bbcode:autofix

Included with Lifetime

$97 forever

Autofix common code-quality issues by running a pipeline of focused sub-agents (one-class-per-file, etc.). Use when the user wants to clean up code smells, normalize file structure, or run autofix on a set of files.

General

What this skill does


# Autofix — Run Common Code-Quality Fixers

Apply a pipeline of focused sub-agents to detect and fix common code-quality issues in a target set of files. Each sub-agent in `agents/` owns one specific issue class.

## Arguments

`$ARGUMENTS` — Optional. Either a list of files / globs, or a natural-language description of which files to target (e.g. `src/**/*.ts`, `the auth module`, `everything I changed since main`). If omitted, target all **uncommitted** files in the working tree.

## Step 1 — Determine Target Files

Two branches:

### Branch A: No argument

Inspect uncommitted files in the working tree:

```bash
git status --porcelain
```

Build the target list from:
- Modified files (`M`, ` M`)
- Added files (`A`, `??`)
- Renamed files (`R` — use the new path)

Skip:
- Deleted files
- Files outside the repo
- Anything matching `.gitignore` patterns the working tree happens to surface

### Branch B: Argument provided

Interpret `$ARGUMENTS` as the targeting instruction:
- If it looks like a file path or glob → expand it directly (use `git ls-files` or globbing)
- If it looks like a natural-language description → resolve it to a concrete file list (ask the user to confirm if ambiguous)


## Step 2 — Discover Sub-Agents

List every `*.md` file in `agents/` (relative to this skill). Each file is a sub-agent specification: its body is the prompt, its filename is its identifier.

Each sub-agent file follows this shape:
- A **Purpose** section — what issue it fixes
- A **Detection** section — how it identifies affected files
- A **Fix** section — what changes it makes
- A **Constraints** section — what it must not touch

## Step 3 — Run the Sub-Agent Loop

For each sub-agent file in `agents/`:

1. **Spawn** a sub-agent via the `Agent` tool with `subagent_type: "general-purpose"`.
2. **Prompt** it with:
   - The **full content of the sub-agent's `.md` file** as instructions
   - The **resolved target file list** from Step 1
   - An explicit instruction to apply changes directly (Edit/Write), not just report
3. **Wait** for the sub-agent to complete and capture its summary.
4. **Report** back to the user: which files the sub-agent touched and a one-line summary of changes.

Run sub-agents **sequentially**, not in parallel — later fixers may depend on the structure produced by earlier ones (e.g. once `single-class-per-file` has split a file, naming/import fixers can run on the result).

## Step 4 — Final Summary

After all sub-agents complete, print:

```
## Autofix Summary

Target: <N files>
Sub-agents run: <N>

### <sub-agent-name>
- Files touched: <list>
- Changes: <one-line summary>

### <sub-agent-name>
- ...

Run tests / typecheck before committing.
```

## Rules

- **Never commit** — autofix only edits the working tree. The user reviews and commits.
- **Never run destructive git commands** (reset, clean, checkout --) to "reset" between sub-agents. The pipeline is additive.
- If a sub-agent fails or reports it cannot safely fix something, surface that in the summary and continue with the next sub-agent — do not abort the whole pipeline.
- Always use repo-root-relative paths in reports.
- If the target file list is empty, say so and exit; do not invent files.

Files: 5

Size: 35.5 KB

Complexity: 44/100

Category: General

Source: https://github.com/benjaminbenetti/bb-claude-plugins/tree/main/plugins/bbcode/skills/autofix

Related in General

modeling-omnistudio-epc-catalog

Included

Salesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).

Generalscripts

relationship-science-coach

Included

Use this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.

Generalscripts

building-sf-integrations

Included

Salesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).

Generalscripts

venue-templates

Included

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

Generalscripts

let-fate-decide

Included

Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.

Generalscripts

net-ops

Included

Cross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.

Generalscripts