apply-architecture
Skill1 starsChanged 8 days agoMITView on GitHub
Use when a change adds, moves or splits a module, or changes a public interface. Checks the design against the architecture principles in this repository.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bootstrapSkill
- clarify-intentSkill
- code-reviewSkill
- map-workSkill
- plan-workSkill
- releaseSkill
- tdd-loopSkill
- triageSkill
- write-adrSkill
- write-prSkill
- writing-checkSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
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 8
Use when you design or change system structure.
- Distinctive: line 10
Read the relevant architecture principles and check the change against them.
- Distinctive: line 12
If the feature has a plan, read its constraints and decisions before you check the design.
- Distinctive: line 17
Read architecture/index.md and the specific files that apply (orthogonality, design-by-contract, reversibility, etc.).
- Distinctive: line 19
Prefer the smallest design that satisfies the principles.
- Distinctive: line 20
If a principle is violated, propose a smaller or more reversible alternative.
- Distinctive: line 24
If you can start subagents, use them when two or more designs are possible.
- Distinctive: line 34
If you cannot start subagents, do the steps one at a time in the order of this skill.
- Distinctive: line 38
When this skill applies, also read stewardship.
- Distinctive: line 42
Do not invent new principles.
- Distinctive: line 44
Keep the change reversible when possible.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Apply architecture
Use when you design or change system structure.
Read the relevant architecture principles and check the change against them.
If the feature has a plan, read its constraints and decisions before you check the design. Record each important new decision in the plan. Keep the permanent decisions in an ADR or in the permanent documentation. Follow feature plans.
Steps
- Identify the design decisions in the task.
- Read architecture/index.md and the specific files that apply (orthogonality, design-by-contract, reversibility, etc.).
- For each decision, state which principle it follows or violates.
- Prefer the smallest design that satisfies the principles.
- If a principle is violated, propose a smaller or more reversible alternative.
Subagents
If you can start subagents, use them when two or more designs are possible. Do step 1 yourself. Then check each design against the principles at the same time, each design in its own subagent. Give each subagent a brief that is complete without your context:
- The task, the design decisions from step 1 and the full text of the one design that it checks.
- The full text of steps 2 and 3, and the rules of this skill.
- What to report: for each decision, the principle that it follows or violates, with a link to the principle file. Also the trade-offs.
- A word limit, for example 400 words.
- This line: "Report to me only. Do not change code, post, approve or merge."
Then collect the reports. Do steps 4 and 5 yourself. A report from a subagent is a claim. Read each principle file that a report links before you use its result. Compare the designs yourself. Do not select a design only because a report prefers it.
If you cannot start subagents, do the steps one at a time in the order of this skill. For each design, do steps 2 and 3. Do steps 4 and 5 once, after you have checked every design.
Rules
- When this skill applies, also read stewardship. Judge the long-term consequences, the alternatives, the reversibility and the documented intent. Keeping the current design is a valid result. Do not copy that page.
- Do not invent new principles. Use only the files in architecture/.
- State trade-offs when two principles pull in different directions.
- Keep the change reversible when possible. See reversibility.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.