improve-codebase-architecture

Name: improve-codebase-architecture
Author: stevesolun

560stars68forks

How to install improve-codebase-architecture?

stevesolun/ctx/improve-codebase-architecture

$npx -y skills add stevesolun/ctx --skill improve-codebase-architecture

Installs into the current project.

Summary

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-

Files · 1

View on GitHub

SKILL.md

1	# Improve Codebase Architecture
2
3	Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
4
5	## Glossary
6
7	Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in [LANGUAGE.md](LANGUAGE.md).
8
9	- Module — anything with an interface and an implementation (function, class, package, slice).
10	- Interface — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
11	- Implementation — the code inside.
12	- Depth — leverage at the interface: a lot of behaviour behind a small interface. Deep = high leverage. Shallow = interface nearly as complex as the implementation.
13	- Seam — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
14	- Adapter — a concrete thing satisfying an interface at a seam.
15	- Leverage — what callers get from depth.
16	- Locality — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
17
18	Key principles (see [LANGUAGE.md](LANGUAGE.md) for the full list):
19
20	- Deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
21	- The interface is the test surface.
22	- One adapter = hypothetical seam. Two adapters = real seam.
23
24	This skill is _informed_ by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.
25
26	## Process
27
28	### 1. Explore
29
30	Read the project's domain glossary and any ADRs in the area you're touching first.
31
32	Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
33
34	- Where does understanding one concept require bouncing between many small modules?
35	- Where are modules shallow — interface nearly as complex as the implementation?
36	- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no locality)?
37	- Where do tightly-coupled modules leak across their seams?
38	- Which parts of the codebase are untested, or hard to test through their current interface?
39
40	Apply the deletion test to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
41
42	### 2. Present candidates
43
44	Present a numbered list of deepening opportunities. For each candidate:
45
46	- Files — which files/modules are involved
47	- Problem — why the current architecture is causing friction
48	- Solution — plain English description of what would change
49	- Benefits — explained in terms of locality and leverage, and also in how tests would improve
50
51	Use CONTEXT.md vocabulary for the domain, and [LANGUAGE.md](LANGUAGE.md) vocabulary for the architecture. If `CONTEXT.md` defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
52
53	ADR conflicts: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly (e.g. _"contradicts ADR-0007 — but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
54
55	Do NOT propose interfaces yet. Ask the user: "Which of these would you like to explore?"
56
57	### 3. Grilling loop
58
59	Once the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
60
61	Side effects happen inline as decisions crystallize:
62
63	- Naming a deepened module after a concept not in `CONTEXT.md`? Add the term to `CONTEXT.md` — same discipline as `/grill-with-docs` (see [CONTEXT-FORMAT.md](../grill-with-docs/CONTEXT-FORMAT.md)). Create the file lazily if it doesn't exist.
64	- Sharpening a fuzzy term during the conversation? Update `CONTEXT.md` right there.
65	- User rejects the candidate with a load-bearing reason? Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones. See [ADR-FORMAT.md](../grill-with-docs/ADR-FORMAT.md).
66	- **Want to explore al

People who liked this also viewed

6 picks

Type

improve-codebase-architecture

560stars68forks

View on GitHub

How to install improve-codebase-architecture?

stevesolun/ctx/improve-codebase-architecture

$npx -y skills add stevesolun/ctx --skill improve-codebase-architecture

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Improve Codebase Architecture
2
3	Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
4
5	## Glossary
6
7	Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in [LANGUAGE.md](LANGUAGE.md).
8
9	- Module — anything with an interface and an implementation (function, class, package, slice).
10	- Interface — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
11	- Implementation — the code inside.
12	- Depth — leverage at the interface: a lot of behaviour behind a small interface. Deep = high leverage. Shallow = interface nearly as complex as the implementation.
13	- Seam — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
14	- Adapter — a concrete thing satisfying an interface at a seam.
15	- Leverage — what callers get from depth.
16	- Locality — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
17
18	Key principles (see [LANGUAGE.md](LANGUAGE.md) for the full list):
19
20	- Deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
21	- The interface is the test surface.
22	- One adapter = hypothetical seam. Two adapters = real seam.
23
24	This skill is _informed_ by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.
25
26	## Process
27
28	### 1. Explore
29
30	Read the project's domain glossary and any ADRs in the area you're touching first.
31
32	Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
33
34	- Where does understanding one concept require bouncing between many small modules?
35	- Where are modules shallow — interface nearly as complex as the implementation?
36	- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no locality)?
37	- Where do tightly-coupled modules leak across their seams?
38	- Which parts of the codebase are untested, or hard to test through their current interface?
39
40	Apply the deletion test to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
41
42	### 2. Present candidates
43
44	Present a numbered list of deepening opportunities. For each candidate:
45
46	- Files — which files/modules are involved
47	- Problem — why the current architecture is causing friction
48	- Solution — plain English description of what would change
49	- Benefits — explained in terms of locality and leverage, and also in how tests would improve
50
51	Use CONTEXT.md vocabulary for the domain, and [LANGUAGE.md](LANGUAGE.md) vocabulary for the architecture. If `CONTEXT.md` defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
52
53	ADR conflicts: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly (e.g. _"contradicts ADR-0007 — but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
54
55	Do NOT propose interfaces yet. Ask the user: "Which of these would you like to explore?"
56
57	### 3. Grilling loop
58
59	Once the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
60
61	Side effects happen inline as decisions crystallize:
62
63	- Naming a deepened module after a concept not in `CONTEXT.md`? Add the term to `CONTEXT.md` — same discipline as `/grill-with-docs` (see [CONTEXT-FORMAT.md](../grill-with-docs/CONTEXT-FORMAT.md)). Create the file lazily if it doesn't exist.
64	- Sharpening a fuzzy term during the conversation? Update `CONTEXT.md` right there.
65	- User rejects the candidate with a load-bearing reason? Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones. See [ADR-FORMAT.md](../grill-with-docs/ADR-FORMAT.md).
66	- **Want to explore al

People who liked this also viewed

6 picks

Type