Agent skill

Adu Corrections Complete

by mikeOnBreeze in mikeOnBreeze/cc-crossbeam

Generates the final response package for ADU permit corrections — the second half of the corrections pipeline.

MITAuto-check passed

Install Adu Corrections Complete

skills CLI
$ npx skills add mikeOnBreeze/cc-crossbeam --skill adu-corrections-complete -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mikeOnBreeze/cc-crossbeam adu-corrections-complete --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mikeOnBreeze/cc-crossbeam.git skills-src && mkdir -p .claude/skills && cp -r skills-src/server/skills/adu-corrections-complete .claude/skills/adu-corrections-complete && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
adu-corrections-complete
GitHub stars
293
Token cost
~2.6k tokens
SKILL.md length
983 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Generates the final response package for ADU permit corrections — the second half of the corrections pipeline.

  • Works in 4 steps: response_letter.md → professional_scope.md → corrections_report.md → …
  • A session directory contains corrections analysis files and a contractoranswers.json has been provided
  • SKILL.md covers Overview, Input: Session Directory, Output: Four Deliverables and Handling Missing Answers, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Adu Corrections Complete is an agent skill from mikeOnBreeze/cc-crossbeam. Generates the final response package for ADU permit corrections — the second half of the corrections pipeline. This skill should be used after adu-corrections-flow has produced its analysis files and the contractor has answered questions. It reads the research artifacts (categorized corrections, state law findings, city research, sheet observations) plus contractor answers, and produces four deliverables — a response letter to the building department, a professional scope of work, a corrections status report, and…

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: CrossBeam Permits — AI-assisted building-permit plan review for cities and builders. The licence is MIT.

When your agent uses it

  • A session directory contains corrections analysis files and a contractoranswers.json has been provided

Example prompts

  • “Use the adu-corrections-complete skill to generate the final response package for ADU permit corrections — the second half of the corrections pipeline”
  • “/adu-corrections-complete”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. response_letter.md
  2. professional_scope.md
  3. corrections_report.md
  4. sheet_annotations.json

What it can do on your machine

Read from SKILL.md and the folder at commit cc5591e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Adu Corrections Complete loads about 2.6k tokens when it runs. Until then it costs about 204 tokens; SKILL.md has 983 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~204
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mikeOnBreeze/cc-crossbeam at commit cc5591e, republished under its MIT licence (© mikeOnBreeze). 983 words, ~2,561 tokens.

Download SKILL.mdSave it as .claude/skills/adu-corrections-complete/SKILL.md (or your agent's skills folder).
name
adu-corrections-complete
description
Generates the final response package for ADU permit corrections — the second half of the corrections pipeline. This skill should be used after adu-corrections-flow has produced its analysis files and the contractor has answered questions. It reads the research artifacts (categorized corrections, state law findings, city research, sheet observations) plus contractor answers, and produces four deliverables — a response letter to the building department, a professional scope of work, a corrections status report, and per-sheet annotations. Triggers when a session directory contains corrections analysis files and a contractor_answers.json has been provided. This skill runs as a cold start — it has no conversation history from the analysis phase and relies entirely on the file artifacts.

ADU Corrections Complete

Overview

Generate the final response package for ADU permit corrections. This is the second skill in a two-skill pipeline:

  1. adu-corrections-flow (Phase 1) — reads the corrections letter, builds the sheet manifest, researches state and city codes, views plan sheets, categorizes corrections, generates contractor questions. Produces research artifacts in a session directory.
  2. adu-corrections-complete (this skill, Phase 2) — reads those research artifacts + contractor answers, generates all deliverables.

This skill runs as a cold start. It has no conversation history from Phase 1. Everything it needs is in the session directory files. The quality of its output depends entirely on the quality of those files — especially corrections_categorized.json, which contains the merged research findings.

