Skip to content

Commit 642ae3e

Browse files
MarcelloCuoghiCuoghi, Marcello
MarcelloCuoghi
and
Cuoghi, Marcello
authored
feat: add ruff-recursive-fix skill for iterative code quality enforcement (#1183)
Co-authored-by: Cuoghi, Marcello <Marcello.Cuoghi@systemlogistics.com>
1 parent c49c7a1 commit 642ae3e

2 files changed

Lines changed: 201 additions & 0 deletions

File tree

‎docs/README.skills.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -233,6 +233,7 @@ See [CONTRIBUTING.md](../CONTRIBUTING.md#adding-skills) for guidelines on how to
233233
| [roundup](../skills/roundup/SKILL.md) | Generate personalized status briefings on demand. Pulls from your configured data sources (GitHub, email, Teams, Slack, and more), synthesizes across them, and drafts updates in your own communication style for any audience you define. | None |
234234
| [roundup-setup](../skills/roundup-setup/SKILL.md) | Interactive onboarding that learns your communication style, audiences, and data sources to configure personalized status briefings. Paste in examples of updates you already write, answer a few questions, and roundup calibrates itself to your workflow. | `references/config-template.md` |
235235
| [ruby-mcp-server-generator](../skills/ruby-mcp-server-generator/SKILL.md) | Generate a complete Model Context Protocol server project in Ruby using the official MCP Ruby SDK gem. | None |
236+
| [ruff-recursive-fix](../skills/ruff-recursive-fix/SKILL.md) | Run Ruff checks with optional scope and rule overrides, apply safe and unsafe autofixes iteratively, review each change, and resolve remaining findings with targeted edits or user decisions. | None |
236237
| [rust-mcp-server-generator](../skills/rust-mcp-server-generator/SKILL.md) | Generate a complete Rust Model Context Protocol server project with tools, prompts, resources, and tests using the official rmcp SDK | None |
237238
| [sandbox-npm-install](../skills/sandbox-npm-install/SKILL.md) | Install npm packages in a Docker sandbox environment. Use this skill whenever you need to install, reinstall, or update node_modules inside a container where the workspace is mounted via virtiofs. Native binaries (esbuild, lightningcss, rollup) crash on virtiofs, so packages must be installed on the local ext4 filesystem and symlinked back. | `scripts/install.sh` |
238239
| [scaffolding-oracle-to-postgres-migration-test-project](../skills/scaffolding-oracle-to-postgres-migration-test-project/SKILL.md) | Scaffolds an xUnit integration test project for validating Oracle-to-PostgreSQL database migration behavior in .NET solutions. Creates the test project, transaction-rollback base class, and seed data manager. Use when setting up test infrastructure before writing migration integration tests, or when a test project is needed for Oracle-to-PostgreSQL validation. | None |

