet-mcaf-human-review-planning
Skill13 starsChanged 8 months agoMITView on GitHub
Apply MCAF human-review-planning guidance for a large AI-generated code drop by reading the target area, tracing the natural user and system flows, identifying the riskiest boundaries, and prioritizing the files a human should inspect first. Use when the codebase is too large to review line-by-line and you need a practical review sequence plus a prioritized file list.
In this repository84 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- dotnet-analyzer-configSkill
- dotnet-architectureSkill
- dotnet-archunitnetSkill
- dotnet-aspireSkill
- dotnet-aspnet-coreSkill
- dotnet-asynkron-profilerSkill
- dotnet-azure-functionsSkill
- dotnet-biomeSkill
- dotnet-blazorSkill
- dotnet-chousSkill
- dotnet-clocSkill
- dotnet-code-analysisSkill
- dotnet-codeqlSkill
- dotnet-code-reviewSkill
- dotnet-complexitySkill
- dotnet-coverletSkill
- dotnet-csharpierSkill
- dotnet-entity-framework6Skill
- dotnet-entity-framework-coreSkill
- dotnet-eslintSkill
- dotnet-formatSkill
- dotnet-grpcSkill
- dotnet-htmlhintSkill
- dotnet-legacy-aspnetSkill
- dotnet-libvlcSkill
- dotnet-managedcode-communicationSkill
- dotnet-managedcode-markitdownSkill
- dotnet-managedcode-mimetypesSkill
- dotnet-managedcode-orleans-graphSkill
- dotnet-managedcode-orleans-signalrSkill
- dotnet-managedcode-storageSkill
- dotnet-mauiSkill
- dotnet-mcaf-agile-deliverySkill
- dotnet-mcaf-devexSkill
- dotnet-mcaf-documentationSkill
- dotnet-mcaf-feature-specSkill
- dotnet-mcaf-ml-ai-deliverySkill
- dotnet-mcaf-nfrSkill
- dotnet-mcafSkill
- dotnet-mcaf-source-controlSkill
- dotnet-mcaf-ui-uxSkill
- dotnet-mcpSkill
- dotnet-metalintSkill
- dotnet-meziantou-analyzerSkill
- dotnet-microsoft-agent-frameworkSkill
- dotnet-microsoft-extensions-aiSkill
- dotnet-microsoft-extensionsSkill
- dotnet-minimal-apisSkill
- dotnet-mixed-realitySkill
- dotnet-mlnetSkill
- dotnet-modern-csharpSkill
- dotnet-mstestSkill
- dotnet-mvvmSkill
- dotnet-netarchtestSkill
- dotnet-nunitSkill
- dotnet-orleansSkill
- dotnet-profilingSkill
- dotnet-project-setupSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 9 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
leave reusable project context so future tasks are faster and safer
- Distinctive: line 38
Read the nearest AGENTS.md and confirm scope and constraints.
- Very specific: line 39
Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
- Distinctive: line 44
Read enough of the target area and its immediate boundaries to understand the generated code before planning review.
- Distinctive: line 52
Use that flow to derive the most efficient human review sequence.
- Distinctive: line 53
Use the reviewer's domain knowledge as a force multiplier:
- Distinctive: line 55
look for places where the new feature should behave like nearby existing flows
- Very specific: line 67
If the user asks for a durable artifact, save the plan to the exact docs path they requested.
- Distinctive: line 87
Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.
- Distinctive: line 95
write a detailed execution plan from the chosen direction
- Distinctive: line 100
Update the plan after each iteration.
- Very specific: line 102
If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.
- Very specific: line 117
read references/review-plan-format.md for the output shape
- Very specific: line 118
read references/risk-signals.md when deciding what deserves human attention first
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MCAF: Human Review Planning
Trigger On
- a large AI-generated code drop needs a human review plan
- the reviewer cannot inspect every line and needs prioritization
- the user asks which files are highest risk before doing manual review
- the user names a generated folder and wants a saved review plan for it
Value
- produce a concrete project delta: code, docs, config, tests, CI, or review artifact
- reduce ambiguity through explicit planning, verification, and final validation skills
- leave reusable project context so future tasks are faster and safer
Do Not Use For
- normal small pull-request review
- automated bug finding without creating a human review sequence
Inputs
- the target folder, feature area, or bounded context under review
- the main user journeys or operational flows involved
- any known architecture context, adjacent entities, or existing system rules
- any exact output path the user wants for the saved plan
Quick Start
- Read the nearest
AGENTS.mdand confirm scope and constraints. - Run this skill's
Workflowthrough theRalph Loopuntil outcomes are acceptable. - Return the
Required Result Formatwith concrete artifacts and verification evidence.
Workflow
- Read enough of the target area and its immediate boundaries to understand the generated code before planning review.
- Map the natural flow of operations first:
- sign up or authentication
- create
- update
- register or configure
- execute primary business action
- complete, archive, or finalize
- Use that flow to derive the most efficient human review sequence.
- Use the reviewer's domain knowledge as a force multiplier:
- compare the generated code against known architecture and existing entities
- look for places where the new feature should behave like nearby existing flows
- prioritize boundaries where generated code may drift from established system rules
- Identify high-risk review zones:
- entry points and orchestration layers
- persistence and state transitions
- cross-boundary integrations
- permissions, validation, and invariants
- side effects such as email, payments, jobs, or notifications
- Produce two separate outputs:
- prioritized review flow
- prioritized files or modules to inspect
- Present both outputs in chat.
- If the user asks for a durable artifact, save the plan to the exact docs path they requested; otherwise use
docs/AREA/HUMAN_REVIEW_PLAN.md.
Deliver
- a prioritized human review sequence
- a prioritized list of files or modules to inspect first
- both sections presented separately in chat
- a saved
HUMAN_REVIEW_PLAN.mdwhen requested
Validate
- the plan is grounded in actual code reading, not only the folder names
- the review order follows actual user or system flows
- high-risk files are explained, not only listed
- priorities account for likely mismatch against existing architecture or analogous entities
- the plan helps a human skip low-value line-by-line review
- the saved plan is readable without extra chat context
Ralph Loop
Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.
- Brainstorm first (mandatory):
- analyze current state
- define the problem, target outcome, constraints, and risks
- generate options and think through trade-offs before committing
- capture the recommended direction and open questions
- Plan second (mandatory):
- write a detailed execution plan from the chosen direction
- list final validation skills to run at the end, with order and reason
- Execute one planned step and produce a concrete delta.
- Review the result and capture findings with actionable next fixes.
- Apply fixes in small batches and rerun the relevant checks or review steps.
- Update the plan after each iteration.
- Repeat until outcomes are acceptable or only explicit exceptions remain.
- If a dependency is missing, bootstrap it or return
status: not_applicablewith explicit reason and fallback path.
Required Result Format
status:complete|clean|improved|configured|not_applicable|blockedplan: concise plan and current iteration stepactions_taken: concrete changes madevalidation_skills: final skills run, or skipped with reasonsverification: commands, checks, or review evidence summaryremaining: top unresolved items ornone
For setup-only requests with no execution, return status: configured and exact next commands.
Load References
- read
references/review-plan-format.mdfor the output shape - read
references/risk-signals.mdwhen deciding what deserves human attention first
Example Requests
- "Plan a human review for this 40K-line AI-generated feature."
- "I cannot review every file. Tell me what to inspect first."
- "Trace the signup-to-completion flow and save a HUMAN_REVIEW_PLAN.md."
- "Look through the generated folder, give me two separate prioritized review lists, and save them under docs for this area."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

