- Skills
- 90
- 仓库
- 1
- 职业覆盖
- 1
- 场景覆盖
- 3
- Stars
- ★ 8
Yan Bourquard-Ania 的 Skills 90
byan
BYAN local project skill. Use when working in the BYAN repo, invoking BYAN agents/workflows/commands, enforcing BYAN Strict Mode, or needing the portable BYAN filesystem map.
byan-yanstaller
Yanstaller - Multi-Platform BYAN Installer Agent Role: Installation Expert + Platform Detection Specialist + Zero-Config Automation. Invoke when user mentions : AUTO, DETECT, HELP, EXIT.
byan-tea-tea
tea agent
byan-suitability
Advisory model-suitability ledger — record adversarial verdicts, read learned ratings, human decides downgrades
byan-strict
Enforcement mode that prevents scope downgrade and forces the agent to self-verify its work against the originally locked request before delivering. Invoke when the user asks for a production deliverable, a complete app, a filled contract from a template, or uses any activation keyword (`prod`, `production`, `client`, `contrat`, `template officiel`, `livrable`, `deliverable`, `mise en production`, `release`). Enforces scope-lock, N>=3 self-verify passes, and a 95% confidence floor on hard claims.
byan-skeptic
Scientific Claim Challenger and Epistemic Guard
byan-rachid
NPM/NPX deployment specialist for BYAN installation Role: NPM/NPX Deployment Expert.
byan-project
Lister les projets BYAN via MCP et en choisir un a inspecter ou importer. Invoquer quand l'utilisateur dit "liste mes projets byan", "choisit un projet byan", "import projet byan", "/byan-project", "list byan projects", "pick byan project".
byan-patnote
Patnote - BYAN Update Manager & Conflict Resolution Specialist Role: Update Manager & Conflict Resolution Specialist.
byan-orchestrate
暂无简介
byan-native-dev-story
Orchestrating conductor for the native dev-story workflow. Runs the autonomous red-green-refactor engine (.claude/workflows/dev-story.js) via the Workflow tool, then presents its verdict at a human gate and records FD/strict state via MCP. This is the Hybrid pattern incarnate - gate OUTSIDE the script, engine INSIDE.
byan-merise-agile
暂无简介
byan-mantra-audit
Semantic embodiment audit of a BYAN persona against its applicable mantras. Out-of-band, LLM-judged, kept out of the commit gate.
byan-insight
Harvest the native Claude Code outcome trails (tool-log, strict-audit gaps, suitability ledger, ELO) into a GATED self-improvement digest for BYAN. Invoke when the user asks "what did this session teach BYAN", "insight digest", "self-improvement", "qu'est-ce que BYAN a appris", or wants to review recurring gaps / routing outcomes / tool health before deciding what to improve. Observe and propose; the human ratifies each change.
byan-hermes-dispatch
Autonomous BYAN dispatcher. Given a user task or a BYAN command result (like "execute FD on feature X"), this skill picks the right specialist agent from the BYAN roster, picks the right execution strategy and model via byan_dispatch (MCP), and spawns the work via the Agent tool without asking for confirmation. Invoke this whenever BYAN or the user describes work that needs to be delegated, or whenever the user says "@hermes <task>".
byan-forge
Forge a reusable persona for the BYAN project via a short structured interview (archetype, blockers, learning style). A persona is NOT an agent — it is a cognitive profile BYAN can embody to test pedagogy, validate an agent, or understand a different point of view. Invoke when user says "forge a persona", "cree une persona", "persona player", or asks for a persona to test an agent against.
byan-fact-check
Fact-check scientifique BYAN (Demonstrable, Quantifiable, Reproductible). Invoquer quand un claim technique est fait, quand l'utilisateur utilise des absolus (toujours/jamais/obviously/faster/better), quand on audite un document, ou pour evaluer une chaine de raisonnement. Applique les 4 types d'assertions (REASONING/HYPOTHESIS/CLAIM Ln/FACT) et 5 niveaux de preuve. Domaines stricts (security/performance/compliance) = LEVEL-2 minimum.
byan-elo-trust
Systeme ELO (0-1000) de confiance epistemique par domaine technique qui calibre l'intensite du challenge BYAN et la profondeur des reponses. Invoquer quand l'utilisateur fait un claim dans un domaine technique (security, javascript, performance, algorithms, etc.), quand il demande `[ELO]`, ou pour decider si BYAN doit expliquer/scaffold ou aller droit au but. Algorithme Glicko-2 simplifie.