DavidCho1999/archaiflow-skills / bundles/construction-admin/skills/bid-review
bid-review
VerifiedThis skill should be used during the bid phase when the user shares contractor bids, sub-bids, or proposal packages and wants them reviewed for completeness, scope alignment, qualifications, exclusions, alternates, and contract terms before owner award. Trigger on 'review these bids', 'bid review', 'check this proposal', 'compare bids', 'are these bids complete', 'bid leveling', 'bid analysis', 'qualifications and exclusions', or pasted bid content with award-decision intent. Generates a structured bid-review markdown in `docs/bids/` and appends to the project bid index.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.1 KB |
| assets/bid-review-template.md | markdown | 7.6 KB |
| references/bid_axes.md | markdown | 9.7 KB |
| references/bid_benchmarks.md | markdown | 7.0 KB |
| scripts/append_to_index.py | script | 1.7 KB |
| scripts/init_bids_workspace.py | script | 771 B |
references/bid_benchmarks.md
View on GitHub# Bid Benchmarks — Pointer Reference (NA)
This file does **not** contain $/sf or unit-price numbers. Concrete numbers age fast (RSMeans publishes quarterly; ENR CCI moves monthly; regional firms publish annually) and reciting them from memory is how silent errors enter a bid review. Instead, this file points to the publishers you should pull current values from, and gives a worked-example *format* for laying out a benchmark row inside a review.
If you find yourself about to write "$130 per CY for rock excavation" with no citation: stop, open RSMeans (or the regional firm's published market report), and quote the value with the source + edition.
---
## Where to pull current numbers (2026)
### $/sf turnkey construction cost benchmarks
- **RSMeans** — *Square Foot Costs with RSMeans Data*, current edition. Granular by building type, location-factored to MSA / 3-digit ZIP. The default for project sizing on private work.
- **Gordian** (RSMeans publisher) — quarterly update bulletins; CCI escalation series.
- **GSA P-100** — *Facilities Standards for the Public Buildings Service*, current edition. Federal courthouse / federal office benchmarks; useful even on non-federal civic work as a reference point.
- **AIA Compensation & Benchmarking Surveys** — fee benchmarks, not construction cost, but useful when the bid review is paired with fee-spread analysis.
### Cost escalation indices (apply to historical benchmarks)
- **ENR Construction Cost Index (CCI)** and **Building Cost Index (BCI)** — monthly. Use to escalate a published benchmark from its publication date to the bid date.
- **Bureau of Labor Statistics PPI** — *Inputs to Construction Industries* series. More volatile than ENR but closer to actual material movement.
- **Turner Building Cost Index** — quarterly; major-market focus.
- **Mortenson Cost Index** — quarterly market reports for Minneapolis, Phoenix, Denver, Chicago, Milwaukee, Seattle.
### Regional / market-specific benchmark publishers
- **Mortenson** — quarterly *Construction Cost Insights*.
- **Turner Construction** — quarterly *Building Cost Index* commentary.
- **Skanska** — annual / semi-annual *Market Insight* reports by US region.
- **Cumming Group** — quarterly *Market Cost Reports* (national + city detail).
- **Rider Levett Bucknall (RLB)** — quarterly *North America Report* with city-by-city construction cost movement.
- **NYC SCA** — published K-12 benchmarks for NYC public schools.
- **CA OPSC / DSA** — published benchmarks for CA K-12 / community college; also DSA-approval cost premium tracking.
- **GSA** — federal building benchmarks.
- **USACE** — civil works unit-cost guidance (PCC, MCACES).
### Public bid-tab data (real awards, not benchmarks)
- **State / agency bid-tab archives** — many state DOTs (Caltrans, NYSDOT, FDOT, TxDOT) publish full bid tabs. Excellent unit-price reality check for civil / earthwork / paving.
- **NYC SCA bid history** — public school awards.
- **CA HCAI** — hospital / clinical project costs (filed under OSHPD legacy tracking).
---
## Sections you would populate locally (with sourced values)
When a project actually needs a benchmark sheet, create one inside the project's review folder (`docs/bids/<slug>-benchmarks.md`) and populate the sections below from the publishers above. **Do not populate them in this file.** Leaving this file source-only protects against stale values being treated as authoritative.
- Construction $/sf benchmarks — by typology and region
- Earthwork $/CY benchmarks — by site condition (open / constrained / urban)
- Concrete & rebar — placed CY, lb-installed
- Structural steel — adjustment $/lb erected, fireproofing $/sf surface
- Envelope — storefront, curtain wall, brick, IMP, roofing
- MEP — $/gsf served by trade (HVAC, plumbing, fire, electrical, low-voltage)
- GC overhead and profit % — typical ranges by project size and delivery method
- Long-lead at-risk premium % — by item (switchgear, AHU, custom curtain wall, elevators)
- Bonding cost — % of contract value, by surety market
---
## Worked-example row format
When recording a benchmark row inside a project's local benchmark sheet, use this format. Each row is a published value, never a recalled value.
```
| Item | Range / value | Unit | Source | Edition / date | Region | Notes |
|---|---|---|---|---|---|---|
| Rock excavation, open access | <published low>-<published high> | $/CY | RSMeans Heavy Construction Cost Data | 2026 Q1 | RCI <factor> for <MSA> | Excludes blasting; add for confined |
| Curtain wall, mid-spec unitized | <published low>-<published high> | $/sf | Cumming Group Market Cost Report | 2026 Q1 | Northeast | Custom adders separate |
| Class A office mid-rise turnkey | <published low>-<published high> | $/gsf | RSMeans Square Foot Costs | 2026 Q1 | RCI 122 (NYC) | Excludes land, soft costs, FF&E |
```
Required columns:
1. **Item** — what is being measured.
2. **Range / value** — the published number(s). Always a range when the source publishes a range; never a single point if the source did not.
3. **Unit** — explicit ($/CY, $/sf, $/lb, $/gsf, %, etc.).
4. **Source** — the publisher and product name.
5. **Edition / date** — quarter and year, or specific publication date.
6. **Region** — RCI factor + MSA, or named region from the publisher.
7. **Notes** — exclusions, conditions, escalation applied.
---
## How to apply (when local benchmarks have been populated)
When a bidder's unit price is **outside** the published range:
- **Above the published range**: contractor is loading the unit price as overrun-recovery or hedging unknown scope. Typical responses: negotiate down to the range, accept with a written cap, or require a basis-of-quote.
- **Below the published range**: contractor is wagering on no-overrun or has misread scope. Typical response: clarify scope before award; require basis-of-quote.
- **Within range**: typical; no flag unless other axes raise concern.
When the leveled bid is **outside** the typology $/sf range:
- 10-20% above: scope creep, region premium, or alternates carried in. Investigate.
- More than 20% above: scope misalignment or speculative pricing. Re-bid or re-scope.
- 10-20% below: hungry-for-backlog or aggressive bid. Verify qualifications, bonding, and SOV front-loading.
- More than 20% below: high abandonment or claims-recovery risk. Treat as non-responsive in spirit pending clarification.
These thresholds are conventions; the publisher's commentary on a given quarter often changes them (e.g., during 2021-2022 supply-shock periods, "above range" was nearly universal and the threshold widened).
---
## Why this file does not list values
Concrete benchmark values from recall are how the well-tracker incident happened (`MEMORY/feedback_standards_verification.md`, 2026-05-09). Every recalled scorecard concept was wrong. The same failure mode applies here: $/sf and $/CY values vary by quarter, by RCI, by site condition, and a single hallucinated point in a bid-review memo gets weaponized in a negotiation. Source it or omit it.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |