Menu
Capture sanitized decisions and lessons into the local Obsidian vault.
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.
Basé sur la classification professionnelle SOC
| name | obsidian-capture |
| description | Capture sanitized decisions and lessons into the local Obsidian vault. |
Use this skill to save durable knowledge to MiVault without putting vault data in the repo. Capture decisions, bug causes, fixes, reusable commands, and project lessons after the work is verified.
Classify before writing. GREEN can go to global notes. YELLOW belongs to the project section. RED is never saved. RED includes secrets, keys, credentials, private customer data, raw sensitive logs, wallet material, and anything the user marks sensitive.
Find the Ralph repo at RALPH_CODEX_REPO or the current checkout root. Initialize the vault with scripts/vault/vault-init.py when needed. Save notes through scripts/vault/vault-save.py with --classification GREEN or --classification YELLOW.
Use templates from templates/vault for concepts, decisions, sessions, handoffs, autoresearch results, and specs. vault-init.py copies those templates into the vault _templates folder.
Report the saved note path. Include classification, source detail, and validation evidence. If content is RED, state that capture was skipped.
Improve, audit, simplify, rewrite, or migrate prompts, tool descriptions, agent instructions, and prompt stacks for GPT-5.6 Sol or the GPT-5.6 family. Use for outcome-first prompt design, autonomy boundaries, tool routing, PTC, grounding, verbosity, reasoning effort, and prompt evals.
Apply a deep, design-minded engineering workflow for complex work that needs careful planning, iteration, and simplification.
Use when preparing or running a Claude CLI agentic engineering review through claude -p for repository audits, architecture analysis, system design, security review, large refactors, specs, RFCs, or evidence-grounded long-form engineering analysis.
Use when preparing or running a ZCode GLM-5.2 agentic builder workflow through zcode --prompt for fast implementation, iterative code generation, focused fixes, and validation on an existing repository.
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.
Review and adjudicate Bugbot, Cursor, Seer, and similar automated PR feedback with local evidence before accepting, fixing, or dismissing findings.