Help us improve
Share bugs, ideas, or general feedback.
From crucible
List past Crucible reviews stored in .review/reports/ and optionally show the full markdown of one. Use to see how the project's review verdicts have evolved over time.
npx claudepluginhub hazarsozer/crucible-cc --plugin crucibleHow this skill is triggered — by the user, by Claude, or both
Slash command
/crucible:historyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
List past Crucible reviews and offer to show one in full. Reviews are stored at `.review/reports/<review_id>.md` in the project root.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Compacts the current conversation into a handoff document for another agent to continue the work, with suggested skills and redacted sensitive info.
Share bugs, ideas, or general feedback.
List past Crucible reviews and offer to show one in full. Reviews are stored at .review/reports/<review_id>.md in the project root.
List reports. Find every file under .review/reports/ matching the pattern *.md. If none exist, print:
No past reviews found. Run /crucible to create one.
and exit.
Parse metadata from each report. For each file, extract:
review_id — from the filename (strip .md).final_score — from the line beginning with **Score:** (or fall back to Score: if formatting differs).final_verdict — from the line beginning with **Verdict:**.scope_description — from the H1 line # Crucible Review — <description>.completed_at — from the metadata line _Review ID: ... · Generated: <timestamp>_.If parsing fails on any field, fall back to ? for that field.
Sort reports newest-first by completed_at if available, else by filename (which encodes the timestamp prefix).
Print a table. Use fixed-width columns. Truncate long descriptions to 40 chars with ….
# Review ID Score Verdict Scope
─────────────────────────────────────────────────────────────────────────────────
1 2026-05-10-1430-auth-refactor 7.1 conditional_approval auth module rewrite
2 2026-05-09-1620-api-rewrite 8.4 approved /api/v2 endpoints
...
Prompt for selection.
Show full report for which # (or `n` to exit)?
n, no, exit, quit, or empty, exit silently.Not a valid selection. and exit.For partial reports. Files matching *-PARTIAL.md (incomplete runs) appear in the listing with a ⚠️ prefix in the Verdict column to make it clear they don't represent a complete pipeline run.
.review/ directory. Treat as no past reviews.? placeholders. Don't crash.... and <N> older reviews. Browse .review/reports/ directly to see all.This skill is read-only. It does not modify any files, does not invoke any subagents, and does not consume model budget. It's purely a navigator over the user's review history.