Skills IA Données et IA

gh-workflow

kaihendry

How to fetch logs from Github's CI/CD with the gh cli

external-write

juljus

Write files outside workspace sandbox (e.g., ~/.claude/skills). Use when creating/editing personal agent skills or other files that must exist outside the current workspace.

debugging

juljus

Systematic debugging approach emphasizing temporal awareness, narrow scope, and appropriate investigation strategies. Use when investigating bugs, analyzing failures, or troubleshooting issues.

dev-workflow

juljus

Development workflow emphasizing test-first development, task classification, and appropriate tracking. Use when starting implementation, planning changes, or structuring development work.

agent-communication

juljus

Principles for writing token-efficient, action-oriented instructions to agents. Use when creating agent prompts, rules, documentation, or improving agent communication.

git-commit

juljus

Git commit guidelines with conventional format, safety checks, and granular strategy. Use when making commits, staging changes, or writing commit messages.

skill-authoring

juljus

Guide for creating effective agent skills. Use when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or tool integration...

django-package

siavashoutadi

Guide for adding support for new django packages to djdevx

research-plan-implement

seekayel

A structured workflow for AI-assisted development using research, planning, and systematic implementation phases. Users refer to this skill as RPI, rpi or Research Plan Implement.

scl-syntax

DeLuAle

SCL (Structured Control Language) syntax assistance for Siemens TIA Portal V20+ PLC programming. Generates error-free SCL code using native functions from a 222-function database. Bilingual support (Italian/Eng...

scl-reference

DeLuAle

Riferimento per funzioni di sistema SCL (TIA Portal V20+) con sintassi e anti-pattern. Usa quando devi generare o revisionare codice SCL per S7-1200/S7-1500, scegliere funzioni native o chiarire la sintassi di...

writing-interviewer

KarthikRaju391

Interviews users to clarify their thinking instead of writing for them. Use when asked to help with writing, content ideas, exploring topics, or reviewing drafts. Reads existing notes to identify themes, asks p...

skill-name

karimzg

release

CodeVachon

Create a new release version. Use when asked to create a release, prepare a release, bump version, or update the changelog.

osctrl-desktop-automation

01000001-01001110

Use when automating desktop interactions via OSCTRL CLI - mouse, keyboard, screen capture, window management. ALWAYS get context before mouse operations.

skillcreator-codex

therealityreport

Codex-native skill creator. Self-contained 4-phase methodology for creating production-ready Claude Code skills. Adapted from SkillCreator v3.2 for Codex agents with embedded methodology and simulated synthesis...

qa-acceptance

therealityreport

Evaluate pipeline runs against ACCEPTANCE_MATRIX.md. Use after feature releases to verify acceptance criteria.

vision-analytics

therealityreport

Advanced visibility analysis using head pose, face mesh, and temporal patterns. Use for face-visible vs body-only breakdowns.

embedding-engine

therealityreport

Embedding backends (InsightFace/PyTorch+ONNXRuntime vs TensorRT). Use when optimizing embedding throughput or debugging drift/fallbacks.

skillcreator

therealityreport

Ultimate meta-skill for creating production-ready Claude Code skills. Uses deep iterative analysis with 11 thinking models, regression questioning until exhausted, evolution and timelessness as core lens, and m...

face-alignment

therealityreport

Face alignment, landmark extraction, and quality gating. Use when debugging alignment issues, reviewing rejected faces, or tuning quality thresholds.

body-tracking

therealityreport

Person detection, tracking, and Re-ID. Use when faces aren't visible but cast should still be tracked, or when debugging face-body association.

pipeline-insights

therealityreport

AI-powered pipeline diagnostics. Explains why faces weren't detected, tracked, embedded, or clustered using OpenAI GPT-4o analysis. Use when debugging pipeline issues, reviewing unclustered tracks, or understan...

unit-test-generator

cha9ro

Generate and improve unit tests using the Assured LLMSE approach from Meta's TestGen-LLM. Use this skill when users request help with writing unit tests, improving test coverage, adding test cases to existing t...