OKF Skills — internal database¶
Private reference for colleagues: what each opencode skill does and when to use it.
96 skills. Rebuilt 2026-09-05 from .opencode/skills/*/SKILL.md — open a skill page for the full text.
OKF practice core¶
| Skill | What it does |
|---|---|
| bieber-scale | Score legal prose against Douglas Biber's Multi-Dimensional Analysis (Dimension 1, Involved vs Informational) using pybiber + spaCy, and enforce academic/passive register targets in drafting. Use when asked to score text… |
| bookshelf | Traverse the unified paragraph-level index of the OKF reference books (Cutts Plain English, Seely A-Z of Grammar & Punctuation, Swan Practical English Usage, Black Written Pleading). Use when asked to look up, quote, cit… |
| call-log-billing | Turn the daily SMS Backup & Restore call-log XML into a per-matter billable call table. Use when the user mentions the call log, calls-*.xml, billing calls, or phone time for Clio. |
| case-law | Case law retrieval, reporting and citation standards for OKF matters. Use whenever the user asks for case law, precedent, authority, "what does the law say", summarising a judgment, finding a case, or citing a case in co… |
| clio | Read-only access to the Clio Manage API (matters, contacts, activities/time entries, bills, documents, tasks, calendar, custom fields) for the firm's Clio account. Use when the user asks about Clio data, pulling matters/… |
| cutts-plain-english | Plain English drafting and rewriting per Martin Cutts, Oxford Guide to Plain English, 5th edn (2020) — short sentences (15-20 word average, nothing over 35 without reason), active voice, vigorous verbs, few negatives, no… |
| draft-augmenter | Augment an existing draft post-hoc on instruction — "add more quotes for this case", "beef up Part 6", "find authority for X", "deepen the application" — by re-opening the matter corpora, inserting verbatim pinpointed pa… |
| factual-event-table | Extract every factual event from source documents into a Date/Time | Actor | Action | Detail | Source table — one row per discrete event, active voice with actor as grammatical subject, [not stated] for gaps, assertion a… |
| freeagent | Read-only access to the FreeAgent accounting API (contacts, invoices, bills, bank accounts and transactions, expenses, estimates, proformas, projects, timeslips, users, company) for the firm's FreeAgent account. Use when… |
| gdrive-share | Publish matter content from the live OneDrive workspace to the firm's shared Google Drive (H:\My Drive\ |
| graphify | Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (cod… |
| mistral-ocr | Verbatim OCR of PDFs and images using Mistral's vision model - ImageMagick conversion at 300 DPI, per-page transcription, QA flags, OCR_Log row. Use when the user requests Mistral-based OCR for verbatim transcription (le… |
| okf-inventory | Build a court Inventory of Productions PDF for an OKF matter (whole-paragraph yellow highlighting of production source PDFs, optional verbatim web-page captures, court-formatted cover + hyperlinked index + page ranges + … |
| okf-mail-watch | Local Outlook thread-precedent mail filing watcher - watches the firm inbox and files new mail into the Clio Manage Open tree by thread precedent. Use when asked about the mail watcher, filing new inbox mail by thread pr… |
| okf-notebooklm | Adapt an OKF matter for NotebookLM (Google's AI notebook). Use when the user mentions NotebookLM, Google NotebookLM, AI notebook, uploading/adapting/preparing an OKF matter for AI question-answering, or building sources/… |
| okf-ocr | Process scanned or text-less documents in OKF matter folders. Use when files appear in 98_Inbox_ToProcess, when OCR log rows are PENDING, when the user mentions OCR, scanning, digitising documents, extracting tables, or … |
| okf-rapidocr | Evaluate RapidOCR (PaddleOCR PP-OCR models on onnxruntime) as a native-ARM64 offline OCR path for OKF matters - A/B against the okf-ocr paddle path, identical sidecar conventions and confidence flags, resume-safe batches… |
| pleading | Draft and review Scottish civil court pleadings using Black, Braid, Scullion & Johnston, "An Introduction to Written Pleading", 2nd edn (EUP 2025) with Macphail, Macphail's Sheriff Court Practice, 4th edn (2006) as secon… |
| scotcourts | Search Scottish court cases via the undocumented scotcourts.gov.uk web API (judgments since 1999, fatal accident inquiry determinations). Use when the user asks to find/search Scottish judgments or opinions by keyword, c… |
| ssdt | Search the Scottish Solicitors' Discipline Tribunal findings database via its undocumented query-string interface (server-rendered GET at ssdt.org.uk/findings - no JSON API, no auth). Use when the user asks whether a Sco… |
| sub-editor | Grammar, punctuation and structure sub-editing of legal drafting — register-independent correctness pass mapped to three indexed books: Practical English Usage (Swan), Oxford A-Z of Grammar and Punctuation (Seely), Oxfor… |
| submission-planner | Plan a detailed submission BEFORE drafting — issues → propositions → verified authorities per proposition → application mapping, with a verification gate and a fact/argument register plan. Use when asked to draft, outlin… |
| verbatim-ocr | Quality-assurance and verbatim-transcription standards for OCR'd legal documents in OKF matters. Use after the deterministic pipeline (okf-ocr skill, tools/ocr_pipeline.py) to verify sidecars, tables and figures against … |
