AI 原生开放教材

外观

Claude Code Ultimate Guide工程手册·英文原文 ↗原件 ↓仓库 ↗

Watch List ​

Resources monitored but not yet integrated into the guide. Event-driven re-evaluation (not time-based).

Lifecycle ​

New resource → /eval-resource
  Score >= 3 but not ready → Active Watch
  Score < 3               → Dropped (or not listed)

Trigger reached → re-evaluation → Integrate (Graduated) / Drop (Dropped)

Active Watch ​

ResourceTypeAddedWhy WatchingRe-eval Trigger
save-webpage-to-obsidianSkill2026-02-25Skill Claude Code qui archive des articles web dans un vault Obsidian (dual extraction: Chrome MCP + WebFetch). Pattern dual-strategy intéressant mais config hardcodée, sécurité non adressée, pas de métriques adoption. Score 2/5.>200 stars GitHub
fp.devTool2026-02-22Agent-native issue tracking pour Claude Code. Un vrai différentiateur (issues .md git-committables) mais adoption insuffisante, Apple Silicon only, redondant avec Tasks API. Score 2/5.GitHub stars visibles + release cadence + write-up praticien en prod
ICMMCP2026-02-12Pre-v1 (1 star, now 508 as of 2026-07-28, 11 commits)First release + >20 stars
System PromptsTool2026-01-26Redundant with official sources. Re-evaluated 2026-02-13 (Opus 4.6 update): still 2/5.Anthropic confirms CLI prompts not published
o16g: Outcome EngineeringManifesto2026-02-13Emerging framework by Cory Ondrejka (CTO Onebrief, co-creator Second Life, ex-VP Google/Meta). 16 principles for shifting from "code writing" to "outcome engineering". Honeycomb endorsement. No Claude Code-specific content yet. Memetic potential (naming follows i18n/k8s pattern).Term adopted in >3 independent AI engineering resources OR author publishes tool-specific implementation
FabroTool2026-03-17Graph-based workflow orchestrator for AI coding agents (Rust binary, zero deps, MIT). DOT graph pipelines + multi-model routing (CSS stylesheets) + Git checkpointing per stage (unique, no equivalent found) + Daytona cloud sandboxes. Direct Claude Code integration via curl | claude. Score 3/5. Eval: 079>200 GitHub stars OR practitioner write-up from production use
Rippletide CodeTool2026-03-17Hook-native runtime rule enforcement for Claude Code. Builds a Context Graph outside LLM context window, uses PreToolUse hooks to block violations pre-execution. Addresses CLAUDE.md degradation at scale (40+ rules) and compaction-driven rule loss. Free beta (npx rippletide-code, no signup). Distinct from eval 072 (MCP/SaaS). Score 3/5. Eval: 081Public GitHub repo >100 stars OR independent practitioner write-up from production

| stacklit-cli | Tool | 2026-06-10 | Go reimplementation of the documented stacklit concept (glincker/stacklit). Claims ~250 tokens codebase context, auto-configures Claude Code/Cursor/Aider. Same concept, different runtime (no npm/Node). Score 2/5. Eval: liza-mas-token-saving-cli-tools.md | >50 GitHub stars AND practitioner write-up from production use | | Switch | Tool | 2026-08-27 | Matrix-based bus connecting heterogeneous agents (Claude Code, Codex, OpenCode) and humans in the same room, relayed into Slack/Teams/Discord/Telegram/Mattermost with owner-inheritance authz. Fills a real category gap (no comparable multi-platform bridge exists elsewhere in the guide) but pre-1.0 (0.21.0), 252 stars/6 weeks, bus factor close to 1 (80%), no independent production adopter found. Score 3/5. Eval: switch-agent-human-chat-bridge.md | Tagged 1.0.0 release, OR independently documented production deployment (not SandboxAQ/Flint AI), OR a second comparable chat-bridge tool appears (enabling a comparison table) |

Graduated ​

Resources that moved from watch to integrated in the guide.

ResourceGraduatedEvaluation

Dropped ​

Resources removed from watch after re-evaluation.

ResourceDroppedReason