GitHub
context-preservation
Activates during long sessions or before context compaction. Manages attention markers and ensures critical information survives memory compression.
Skills IA Recherche
Découvrez les skills Recherche, comparez leurs dépôts et consultez leurs instructions.
Catégories: Recherche
Recherche Effacer les filtres
Explorer
GitHub
error-recovery
Activates when errors occur during execution. Provides self-correction patterns for immediate error fixing without verbose explanations or apologies.
GitHub
ai-workflow-integration
Convert AI fluency into throughput by embedding AI into repeatable workflows with triggers, quality gates, and iteration loops that compound over time.
GitHub
ai-fluency-certification
Assess AI fluency proficiency using 5-level certification criteria (A through E) based on demonstrated capabilities across the 4D Framework dimensions.
GitHub
ai-collaboration-modes
Select appropriate human-AI collaboration modes: Automation (AI acts independently), Augmentation (AI assists human work), or Agency (AI takes delegated responsibility).
GitHub
ai-fluency-antipatterns
Recognize and avoid 15 common AI fluency anti-patterns that undermine effectiveness: over-reliance, prompt magic thinking, verification theater, and more.
GitHub
ai-instruction-design
Control AI output through structured specifications: define roles, scope, format, decision rules, and abstraction levels. Prompts become contracts, not requests.
GitHub
ai-4d-framework
Apply Anthropic's 4D Framework for AI delegation: Delegation (task selection), Description (instructions), Discernment (verification), and Diligence (iteration).
GitHub
ai-problem-framing
Turn vague intent into solvable structures with explicit objectives, constraints, success criteria, and clear human vs AI responsibility boundaries.
GitHub
ai-system-governance
Scale AI fluency beyond individuals through standards, guardrails, audit trails, and organizational policies that maintain quality and accountability.
GitHub
ai-evaluation-verification
Retain epistemic control by validating AI outputs against logic, first principles, and reality. Detect confident nonsense, false completeness, and category errors.
GitHub
ai-system-literacy
Build accurate mental models of AI behavior: understand context windows, probabilistic generation, hallucination causes, and predict failure modes before they occur.
GitHub
ai-reasoning-scaffolds
Use AI as a thinking partner by injecting checklists, reasoning trees, critique loops, and stepwise logic. Delegate sub-reasoning without losing coherence.
GitHub
ai-strategic-fluency
Use AI to reshape strategic decisions, not just execution. Identify where AI creates competitive advantage, shifts constraints, and enables new business models.
GitHub
ai-cognitive-readiness
Develop pre-fluency cognitive habits: recognize when not to use AI, separate thinking from generation, resist automation bias and output authority.
GitHub
critical-reviewer
Critical code review methodology. Use when reviewing code, PRs, or changes to enforce rigorous review standards.
GitHub
python-standards
Python 3.12+ coding standards and conventions (source of truth). Use when working on Python projects, implementing features, or reviewing code for standards compliance.
GitHub
python-developer
Expert Python development guidance for this codebase. Use when writing Python code, implementing features, or following project coding standards and patterns.
GitHub
python-reviewer
Python code review specialist. Use when reviewing Python code, checking for bugs, security issues, or ensuring code quality standards.
GitHub
acli-jira
Atlassian CLI (acli) for Jira operations. Use when creating tickets, searching issues, updating status, or managing Jira work items from the command line.
GitHub
bmad-parallel
Auto-detect and parallelize BMAD story tasks
GitHub
parallel-executor
Automatically detect and execute parallel development tasks
GitHub
spec-parallel
Auto-detect and parallelize Spec Kit tasks
GitHub
athena-pr-reviewer
PROACTIVELY USED when reviewing a PR, branch, or Jira story. Handles code review against requirements and provides actionable feedback.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.