assemble
無料Dev-Critic loop: implement, review, fix — repeat until clean
日本語の概要は準備中です。原文の説明を表示しています。
Triage the content corpus against the latest GSC snapshot and produce a prioritized refresh report. Read-only: reports, never edits.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Read-only analytical skill. Joins GSC traffic data with the content collection and produces a prioritized triage report. Spec: specs/content-curator/spec.md.
dev or assess.--page /patterns/typed-handoffs.Check snapshot freshness. Run ls -lt data/gsc/*.jsonl | head -1. If the latest snapshot date is older than 14 days (STALE_SNAPSHOT_DAYS in tools/curator/rubric.ts), warn the user and offer to run with --live. Do not block — stale-but-present is still useful.
Run the triage.
pnpm curatorpnpm curator -- --page <path>pnpm curator -- --live (re-runs pnpm gsc:snapshot first)Surface the report. The runner writes reports/curator/YYYY-MM-DD.md. Read it back, summarize the Top 10 in one paragraph plus per-bucket counts, and link to the file. Highlight any "insufficient data" notice or staleness warning.
Hand off, don't fix. For each Top 5 item, name the appropriate next skill:
assess, then dev for the title/meta rewriteassess for a depth-and-structure plan, then devdev to update examplesgeo-audittools/curator/rubric.ts. Do not quote magic numbers from memory — read the file if asked.reports/curator/*.md is gitignored. They are GSC-derived (they quote query strings) and regenerable from the snapshot + rubric. Retros run against locally-retained snapshots. See ADR 0002.$ARGUMENTS
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Dev-Critic loop: implement, review, fix — repeat until clean
日本語の概要は準備中です。原文の説明を表示しています。
Assess source material against the ASDLC Knowledge Base and produce an evidence-calibrated Content Review Report.
日本語の概要は準備中です。原文の説明を表示しています。
Perform an adversarial review of the current uncommitted changeset, validating it against project contracts and architectural intent.
日本語の概要は準備中です。原文の説明を表示しています。
Implement features, fix bugs, and keep the codebase healthy and maintainable. Works from a defined PBI, issue, or task description.
日本語の概要は準備中です。原文の説明を表示しています。
GEO+SEO audit of asdlc.io — analyzes the codebase for Generative Engine Optimization across AI citability, technical infrastructure, content quality, schema markup, and knowledge base discoverability. Produces a composite GEO Score (0-100) with prioritized action plan.
日本語の概要は準備中です。原文の説明を表示しています。
Produce written specs and atomic PBIs that an implementation agent can execute independently. Authors specs and Linear issues.
日本語の概要は準備中です。原文の説明を表示しています。