forge

Dispatch the Capability Forge to detect workforce gaps, scout for existing implementations, or author new skills/MCPs/plugins. Use this skill when the user asks "what capability are we missing", "build a skill for X", "check MCP Registry for Y", "what skills should we add", "extend the workforce", or when a retrospective mentions a recurring capability gap.

Aller à l'installation

Dépôt: TheAdaply/re-forge
Dernière activité de la source: 13 avril 2026 à 15:04
Langue détectée de SKILL.md: anglais
Étoiles: 0
Forks: 0

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.

npx skills add https://github.com/TheAdaply/re-forge --skill forge

La commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.

Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

SKILL.md

Instructions source · Aperçu en lecture seule

Retour à la recherche Retour à l’installation

causal-inference

Correlation-to-causation discipline for any "does X cause Y", "what is the effect of X", or "should we do X" question. Use when a decision rests on a causal claim drawn from observational data, an A/B test, an event study, or a regression with controls — before reporting any effect as causal. Enforces draw-the-DAG-first, identification-before-estimation, the design hierarchy (RCT > natural experiment > diff-in-diff > IV > controls), A/B-test pitfalls, and unmeasured-confounder sensitivity analysis.

2026-06-11

nnsight

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

2026-06-11

spec-driven

Use this skill for long-horizon agentic coding where a feature spans many turns and the agent drifts: it freezes a re-readable contract before code. Writes EARS-style requirements -> design -> task breakdown -> verification evidence, one feature directory per feature, with status gates and grep-able traceability IDs. Triggers on 'spec this out', 'write a spec', 'spec-driven', 'requirements then design', or planning a multi-session build.

2026-06-04

Tout voir dans ce dépôt

name	forge
description	Dispatch the Capability Forge to detect workforce gaps, scout for existing implementations, or author new skills/MCPs/plugins. Use this skill when the user asks "what capability are we missing", "build a skill for X", "check MCP Registry for Y", "what skills should we add", "extend the workforce", or when a retrospective mentions a recurring capability gap.

Capability Forge dispatch

You are invoking the Capability Forge (forge-lead, H1 architecture).

What to do

Read ~/.claude/agent-memory/forge-lead/MEMORY.md — authored skills catalog + process lessons.
Read ~/.claude/agents/forge-lead.md — adopt this as your behavioral contract.
If the user specifies a gap, skip to step 5. Otherwise:
Run /forge:gap — inventory the workforce and detect gaps. Read the gap skill at ~/.claude/forge/skills/gap/SKILL.md and execute its method.
Run /forge:scout — query MCP Registry + anthropics/skills + marketplaces for existing implementations. Read ~/.claude/forge/skills/scout/SKILL.md.
Decision: INSTALL existing / ADOPT existing / AUTHOR new / DEFER to research.
If AUTHOR: run /forge:draft → /forge:test → /forge:promote pipeline.
If DEFER: write research-request drop-file and stop.

Hard rules

Never author what already exists — check registry + marketplaces first
Never promote without passing /forge:test (≥3 eval cases, ≥0.8 pass rate)
Every authored skill gets an ACE-style MEMORY.md bullet with helpful/harmful counters
Research-request handoff is user-mediated (no automated polling)

forge

Informations de source

Options d'installation

Vérifiez les fichiers source

Plus depuis ce dépôt

Plus depuis ce dépôt

Capability Forge dispatch

What to do

Hard rules

Capability Forge dispatch

What to do

Hard rules