‎skills/ruff-recursive-fix/SKILL.md‎

Lines changed: 200 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,200 @@
1+
---
2+
name: ruff-recursive-fix
3+
description: Run Ruff checks with optional scope and rule overrides, apply safe and unsafe autofixes iteratively, review each change, and resolve remaining findings with targeted edits or user decisions.
4+
---
5+
6+
# Ruff Recursive Fix
7+
8+
## Overview
9+
10+
Use this skill to enforce code quality with Ruff in a controlled, iterative workflow.
11+
It supports:
12+
13+
- Optional scope limitation to a specific folder.
14+
- Default project settings from `pyproject.toml`.
15+
- Flexible Ruff invocation (`uv`, direct `ruff`, `python -m ruff`, or equivalent).
16+
- Optional per-run rule overrides (`--select`, `--ignore`, `--extend-select`, `--extend-ignore`).
17+
- Automatic safe then unsafe autofixes.
18+
- Diff review after each fix pass.
19+
- Recursive repetition until findings are resolved or require a decision.
20+
- Judicious use of inline `# noqa` only when suppression is justified.
21+
22+
## Inputs
23+
24+
Collect these inputs before running:
25+
26+
- `target_path` (optional): folder or file to check. Empty means whole repository.
27+
- `ruff_runner` (optional): explicit Ruff command prefix (for example `uv run`, `ruff`, `python -m ruff`, `pipx run ruff`).
28+
- `rules_select` (optional): comma-separated rule codes to enforce.
29+
- `rules_ignore` (optional): comma-separated rule codes to ignore.
30+
- `extend_select` (optional): extra rules to add without replacing configured defaults.
31+
- `extend_ignore` (optional): extra ignored rules without replacing configured defaults.
32+
- `allow_unsafe_fixes` (default: true): whether to run Ruff unsafe fixes.
33+
- `ask_on_ambiguity` (default: true): always ask the user when multiple valid choices exist.
34+
35+
## Command Construction
36+
37+
Build Ruff commands from inputs.
38+
39+
### 0. Resolve Ruff Runner
40+
41+
Determine a reusable `ruff_cmd` prefix before building commands.
42+
43+
Resolution order:
44+
45+
1. If `ruff_runner` is provided, use it as-is.
46+
2. Else if `uv` is available and Ruff is managed through `uv`, use `uv run ruff`.
47+
3. Else if `ruff` is available on `PATH`, use `ruff`.
48+
4. Else if Python is available and Ruff is installed in that environment, use `python -m ruff`.
49+
5. Else use any project-specific equivalent that invokes installed Ruff (for example `pipx run ruff`), or stop and ask the user.
50+
51+
Use the same resolved `ruff_cmd` for all `check` and `format` commands in the workflow.
52+
53+
Base command:
54+
55+
```bash
56+
<ruff_cmd> check
57+
```
58+
59+
Formatter command:
60+
61+
```bash
62+
<ruff_cmd> format
63+
```
64+
65+
With optional target:
66+
67+
```bash
68+
<ruff_cmd> format <target_path>
69+
```
70+
71+
Add optional target:
72+
73+
```bash
74+
<ruff_cmd> check <target_path>
75+
```
76+
77+
Add optional overrides as needed:
78+
79+
```bash
80+
--select <codes>
81+
--ignore <codes>
82+
--extend-select <codes>
83+
--extend-ignore <codes>
84+
```
85+
86+
Examples:
87+
88+
```bash
89+
# Full project with defaults from pyproject.toml
90+
ruff check
91+
92+
# One folder with defaults
93+
python -m ruff check src/models
94+
95+
# Override to skip docs and TODO-like rules for this run
96+
uv run ruff check src --extend-ignore D,TD
97+
98+
# Check only selected rules in a folder
99+
ruff check src/data --select F,E9,I
100+
```
101+
102+
## Workflow
103+
104+
### 1. Baseline Analysis
105+
106+
1. Run `<ruff_cmd> check` with the selected scope and options.
107+
2. Classify findings by type:
108+
- Autofixable safe.
109+
- Autofixable unsafe.
110+
- Not autofixable.
111+
3. If no findings remain, stop.
112+
113+
### 2. Safe Autofix Pass
114+
115+
1. Run Ruff with `--fix` using the same scope/options.
116+
2. Review resulting diff carefully for semantic correctness and style consistency.
117+
3. Run `<ruff_cmd> format` on the same scope.
118+
4. Re-run `<ruff_cmd> check` to refresh remaining findings.
119+
120+
### 3. Unsafe Autofix Pass
121+
122+
Run only if findings remain and `allow_unsafe_fixes=true`.
123+
124+
1. Run Ruff with `--fix --unsafe-fixes` using the same scope/options.
125+
2. Review resulting diff carefully, prioritizing behavior-sensitive edits.
126+
3. Run `<ruff_cmd> format` on the same scope.
127+
4. Re-run `<ruff_cmd> check`.
128+
129+
### 4. Manual Remediation Pass
130+
131+
For remaining findings:
132+
133+
1. Fix directly in code when there is a clear, safe correction.
134+
2. Keep edits minimal and local.
135+
3. Run `<ruff_cmd> format` on the same scope.
136+
4. Re-run `<ruff_cmd> check`.
137+
138+
### 5. Ambiguity Policy
139+
140+
If there are multiple valid solutions at any step, always ask the user before proceeding.
141+
Do not choose silently between equivalent options.
142+
143+
### 6. Suppression Decision (`# noqa`)
144+
145+
Use suppression only when all conditions are true:
146+
147+
- The rule conflicts with required behavior, public API, framework conventions, or readability goals.
148+
- Refactoring would be disproportionate to the value of the rule.
149+
- The suppression is narrow and specific (single line, explicit code when possible).
150+
151+
Guidelines:
152+
153+
- Prefer `# noqa: <RULE>` over broad `# noqa`.
154+
- Add a brief reason comment for non-obvious suppressions.
155+
- If two or more valid outcomes exist, always ask the user which option to prefer.
156+
157+
### 7. Recursive Loop and Stop Criteria
158+
159+
Repeat steps 2 to 6 until one of these outcomes:
160+
161+
- `<ruff_cmd> check` returns clean.
162+
- Remaining findings require architectural/product decisions.
163+
- Remaining findings are intentionally suppressed with documented rationale.
164+
- Repeated loop makes no progress.
165+
166+
Each loop iteration must include `<ruff_cmd> format` before the next `<ruff_cmd> check`.
167+
168+
When no progress is detected:
169+
170+
1. Summarize blocked rules and affected files.
171+
2. Present valid options and trade-offs.
172+
3. Ask the user to choose.
173+
174+
## Quality Gates
175+
176+
Before declaring completion:
177+
178+
- Ruff returns no unexpected findings for the chosen scope/options.
179+
- All autofix diffs are reviewed for correctness.
180+
- No suppression is added without explicit justification.
181+
- Any unsafe fix with possible behavioral impact is highlighted to the user.
182+
- Ruff formatting is executed in every iteration.
183+
184+
## Output Contract
185+
186+
At the end of execution, report:
187+
188+
- Scope and Ruff options used.
189+
- Number of iterations performed.
190+
- Summary of fixed findings.
191+
- List of manual fixes.
192+
- List of suppressions with rationale.
193+
- Remaining findings, if any, and required user decisions.
194+
195+
## Suggested Prompt Starters
196+
197+
- "Run ruff-recursive-fix on the whole repo with default config."
198+
- "Run ruff-recursive-fix only on src/models, ignore DOC rules."
199+
- "Run ruff-recursive-fix on tests with select F,E9,I and no unsafe fixes."
200+
- "Run ruff-recursive-fix on src/data and ask me before adding any noqa."

0 commit comments

Comments
 (0)