Input: Session Directory

The session directory (e.g., correction-01/) must contain these files from Phase 1:

FileWhat It ContainsHow This Skill Uses It
corrections_parsed.jsonRaw correction items with original wordingOriginal wording preserved in response letter
sheet-manifest.jsonSheet ID ↔ page number mappingSheet references in all outputs
state_law_findings.jsonPer-code-section lookups (CRC, CBC, ASCE, etc.)Code citations in response letter
city_research_findings.jsonMunicipal code, standard details, IBsCity-specific references in outputs
sheet_observations.jsonWhat's currently on each plan sheetInforms what needs to change
corrections_categorized.jsonThe main input. Each item with category, research context, state findings, city findings, sheet observations, affected sheetsDrives all output generation
contractor_questions.jsonWhat questions were askedMaps answer keys to correction items
contractor_answers.jsonContractor's responsesThe new input that completes the picture
Reading Order

Read files in this order to build context efficiently:

  1. corrections_categorized.json — read first, it's the backbone. Each item has its category, research context, and cross-referenced findings already merged.
  2. contractor_answers.json — read second, map answers to items.
  3. sheet-manifest.json — read third, for accurate sheet references.
  4. corrections_parsed.json — read fourth, for original wording to preserve in the response letter.
  5. Other files only if corrections_categorized.json doesn't have enough detail on a specific item — it usually does.

Output: Four Deliverables

1. response_letter.md

Professional letter from the contractor to the building department, addressing every correction item.

Structure:

# Response to Plan Check Comments
## [Review Round] — [Address]
### [Permit Number] | [Project Type]

Date / To / From / Re header

---

### [Section from original letter]

**Item [#] — [Summary]**
[Response addressing the correction with specific references]

...

---

**Summary of Sheet Revisions:**
| Sheet | Changes |

Rules:

  • Address EVERY item — do not skip any, even procedural ones (Items 1, 2)
  • Preserve the original correction wording — quote it or reference it clearly
  • For items with contractor answers: incorporate the answer with code justification
    • Example: "Existing 4" ABS waste line serves 22 DFU. ADU adds 12 DFU. Combined 34 DFU is within the 216 DFU capacity of a 4" drain per CPC Table 702.1."
  • For items without answers (skipped): mark as [TODO: description of what's needed]
  • For auto-fixable items: state what was changed and on which sheet
  • For professional items: state the scope and who will do the work
  • Reference specific sheets from the manifest — never guess
  • End with a summary table of sheet revisions
  • Tone: professional, specific, respectful. This goes to a city plan checker.
2. professional_scope.md

Work breakdown grouped by professional, with enough detail that the designer/engineer can execute without re-reading the corrections letter.

Structure:

# Professional Scope of Work
## [Address] — [Permit Number]

---

## [Professional Name / Firm]
**Sheets:** [list]

### Required Actions
| Item | Sheet | Action | Contractor Input | Status |

### Key Specifications
[Detailed specs from contractor answers — dimensions, materials, elevations]

### Deliverables
- [ ] checklist items

---

## Per-Sheet Action Summary
| Sheet | Actions | Professional | Status |

Rules:

  • Group by professional (Designer, Structural Engineer, HERS Rater, etc.)
  • Extract professional names from the plan sheets if available (title block info in sheet observations)
  • Include a Key Specifications section with contractor-provided details formatted for the designer
    • DFU justification note ready to paste onto Sheet A1
    • Grade elevation table with drops from finished floor
    • Patio dimensions for the structural engineer
  • Mark status: READY (can proceed), PENDING (waiting on other items), FINAL STEP (stamps/signatures last)
  • The per-sheet action summary at the bottom is the quick-reference — one row per sheet showing all work
Show full SKILL.md (409 more words)Show less
3. corrections_report.md

Status dashboard with checklist — the project manager's view.

Structure:

# Corrections Report
## [Address] — [Permit Number]

### Summary
| Category | Count | Items |

### Item Status Table
| Item | Section | Category | Status | Notes |

### Key Findings from Contractor Answers
[Important conclusions — capacity is fine, drainage works, etc.]

### Action Items Checklist
#### [Role]
- [ ] / [x] checklist items

### Critical Path
[Dependency diagram showing what blocks what]

Rules:

  • Status values: COMPLETE (fully resolved), SCOPED (professional work defined), PENDING (waiting on other items or final actions), TODO (missing contractor input)
  • The "Key Findings" section is important — it translates raw answers into conclusions
    • "Sewer capacity is fine — 34 DFU on a 216 DFU line"
    • "Water meter adequate — 3/4" for SFR + 600 sq ft ADU"
    • "Drainage works naturally — property slopes SW"
  • Mark completed contractor items with [x] in the checklist
  • Show the critical path — what can proceed in parallel, what's sequential
4. sheet_annotations.json

Per-sheet breakdown of what needs to change, structured for potential future PDF markup.

