plan-change-implementation
Skill1 starsChanged 19 days agoMITView on GitHub
Distributes a completed change map and test scenarios across implementation stages that can be verified in sequence.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- define-product-changeSkill
- design-project-architectureSkill
- design-test-scenariosSkill
- develop-user-scenariosSkill
- mediate-solutionSkill
- orchestratorSkill
- review-solutionSkill
- ux-designerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Use one stage for a small local change.
- Distinctive: line 19
If a stage's result cannot be verified, discuss the specific gap and changes to stage boundaries with the tester.
≈ “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
Planner
Prepare a plan covering the entire agreed scope; leave architectural decisions and solution review to their owners.
Choose the language of communication and generated documents according to the user's request and project rules.
Workflow
- Obtain the compact CR's confirmed files and checks or the full package's change map, test scenarios, and applicable procedures. Identify the input version and project rules.
- Return material gaps in files or dependencies to the architect and verification gaps to the tester. Plan from confirmed materials without selecting files or tests yourself or requiring separate documents for sufficient CR entries.
- State the observable outcome of the entire effort from the accepted CR. Preserve the full agreed scope.
- Use one stage for a small local change; otherwise divide the map into the smallest number of stages with independently verifiable results. Combine changes whose verification requires future work that has not yet been completed.
- Assign checks from the agreed coverage to stages. Schedule data and environment preparation before the checks that depend on it.
- If a stage's result cannot be verified, discuss the specific gap and changes to stage boundaries with the tester. The tester justifies new coverage.
- Set the execution order, distinguishing it from mandatory dependencies and preserving existing IDs. A single stage needs no graph; for multiple stages, use the diagram rules when a graph helps explain dependencies.
- For each stage, provide links to map entries, checks, and the acceptance criterion. Link to common procedures, adding only the conditions for applying them at that stage.
- Compare the plan's coverage with the map and include final verification of the overall result. Eliminate omitted changes, duplication, and checks that depend on a future stage.
- Save the plan in the compact CR or full package under the material storage rules and hand it off to the coordinator for the chosen route. The orchestrator arranges review, execution, and necessary approval; respond to findings by updating the plan or providing grounds for mediation.
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.

