a5942f1c53
Integration of "How to write a good spec for AI agents" by Addy Osmani: Evaluation (docs/resource-evaluations/addy-osmani-good-spec.md): - Score: 4/5 (High Value - Integrate within 1 week) - Fills gaps: modular design, operational boundaries, command specs - Fact-checked: credentials verified via Perplexity, all claims sourced - Challenge phase: technical-writer agent corrected initial 3/5 → 4/5 Spec-First Workflow Updates (guide/workflows/spec-first.md): - NEW: "Modular Spec Design" section (~50 lines, line 322) Pattern: Split large specs into focused files (CLAUDE-[domain].md) - NEW: "Operational Boundaries" section (~60 lines, line 372) Three-tier system: Always/Ask First/Never → maps to Claude Code modes - NEW: "Command Spec Template" section (~40 lines, line 432) Executable command specs with expected outputs & error handling - NEW: "Anti-Pattern: Monolithic CLAUDE.md" section (~30 lines, line 472) Explains cognitive load problem (>200 lines = context pollution) Reference Index (machine-readable/reference.yaml): - 8 new entries: spec_first_workflow → spec_osmani_score - Links to new spec-first.md sections with line numbers - Source attribution: https://addyosmani.com/blog/good-spec/ Public Facing (README.md): - Incremented resource evaluations count: 35 → 36 File growth: spec-first.md 327 → 507 lines (+180) Source: Addy Osmani (former Chrome team, 14y), published Jan 13, 2026 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| 015-everything-claude-code-github-repo.md | ||
| 016-gang-rui-tasks-api-limitations.md | ||
| 017-pat-cullen-final-review.md | ||
| 023-community-discussions-report-jan2026.md | ||
| 024-addy-osmani-80-percent-problem.md | ||
| 025-vercel-agents-md-vs-skills-eval.md | ||
| 026-contribution-metrics-blog.md | ||
| 2026-01-27-claude-code-hidden-feature-social-post.md | ||
| addy-osmani-good-spec.md | ||
| agentskills-io-specification.md | ||
| anaconda-croce-evaluation.md | ||
| anthropic-releases-jan16-23-2026.md | ||
| astgrep-flavien-metivier.md | ||
| boris-cowork-video-eval.md | ||
| clawdbot-twitter-analysis.md | ||
| dclaude-docker-wrapper.md | ||
| docker-sandboxes-isolation.md | ||
| eval-claude-code-releases-jan2026.md | ||
| gsd-evaluation.md | ||
| mcp-apps-announcement.md | ||
| melvyn-malherbe-async-hooks-linkedin.md | ||
| mikul-gohil-hooks-evaluation.md | ||
| nick-jensen-plugins.md | ||
| paddo-team-tips-eval.md | ||
| prompt-repetition-paper.md | ||
| README.md | ||
| remotion-claude-code-video.md | ||
| rtk-evaluation.md | ||
| se-cove-plugin.md | ||
| self-improve-skill.md | ||
| skill-doctor-github-action.md | ||
| steinberger-inference-speed.md | ||
| system-prompts-official-vs-community.md | ||
| uml-oop-diagrams.md | ||
| vibe-coding-rusitschka.md | ||
| wooldridge-productivity-stack.md | ||
| worktrunk-evaluation.md | ||
Resource Evaluations
Ce dossier contient les évaluations de ressources externes (articles, vidéos, discussions) pour déterminer leur pertinence pour le Claude Code Ultimate Guide.
Méthodologie
Chaque ressource est évaluée selon un système de scoring standardisé et challengée par un agent technique pour garantir l'objectivité.
