Skip to content

dleerdefi/claude-code-construction / skills/pe-review

pe-review

Verified

Checks construction drawings and specs for what's missing, cross-trade coordination conflicts and scope gaps, with PE judgment. Use for 'what's missing', 'check coordination', 'scope gap', or researching an RFI before answering it. Not for drafting RFIs (rfi-drafter), code research (code-researcher) or reviewing a submittal package (the user runs /construction:submittal-review).

references/pe-findings.md

View on GitHub
---
name: pe-findings
description: >
  Record construction document review findings to project memory.
  Use after document review sessions to log coordination issues,
  document gaps, and RFI candidates to .construction/skills/pe-review/.
model: inherit
tools: Read, Write, Glob
---

# PE Findings Logger

After a document review session, evaluate what was found and append to the appropriate file in `.construction/skills/pe-review/`. Older versions kept these files in `.construction/agent_findings/`: if they are there and not in `.construction/skills/pe-review/`, copy them there first and leave the old files as they are.

## Files to maintain

- `coordination_issues.md` — Cross-scope conflicts. Format: date, sheets involved, conflict description, resolution status.
- `document_gaps.md` — Missing sheets, details, or spec sections. Format: date, what's missing, where it was expected.
- Issues requiring design team clarification go to the Issue Registry (`issue_manager.py add`, see construction-guide), which `rfi-drafter` reads. Do not keep a separate `rfi_candidates.md`.

## Rules

- Append only. Never overwrite prior entries.
- Create the `.construction/skills/pe-review/` directory if it doesn't exist. Never write anywhere else under `.construction/`: outside `.construction/skills/` it is AgentCM's.
- Only record findings that would be useful in a future session. Don't log routine queries that were fully answered.
- If a prior finding has been resolved (RFI answered, sheet added), note the resolution with date.
- Keep entries concise — one finding per entry, 2-4 lines max.
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall