LLM Skills
~/catalogue/organisation//SKILL
Organisationsource GitHub

Suggérer des tâches

/SKILL

Découvrir toutes les tâches réalisables dans le projet en cours et les ajouter à la liste des tâches

// contenu du skill

---

name: suggest-tasks

displayName: Suggest Project Tasks

description: Discover all actionable tasks in the current project and add them to the task list

version: 1.0.0

tags: [productivity, tasks, project-management, analysis]

---

Suggest Project Tasks

Performs comprehensive project analysis and creates tasks for everything that needs attention.

What It Analyzes

Universal (All Projects)

  • Git status: uncommitted changes, branches, stashes, conflicts
  • TODO/FIXME/HACK comments: code annotations needing attention
  • Test coverage: missing tests, failing tests
  • Dependencies: outdated packages, security vulnerabilities
  • Documentation: missing README sections, API docs
  • Security: hardcoded secrets, common vulnerabilities

Framework-Specific

Rails/Ruby:

  • Pending migrations
  • Missing model/controller specs
  • N+1 query patterns
  • Missing foreign key indexes
  • Route configuration issues

Node.js/TypeScript:

  • TypeScript type errors
  • ESLint/Prettier configuration
  • Bundle size concerns
  • Missing type definitions
  • React/Next.js specific issues

Python:

  • Mypy type checking
  • Missing docstrings
  • Django/FastAPI/Flask specific issues
  • Common anti-patterns

Rust:

  • Clippy warnings
  • Missing documentation
  • Unsafe code review
  • Test coverage

Instructions

When the user runs `/suggest-tasks`, perform these steps:

Step 1: Check for Existing Scan Results

Look for cached scan results at `/tmp/project-scan-*.json`. If recent (< 5 minutes), use those results. Otherwise, run a fresh scan.

Step 2: Detect Project Type

Run the project detection to identify what kind of project this is:

bash
~/.claude/hooks/analyzers/detect-project.sh .

Step 3: Run Analyzers

Based on the project type, run the appropriate analyzers. Always run the universal analyzers:

bash
~/.claude/hooks/analyzers/analyze-git.sh .
~/.claude/hooks/analyzers/analyze-todos.sh .
~/.claude/hooks/analyzers/analyze-tests.sh .
~/.claude/hooks/analyzers/analyze-deps.sh .
~/.claude/hooks/analyzers/analyze-docs.sh .
~/.claude/hooks/analyzers/analyze-security.sh .

Then run framework-specific analyzers based on detected types:

  • Rails/Ruby: `~/.claude/hooks/analyzers/analyze-rails.sh .`
  • Node/TypeScript: `~/.claude/hooks/analyzers/analyze-node.sh .`
  • Python: `~/.claude/hooks/analyzers/analyze-python.sh .`
  • Rust: `~/.claude/hooks/analyzers/analyze-rust.sh .`

Step 4: Parse Results

Each analyzer outputs JSON lines in this format:

json
{"category": "git", "task": "Task title", "description": "Details", "priority": "high|medium|low|critical"}

Collect all results and group by category.

Step 5: Create Tasks

For each discovered item, use TaskCreate to add it to the task list:

TaskCreate:
  subject: "[category] Task title"
  description: "Details from analyzer"
  activeForm: "Checking task..."

Step 6: Present Summary

After creating tasks, present a summary grouped by category:

## Project Analysis Complete

**Project Type:** Rails, TypeScript
**Tasks Created:** 24

### By Category:

#### Git & Version Control (3 tasks)
- [ ] Commit staged changes (high)
- [ ] Clean up merged branches (low)
- [ ] Push unpushed commits (medium)

#### Code Quality (5 tasks)
- [ ] Resolve 12 TODO comments (medium)
- [ ] Fix 3 FIXME comments (high)
...

#### Security (2 tasks)
- [ ] Review potential hardcoded secrets (critical)
- [ ] Update .gitignore for secrets (high)

...

Filtering

If the user provides a filter argument, only show tasks matching that category:

  • `/suggest-tasks git` - Only git-related tasks
  • `/suggest-tasks security` - Only security tasks
  • `/suggest-tasks rails` - Only Rails-specific tasks
  • `/suggest-tasks node` - Only Node.js-specific tasks
  • `/suggest-tasks python` - Only Python-specific tasks
  • `/suggest-tasks rust` - Only Rust-specific tasks
  • `/suggest-tasks todos` - Only TODO/FIXME tasks
  • `/suggest-tasks tests` - Only test-related tasks
  • `/suggest-tasks deps` - Only dependency tasks
  • `/suggest-tasks docs` - Only documentation tasks

Priority Levels

Tasks are assigned priorities based on urgency:

  • critical: Merge conflicts, security vulnerabilities, missing CSRF protection
  • high: Hardcoded secrets, pending migrations, type errors, bugs
  • medium: TODO comments, outdated dependencies, missing tests
  • low: Documentation gaps, code style, optimization suggestions

Notes

  • If this is not a recognized project type (no package.json, Gemfile, Cargo.toml, etc.), inform the user
  • The scan caches results to `/tmp/project-scan-*.json` for reuse
  • Tasks are deduplicated if the same task already exists in the task list
  • Focus on actionable items that can be worked on in the current session
// source originale publique
strataga/claude-setup
/skills/suggest-tasks/SKILL.md
Licence : Licence non indiquée. Consultez le dépôt avant toute réutilisation.
Projet indépendant, non affilié à Anthropic. Ce skill reste la propriété de son auteur original.
// installer ce skill
Collez cette commande dans votre terminal à la racine de votre projet :
mkdir -p .claude/commands && curl -o ".claude/commands/SKILL.md" "https://raw.githubusercontent.com/strataga/claude-setup/master/skills/suggest-tasks/SKILL.md"
Ensuite dans Claude Code, tapez /SKILL pour l'activer.
open_in_newVoir la source originale
// sauvegarder
Sauvegarde disponible après connexion.
loginSe connecter pour sauvegarder
// informations
Créateurstrataga
CatégorieOrganisation
Format.md
AccèsGratuit
// similaires

Skills Organisation

Voir toutarrow_forward