Schema:

json
{
  "project": { "address": "", "permit_number": "" },
  "revision_number": 1,
  "revision_date": "YYYY-MM-DD",
  "annotations": [
    {
      "sheet_id": "A3",
      "page_number": 7,
      "file": "page-07.png",
      "sheet_title": "Elevations & Proposed Roof Plan",
      "actions": [
        {
          "item_number": "14",
          "area": "South elevation, patio soffit — Detail 2 area",
          "action": "New fire-rated assembly detail replacing Detail 2/A3",
          "specification": "5/8\" Type X gypsum on underside of 2x rafter framing",
          "professional": "Designer",
          "status": "SCOPED",
          "revision_note": "REV 1: New fire-rated soffit detail per Item 14"
        }
      ]
    }
  ],
  "revision_table": [
    { "rev": 1, "date": "", "description": "", "sheet": "", "item": "" }
  ]
}

Rules:

  • Every annotation must reference a valid sheet from sheet-manifest.json
  • Include revision_note text for each action — ready for a revision table
  • Status follows the same values as the corrections report
  • The revision_table at the bottom collects all revision entries

Handling Missing Answers

When contractor_answers.json has items in the skipped array or questions left unanswered:

  • Response letter: Insert [TODO: specific description] at the exact gap
  • Professional scope: Show "Awaiting contractor input" with the specific missing info listed
  • Corrections report: Mark status as TODO or PARTIAL
  • Sheet annotations: Set status to "TODO", set specification to null

Never block on missing answers. A partial response package is still valuable — the professional can start on everything that IS answered.

Important Notes

  • This skill has no memory of Phase 1. Do not assume any context beyond what's in the files. Read the files carefully.
  • corrections_categorized.json is the source of truth. It has the merged research — state law findings, city findings, sheet observations — all cross-referenced per item. Trust it.
  • Preserve original wording. The corrections_parsed.json has the exact text from the corrections letter. Use it in the response letter — the plan checker needs to see their language referenced.
  • Sheet references are sacred. Every sheet reference must come from sheet-manifest.json. The manifest is the ground truth for which sheet ID maps to which page.
  • Professional scope should be actionable. A designer reading the scope should be able to sit down and start drawing without re-reading the corrections letter. Include specific dimensions, materials, code references.
  • Contractor answers become specifications. "4 inch ABS" in the answer becomes "4" ABS" in the professional scope with a ready-to-paste note for the plan. "102.85" becomes a row in a grade table with the calculated drop from finished floor.
  • This tool helps contractors comply, not litigate. If the city says fix it, help fix it.

© mikeOnBreeze, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in server/skills/adu-corrections-complete of mikeOnBreeze/cc-crossbeam.

Open the folder on GitHubat commit cc5591e

Compare with similar skills

Adu Corrections Complete next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Adu Corrections Complete compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adu Corrections Complete this skillmikeOnBreeze/cc-crossbeam293—~2.6kAutomated safety check: PassMIT
Generatealirezarezvani/claude-skills28k1 repos~1.1kAutomated safety check: PassMIT
Response Schema Generatorjeremylongshore/tons-of-skills-marketplace2.8k—~577Automated safety check: PassMIT
Responsive Unitsthedaviddias/Front-End-Checklist74k—~472Automated safety check: PassMIT
Fal Generatenexu-io/open-design100k—~306Automated safety check: PassApache-2.0
Runbook Generatoralirezarezvani/claude-skills28k—~535Automated safety check: PassMIT

Similar skills

  • Generate

    alirezarezvani/claude-skills

    Generate Playwright tests. An agent skill from alirezarezvani/claude-skills.

    28k GitHub starsUsed in 1 repo~1.1k tokens
    Testing & QAAuto-check passed
  • Response Schema Generator

    jeremylongshore/tons-of-skills-marketplace

    Generate response schema generator operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~577 tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Responsive Units

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Use relative units for responsive layouts.

    74k GitHub stars~472 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Fal Generate

    nexu-io/open-design

    Generate images and videos using fal.ai AI models. An agent skill from nexu-io/open-design.