| web-research | General web research for OKF matters — legislation, statutory instruments, regulations, standards (BS/EN), guidance, news and web sources — with token-efficient layered fetching, source hierarchy, and mandatory citation … |
Register locks (11) — Biber Dimension 1 discipline; DeepSeek fact ⇄ argument pairs + specialized registers¶
| Skill | What it does |
|---|---|
| deepseek-biber-argument | Register lock for legal argument and submissions tuned for DeepSeek V4 Pro — present-tense propositions, dense modals and suasive verbs, nominalized abstractions, passives where the agent is law or court. Use when drafti… |
| deepseek-biber-client-letter | Register lock for correspondence with clients tuned for DeepSeek V4 Pro - professional dialogue: rationed first/second person, advice modals, clear narrative updates. Use when drafting or rewriting a letter or email to a… |
| deepseek-biber-counsel | Register lock for instructions to counsel (memorials) tuned for DeepSeek V4 Pro - the memorial register: both-sides objectivity in advise mode, drafting advocacy in draft mode, numbered questions for counsel, citation di… |
| deepseek-biber-expert | Register lock for instructions to expert witnesses tuned for DeepSeek V4 Pro - the deepest informational register of the family: independence-by-syntax question frames (address/consider, never conclude), dense document r… |
| deepseek-biber-fact | Register lock for factual legal narration tuned for DeepSeek V4 Pro — past-tense narrative, third person, no evaluation. Use when drafting or rewriting a statement of facts, chronology, condescendence narration, witness … |
| deepseek-biber-fact-plain | Factual legal narration in the Bingham plain voice, tuned for DeepSeek V4 Flash, under the full Biber register discipline — past-tense narrative, third person, no evaluation, informational features, written in Lord Bingh… |
| deepseek-biber-opponent-letter | Register lock for correspondence to opposing parties and their agents tuned for DeepSeek V4 Pro - combative professional prose: demands, warnings, reserved positions; high D4 persuasion; citation discipline; escalation l… |
| deepseek-biber-witness | Register lock for witness statements and precognitions tuned for DeepSeek V4 Pro - first-person past-tense narrative, high D2, zero argument. Use when drafting or rewriting a witness statement, precognition, statement of… |
| deepseek-flash-biber-argument | Register lock for legal argument and submissions tuned for DeepSeek V4 Flash — present-tense propositions, dense modals and suasive verbs, nominalized abstractions, passives where the agent is law or court. Use when draf… |
| deepseek-flash-biber-fact | Register lock for factual legal narration tuned for DeepSeek V4 Flash — past-tense narrative, third person, no evaluation. Use when drafting or rewriting a statement of facts, chronology, condescendence narration, witnes… |
Typst generators (templates bundled per skill; docs mirror _typst-manual is a sibling)¶
| Skill | What it does |
|---|---|
| scottish-legal-letter-writer | >- Generates authoritative, beautifully styled Scottish legal correspondence, court lodging cover letters, opponent intimations, client reporting letters, and expert instructions using Typst & HTML master templates, inco… |
| scottish-legal-letter-writer | Generate authoritative Scottish legal correspondence using the exact master Typst letterhead template. Use when asked to write a formal Scottish legal letter or notice on firm letterhead. |
| typst-adjudication-generator | |
| typst-building-contract-generator | |
| typst-letter-generator | |
| typst-planner | Plan ANY Typst document before drafting — classify the document type, route to the correct typst generator skill, gather every required variable binding, and emit a structured plan for sign-off. Use when the user asks to… |
| typst-report-generator |
Court & documents¶
| Skill | What it does |
|---|---|
| docx | Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or… |
| docx-expert | Make surgical, style-preserving edits to .docx legal documents (keeps branding and JCT tables intact) via safe-docx tools. Use when asked to edit, fill placeholders in, or amend a Word (.docx) legal document. |
| markdown-to-word-converter | Convert a Markdown (.md) file to a Word (.docx) document using Pandoc. Use when the user asks to convert markdown to Word. |
| professional-appointment-manager | Generate and manage professional appointment documents - full lifecycle from draft to amendable Word file to final styled Typst PDF, plus Typst-native drafting of forensic legal reviews, commercial advisory reports, and … |
| scottish-court-form-builder | Generate Scottish Sheriff Court civil forms (Ordinary Cause & Commercial Actions) and collateral documents (intimations, certificates, oppositions, citations) with case-ref enforcement and Sheriffdom suggestions. Also dr… |
| webapp-testing | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. |
| xlsx | Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, … |
Writing style¶
| Skill | What it does |
|---|---|
| asd-ste100 | Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads… |
| avoid-ai-writing | Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound… |
| bingham-architect | Turn messy, conversational, or emotive notes into a structured, dispassionate legal first draft using the Bingham/Sumption syntax protocol (Workflow 1, Phase 1, before the 4-Agent Polisher). Use when asked to draft, stru… |
