skill-lake-repair

Name: skill-lake-repair
Author: benbrastmckie

Engineering Community

Repo stars 435
Author updated Live
Author repo nvim

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Engineering
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 88 / 100 · community maintained
Author / version / license: @benbrastmckie · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Not required
Operating systems: Unspecified (assume cross-platform)
Runtime requirements: No special requirements
Permissions: Read-only
Write / modify
Shell exec
Network behavior: Local-only
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview skill-lake-repair.preview

---
name: skill-lake-repair
description: Run Lean build with automatic error repair for missing cases, unused variables, and unused impor…
category: engineering
runtime: no special runtime
---

# skill-lake-repair output preview

## PART A: Task fit
- Use case: Run Lean build with automatic error repair for missing cases, unused variables, and unused imports Direct execution skill for automated Lean build repair. Runs lake build, parses errors, and automatically fixes common mechanical errors in an iterative loop. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Execution / Step 1: Parse Arguments / Step 2: Initial Clean (Optional)” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Run Lean build with automatic error repair for missing cases, unused variables, and unused imports Direct execution skill for automated Lean build repair. Runs lake build, parses errors, and automatically fixes common mechanical errors in an iterative loop. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Execution / Step 1: Parse Arguments / Step 2: Initial Clean (Optional)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.

## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: skill-lake-repair
description: Run Lean build with automatic error repair for missing cases, unused variables, and unused impor…
category: engineering
source: benbrastmckie/nvim
---

# skill-lake-repair

## When to use
- Run Lean build with automatic error repair for missing cases, unused variables, and unused imports Direct execution sk…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “Execution / Step 1: Parse Arguments / Step 2: Initial Clean (Optional)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "skill-lake-repair" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> Execution / Step 1: Parse Arguments / Step 2: Initial Clean (Optional)
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
  guardrails -> usually needs no extra API key + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Run Lean build with automatic error repair for missing cases, unused variables, and unused imports Direct execution skill for au…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Execution”, “Step 1: Parse Arguments”, “Step 2: Initial Clean (Optional)”, “Step 3: Build Loop”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name skill-lake-repair directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Execution / Step 1: Parse Arguments / Step 2: Initial Clean (Optional)” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Lake Repair Skill (Direct Execution)

Direct execution skill for automated Lean build repair. Runs lake build, parses errors, and automatically fixes common mechanical errors in an iterative loop.

This skill executes inline without spawning a subagent.

Execution

Step 1: Parse Arguments

Extract flags from command input:

--clean: Run lake clean before building
--max-retries N: Maximum fix iterations (default: 3)
--dry-run: Preview fixes without applying
--module NAME: Build specific module only

clean=false
max_retries=3
dry_run=false
module=""

for arg in "$@"; do
  case "$arg" in
    --clean) clean=true ;;
    --dry-run) dry_run=true ;;
    --max-retries=*) max_retries="${arg#*=}" ;;
    --module=*) module="${arg#*=}" ;;
  esac
done

Step 2: Initial Clean (Optional)

If --clean flag is set:

if [ "$clean" = true ]; then
  echo "Running lake clean..."
  lake clean
fi

Step 3: Build Loop

Initialize tracking variables:

retry_count=0
previous_errors="" (for cycle detection)
total_fixes=0

Step 4: Run Build

Attempt to build the project:

if [ -n "$module" ]; then
  build_output=$(lake build "$module" 2>&1)
else
  build_output=$(lake build 2>&1)
fi
build_exit_code=$?

Step 5: Parse Build Errors

Extract errors and warnings from build output using regex pattern:

Pattern: ^(.+\.lean):(\d+):(\d+): (error|warning): (.+)$

Step 6: Classify Errors

Error Pattern	Fix Type
Missing cases	missing_cases
Unused variable	unused_variable
Unused import	unused_import
All other	UNFIXABLE

Step 7: Apply Fixes

Missing Cases Fix

Add match cases with sorry placeholders.

Unused Variable Fix

Rename by adding underscore prefix: {name} -> _{name}

Unused Import Fix

Remove the import line (only clean single-import lines).

Step 8: Final Report

After loop exits:

Lake Build Complete
===================

Build succeeded after {retry_count} iterations.

Fixes applied:
- {file}:{line} - {description}

All modules built successfully.

Error Handling

MCP Tool Failure

Fall back to lake build via Bash.

File Read/Write Failure

Skip that particular fix, continue with others.

Parse Failure

Treat as unfixable error.

Safety Measures

Conservative Fixes

All missing case fixes use sorry placeholders
Unused variable fixes only add underscore prefix
Unused import removal is cautious (single-import lines only)

Cycle Prevention

Track error signatures between iterations
Stop if same errors recur
Hard limit via max_retries (default 3)

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add benbrastmckie/nvim/.claude/extensions/lean/skills/skill-lake-repair -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

88 / 100

Community

未声明 license/许可。
未声明 version。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
benbrastmckie/nvim
中文

More by @benbrastmckie

Category & tags

Category Engineering