    100k GitHub stars~306 tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Runbook Generator

    alirezarezvani/claude-skills

    Generate operational runbooks from a service name — deployment, incident response, maintenance, and rollback workflows.

    28k GitHub stars~535 tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Video Generation

    bytedance/deer-flow

    Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.

    84k GitHub starsUsed in 3 repos~1.4k tokens
    Media & CreativeAuto-check passed

More from mikeOnBreeze/cc-crossbeam

All 20 skills in this repo
  • Adu PDF Extraction

    mikeOnBreeze/cc-crossbeam

    This skill extracts construction PDF plan binders into agent-consumable formats.

    293 GitHub stars~5k tokensUpdated 7 mo ago
    Auto-check passed
  • Adu Targeted Page Viewer

    mikeOnBreeze/cc-crossbeam

    Extracts construction plan PDFs into page PNGs, reads the sheet index to build a sheet-to-page manifest, and enables targeted viewing of specific sheets.

    293 GitHub stars~1.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Fal AI

    mikeOnBreeze/cc-crossbeam

    This skill enables AI video generation from images AND text-to-speech voiceover generation using Fal.ai's API.

    293 GitHub stars~1.9k tokensUpdated 7 mo ago
    Auto-check: notes
  • Nano Banana

    mikeOnBreeze/cc-crossbeam

    This skill enables image generation and editing using Google's Gemini Nano Banana models.

    293 GitHub stars~944 tokensUpdated 7 mo ago
    Auto-check: notes
  • Adu City Research

    mikeOnBreeze/cc-crossbeam

    Researches city-level ADU regulations, municipal codes, and standard details for any California city.

    293 GitHub stars~3.9k tokensUpdated 7 mo ago
    Auto-check passed
  • Adu Plan Review

    mikeOnBreeze/cc-crossbeam

    City-side ADU plan review — the flip side of adu-corrections-flow.

    293 GitHub stars~3.7k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Adu Corrections Complete

What does Adu Corrections Complete do?

Generates the final response package for ADU permit corrections — the second half of the corrections pipeline. Adu Corrections Complete is an agent skill from mikeOnBreeze/cc-crossbeam. Generates the final response package for ADU permit corrections — the second half of the corrections pipeline.

When should I use Adu Corrections Complete?

Adu Corrections Complete fits situations like: A session directory contains corrections analysis files and a contractoranswers.json has been provided.

How do I install Adu Corrections Complete in Claude Code?

Run `npx skills add mikeOnBreeze/cc-crossbeam --skill adu-corrections-complete -a claude-code`. Or copy the skill folder (server/skills/adu-corrections-complete in mikeOnBreeze/cc-crossbeam) into .claude/skills/adu-corrections-complete in your project. Claude Code loads it when a task matches its description.

How do I install Adu Corrections Complete in Codex?

Run `npx skills add mikeOnBreeze/cc-crossbeam --skill adu-corrections-complete -a codex`. Or copy the skill folder (server/skills/adu-corrections-complete in mikeOnBreeze/cc-crossbeam) into .agents/skills/adu-corrections-complete in your project. Codex loads it when a task matches its description.

Can I use Adu Corrections Complete in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mikeOnBreeze/cc-crossbeam --skill adu-corrections-complete -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adu-corrections-complete, .gemini/skills/adu-corrections-complete, .github/skills/adu-corrections-complete and .opencode/skills/adu-corrections-complete in your project.

What does Adu Corrections Complete need to run?

SKILL.md names no scripts, command-line tools or credentials: Adu Corrections Complete is instructions for the agent only.

Does Adu Corrections Complete access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Adu Corrections Complete safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Adu Corrections Complete use?

Adu Corrections Complete is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Adu Corrections Complete use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Adu Corrections Complete?

Skills that share tags, products or a category with Adu Corrections Complete: Generate (alirezarezvani/claude-skills, 28k stars), Response Schema Generator (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Responsive Units (thedaviddias/Front-End-Checklist, 74k stars) and Fal Generate (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adu Corrections Complete?

mikeOnBreeze (a GitHub user) maintains it in mikeOnBreeze/cc-crossbeam, which has 293 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on March 2, 2026.

Source: mikeOnBreeze/cc-crossbeam on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.