heal

Included with Lifetime

$97 forever

Use when build/test/lint/typecheck is failing and the user wants automatic recovery. Self-healing loop — retries with DIFFERENT strategies, not the same one twice. Bounded retry count.

Code Review

What this skill does


# heal

Failing CI / failing local checks → auto-fix loop. Smart enough to not loop forever.

## Method

1. **Capture failure.** Run the failing command. Save full stderr + first 100 lines stdout.
2. **Classify.** Is this:
   - Type error? → narrow to file:line, propose fix
   - Lint error? → run linter's auto-fix, then re-run
   - Test failure? → read the test, read the code, hypothesis-driven fix (use `fix` skill discipline)
   - Build error? → missing dep / wrong import / wrong config
   - Flaky? → re-run once. If passes, log to memory; do NOT mark stable.
2. **Strategy 1.** Apply the most-likely fix.
3. **Re-run.** If pass → done. If fail and **same error** → escalate. If fail and **different error** → strategy 2.
4. **Strategy 2.** Different angle (e.g. if strategy 1 was "add type annotation", strategy 2 is "fix the call site").
5. **Strategy 3.** Read the relevant area more broadly. If still failing, **stop** and surface to user with the full diagnosis.
6. **Cap.** Max 3 strategies per failure. No infinite loops.

## Output shape per cycle

```
Cycle 1: type error in src/foo.ts:42
  Strategy: <description>
  Result:   ✗ same error
Cycle 2: ...
  Strategy: <different angle>
  Result:   ✓ fixed, moving on
Cycle 3: lint error in tests/bar.test.ts:7
  Strategy: <description>
  Result:   ✓ fixed
Final:   build green
```

If escalating to user:
```
Stuck after 3 strategies. Diagnosis:
  <hypothesis>
Suggested next: <human-driven option>
```

## Rules

- **Never retry the same strategy twice.** Define strategy by approach, not just by file edited.
- Never silently weaken tests / disable checks to make CI green.
- Never edit beyond the failure's actual scope.
- Cap at 3 strategies per failure; cap at 5 failures per session before bailing entirely.
- Capture every cycle to memory — future heal sessions learn what worked.

## Anti-patterns

- Same fix applied twice with slight variation (counts as same strategy)
- Casting the type to `any` to bypass type errors
- Adding `eslint-disable` to bypass lint
- `@skip` or deleting failing tests
- Retrying network failures with longer timeouts but no other change

## When NOT to use

- New work (no existing failure) — `/siftcoder:build` or `/siftcoder:add-feature`
- Single known fix — apply directly, no heal loop needed
- Investigation only — `/siftcoder:investigate`

## Subagent dispatch

- `general-purpose` for each strategy attempt
- `investigator` if 2 strategies fail (escalate to deeper diagnosis)

## Memory capture

Each cycle's strategy + result. Future "heal X" queries hit prior strategies that worked for the same error class.

Files: 1

Size: 2.8 KB

Complexity: 6/100

Category: Code Review

Source: https://github.com/ialameh/sift-coder/tree/main/skills/coding/heal

Related in Code Review

gstack

Included

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)

Code Reviewscriptsfeatured

startup-due-diligence

Included

Legal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.

Code Reviewscripts

interview-master

Included

This skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.

Code Reviewscripts

fix-issue

Included

Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.

Code Reviewscripts

sf-apex

Included

Generates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.

Code Reviewscripts

swift-development

Included

Comprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.

Code Reviewscripts