원클릭으로
capture
Capture a content-worthy moment — writes structured record to content/captures/
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Capture a content-worthy moment — writes structured record to content/captures/
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Scan all ecosystem repos for convention deviations. Reports findings; does not fix anything. Use proactively after cross-repo changes.
Validates pipeline parquet outputs for schema compliance, null rates, row count baselines, and freshness. Use after pipeline runs or when triage shows data quality concerns. Fast and read-only (uses haiku).
Run tests across all ecosystem repos and report pass/fail summary. Use when the user wants to verify the ecosystem is healthy or after cross-repo changes.
Runs the krff-shell ETL pipeline with pre/post validation. Use when data needs refreshing, after dependency updates, or when triage shows stale parquets. Reads CLAUDE.md before running.
Research across sibling repos to gather context for cross-project tasks. Use when working in one repo and needing to understand how another repo works, what it exports, or how data flows between them.
Show all open work (board + backlog) with dependency-aware execution order
| name | capture |
| description | Capture a content-worthy moment — writes structured record to content/captures/ |
| user-invocable | true |
| disable-model-invocation | false |
| allowed-tools | Read, Write, Glob, Grep |
Capture a content-worthy technical moment as a structured record. The argument $ARGUMENTS is the title (e.g., /capture DART crDecsn.json endpoint discovery).
Parse the title. If $ARGUMENTS is provided, use it as the capture title. If empty, ask what to capture.
Generate filename. Create a slug from the title:
content/captures/YYYY-MM-DD-{slug}.md (use today's date)Check for duplicates. Glob content/captures/*{slug-keywords}* to avoid creating near-duplicate captures. If a similar capture exists, ask whether to update it or create a new one.
Gather context. Review the current conversation for:
Classify the type:
case-study: A problem was investigated and resolved with a clear arcexplainer: A complex topic was broken down and understoodinsight: A non-obvious discovery or pattern was identifiedwar-story: A debugging or investigation sequence with twistsWrite the capture file with this structure:
---
title: "{title}"
date: YYYY-MM-DD
status: raw
type: {case-study | explainer | insight | war-story}
repos: [repos involved]
tags: [relevant tags]
---
## What happened
{1-3 paragraph summary of the event}
## Why it matters
{Why an external audience would care — what's generalizable}
## Technical detail
{Error messages, metrics, API responses, code paths — the raw evidence}
## Narrative arc
- Setup: {what we were trying to do}
- Conflict: {what went wrong or was surprising}
- Resolution: {how we solved it}
- Lesson: {the takeaway}
Append to ideas.md. Add a one-line cross-reference entry to content/ideas.md:
- {title} (captured: YYYY-MM-DD → captures/{filename})
Report. Show the filename and a 2-line summary of what was captured.
drafts/