Grille de score (sur 5)
| Score | Signification | Action |
|---|---|---|
| 5 | Critical - Breakthrough, must integrate immediately | Intégrer sous 24h |
| 4 | High Value - New capability or major improvement | Intégrer sous 1 semaine |
| 3 | Moderate - Useful addition but not urgent | Intégrer si temps disponible |
| 2 | Marginal - Secondary info or niche use case | Ne pas intégrer (ou mention minimale) |
| 1 | Low - Redundant, incorrect, or off-topic | Rejeter |
Process
- Analyse initiale: Extraction des faits, vérification des sources
- Scoring: Attribution d'un score avec justification
- Challenge: Agent technical-writer remet en question le score
- Décision finale: Intégration ou rejet avec traçabilité
Nomenclature des fichiers
Format: [topic-slug].md (date supprimée pour stabilité des liens)
Exemple: remotion-claude-code-video.md
Working Documents
Les documents de travail bruts (prompts Perplexity, audits clients) restent dans claudedocs/resource-evaluations/ (gitignored).
Index des Évaluations
| Ressource | Score Initial | Score Final | Décision | Fichier |
|---|---|---|---|---|
| Anthropic Releases (Jan 16-23, 2026) | - | - | ✅ Suivi régulier | anthropic-releases-jan16-23-2026.md |
| AST-grep (Flavien Métivier) | 3/5 | 4/5 | ✅ Intégrer workflow | astgrep-flavien-metivier.md |
| MCP Apps (SEP-1865) | 3/5 | 4/5 | ✅ Intégré (architecture + guide) | mcp-apps-announcement.md |
| Boris Cherny (Cowork Video) | 4/5 | 4/5 | ✅ Intégré (mental models) | boris-cowork-video-eval.md |
| Clawdbot (Twitter Analysis) | 2/5 | 2/5 | ⚠️ Watch only | clawdbot-twitter-analysis.md |
| GSD (Getting Shit Done) | 4/5 | 4/5 | ✅ Intégré (workflow) | gsd-evaluation.md |
| Nick Jensen Plugins | 3/5 | 3/5 | ✅ Mention | nick-jensen-plugins.md |
| Prompt Repetition Paper | 3/5 | 4/5 | ✅ Intégrer best practices | prompt-repetition-paper.md |
| Remotion + Claude Code (Video Production) | 2/5 | 3/5 | ✅ Mention minimale | remotion-claude-code-video.md |
| SE-Cove Plugin | 2/5 | 2/5 | ⚠️ Watch only | se-cove-plugin.md |
| Self-Improve Skill | 3/5 | 3/5 | ✅ Template ajouté | self-improve-skill.md |
| Steinberger (Inference Speed) | 3/5 | 3/5 | ✅ Intégré (minimal) | steinberger-inference-speed.md |
| UML & OOP Diagrams | 3/5 | 3/5 | ✅ Mention | uml-oop-diagrams.md |
| Vibe Coding Level 2 (Rusitschka) | 4/5 | 4/5 | ✅ Intégré (workflows) | vibe-coding-rusitschka.md |
| Peter Wooldridge (Productivity Stack) | 2/5 | 3/5 | ✅ Practitioner Insights | wooldridge-productivity-stack.md |
| System Prompts (Official vs Community) | 4/5 | 2/5 | ⚠️ Watch only (official sources exist) | system-prompts-official-vs-community.md |
| Worktrunk | 4/5 | 4/5 | ✅ Intégré (workflow) | worktrunk-evaluation.md |
| Pat Cullen (Multi-Agent PR Review) | 5/5 | 5/5 | ✅ Intégré (review-pr, code-reviewer, guide) | 017-pat-cullen-final-review.md |
| Docker Sandboxes (Isolation Landscape) | 4/5 | 4/5 | ✅ Intégré (guide + notice) | docker-sandboxes-isolation.md |
| dclaude (Dockerized Claude Code) | 2/5 | 2/5 | ⚠️ Footnote (sandbox-isolation.md) | dclaude-docker-wrapper.md |
| 10 Tips from Inside the Claude Code Team (paddo.dev) | 4/5 | 4/5 | ✅ Intégré (4 sections) | paddo-team-tips-eval.md |
Dernier update: 2026-02-01 (20 évaluations)