| bingham-plain | Rewrite legal prose in Lord Bingham's plain-speaking voice — short declarative sentences, plain words, active voice, one idea per sentence, concrete before abstract, judgment last. Fact-narration first (statements of fac… |
| concise-answers | |
| no-ai-slop | Hard-rule audit that strips AI slop: emdashes, intensifiers, filler, hollow claims, fabricated facts, AI verbs and transitions, dramatic headings, weasel words — 24 non-negotiable rules with WRONG/RIGHT examples and a ba… |
| rossmann-voice | Louis Rossmann's data-driven voice for general prose: testable-number density, high sentence-length variance, claim-then-proof structure, contractions, contempt shown through precision. Complementary to the Biber registe… |
| sumption-rewriter | Rewrite legal or commercial arguments into the crisp, authoritative passive voice and cadence of Lord Jonathan Sumption. Use when asked to make writing more forceful, formal, or judicial in style. |
Utility & design (isolated)¶
| Skill | What it does |
|---|---|
| architecture-diagram | Create polished dark-themed architecture diagrams as self-contained HTML+SVG files. Use when the user asks for system, infrastructure, cloud, security, or network topology diagrams. |
| boilerplate-clause-analyzer | Analyze T&C or contracts against the 77 boilerplate clauses, then summarise, assess per-party risk in callout boxes, and rewrite clauses per precedent. Polite formal UK legal English; always asks, never guesses. Use when… |
| brand-guidelines | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design … |
| canvas-design | Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs… |
| contract-review | Execute a micro-granular 7-stage review of building contracts and schedules of amendments — risk matrix, redline negotiation package, BSA 2022 SI mapping, and mandatory independent audit (contract-review-auditor subagent… |
| downloads-tidier | Tidy the user's Downloads folder into category folders (Books, CourtLegal, ResearchNotes, Installers, Archives, Documents), quarantining duplicate downloads into _Duplicates and logging every move. Use when the user says… |
| excalidraw-diagram | Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts. |
| frontend-design | Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. |
| Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding w… | |
| theme-factory | Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creatin… |
Other¶
| Skill | What it does |
|---|---|
| archify | Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM exp… |
| ask-matt | Ask which skill or flow fits your situation. A router over the skills in this repo. |
| code-review | Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating iss… |
| codebase-design | Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when an… |
| diagnosing-bugs | Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. |
| domain-modeling | Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR. |
| engagement-letter-generator | Interactive skill for generating legal Engagement Letters and Terms of Business for The Building Law Practice Limited using Typst. Guides the user socratically through required template parameters and compiles or updates… |
| gemini-api | The firm's Gemini API key (free tier, no billing attached) and every tool that consumes it. Use when the user mentions the Gemini API key, free Gemini key, the Google AI API key, gemini OCR cost, "no billing", or needs t… |
| grill-me | A relentless interview to sharpen a plan or design. |
| grill-with-docs | A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. |
| grilling | Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases. |
| handoff | Compact the current conversation into a handoff document for another agent to pick up. |
| implement | Implement a piece of work based on a spec or set of tickets. |
| improve-codebase-architecture | Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. |
| notebooklm | Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or dow… |
| papers-for-counsel-typst | Build a papers-for-counsel / inventory-of-papers bundle PDF whose cover and index are rendered in Typst in the in-house report style (clinical serif, monogram box, metadata grid, running header, centred page counter), wi… |
| prototype | Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like. |
| research | Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a… |
| resolving-merge-conflicts | Use when you need to resolve an in-progress git merge/rebase conflict. |
| setup-matt-pocock-skills | Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills. |
| tdd | Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests. |
| teach | Teach the user a new skill or concept, within this workspace. |
| to-questionnaire | Turn a decision you can't fully answer into a questionnaire for someone else to fill in. |
| to-spec | Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed. |
| to-tickets | Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blockin… |
| triage | Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. |
| wait-what | Stop. That last message did not land: re-pitch it. |
| wayfinder | Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear. |
| wizard | Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or runn… |
| writing-for-agents | Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. |