Docs & Writing
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
-
sboghossian-mini-claude-for-legal Skill Docs Practice Management GuideUse when a user asks about the platform's practice management features — matters, time tracking, billing, conflict checking, and trust accounts — or about integrating with accounting and CRM systems. This is a platform documentation skill covering the practice management feature set and its integration map (HubSpot, Stripe, NetSuite, QuickBooks, Xero).
-
sboghossian-mini-claude-for-legal Skill Justice Result Page RoutingUse to decide, after a substantive AI task completes, whether to display the output inline in chat or route the user to a dedicated result page (doc workspace, memo viewer, compare viewer, citation report, etc.). Applies a deterministic threshold based on output type, length, and follow-up tool needs. Covers all jurisdictions; no practice area restriction — this is a UI-routing and output-orchestration skill.
-
sboghossian-mini-claude-for-legal Skill Output Mobile Friendly ShortUse when Claude must adapt its output for mobile surfaces — short chat responses, in-app legal answers, or any context where the user is on a small screen or expects a concise result. Enforces hard word limits, removes wide tables, and strips verbose hedging. Triggers on mobile UI signals, short-form question context, or explicit brevity requests.
-
sboghossian-mini-claude-for-legal Skill Pillar Legal Skills AuthoringInternal architectural principle establishing that legal skills are first-class artifacts — each skill is a versioned, reviewable markdown file with structured frontmatter. Use when designing the skill authoring workflow, reviewing skill quality, or understanding how skills are loaded, routed, and updated in the Louis system.
-
freedomintelligence Bundle Pharmgx ReporterPharmacogenomic report from DTC genetic data (23andMe/AncestryDNA) — 12 genes, 31 SNPs, 51 drugs
-
sboghossian-mini-claude-for-legal Skill Workflow Fire Employee PackUse when a user needs to manage an employee termination from a legal and documentation standpoint — covering pre-termination risk assessment, final pay calculation, document generation, visa cancellation in MENA, government deregistration, and post-termination compliance. Provides jurisdiction-specific guidance for UAE (Federal Decree-Law 33/2021), KSA (Labour Code Arts 76–80), Lebanon (Labor Code Arts 50/74), and DIFC Employment Law.
-
sboghossian-mini-claude-for-legal Skill Intel Anthropic Claude For WordUse when discussing Anthropic's Claude for Word integration, the Microsoft Word plugin landscape for legal AI, competitive implications for document-drafting tools (Spellbook, Harvey, Louis), or distribution strategy via productivity software. Covers the 2025 launch, what the plugin does, which user segments it targets (BigLaw, corporate legal), and strategic implications for MENA-focused legal AI platforms.
-
sboghossian-mini-claude-for-legal Skill Report Weekly AI Quality TrendUse when the product or engineering team needs a single aggregated weekly view of AI output quality across all tracked dimensions — eval suite scores, user NPS/satisfaction signals, hallucination rate, and bug rate — to spot regressions early, validate improvements, and maintain a historical quality record. This is an internal executive-level quality report. Trigger on the weekly quality-review schedule; escalate to an incident if any metric crosses a red threshold.
-
gptomics Bundle Bio Imaging Mass Cytometry Quality MetricsQuality control for IMC/MIBI data across pixel, channel, image, slide, and batch levels, covering Poisson-count SNR (cell-level Gaussian-mixture and empty-channel comparison), spillover-matrix QC (the three physical sources), drift and the missing EQ-bead analog, acquisition artifacts, and sample-of-origin batch effects. Use when deciding whether to keep or drop a channel, ROI, or slide, distinguishing a dim antibody from a failed one, reading a spillover matrix, or diagnosing batch-driven clustering before analysis.
-
sboghossian-mini-claude-for-legal Skill Safety Violence Threats HandlingUse when a user describes violence, domestic abuse, physical threats, or expresses intent to harm themselves or others. Immediately surfaces emergency resources and legal remedies (protective orders, criminal complaints), provides documentation guidance, and re-routes threatening language toward de-escalation and professional support. Provides jurisdiction-specific DV hotlines and emergency contacts for Lebanon, KSA, UAE, France, UK, and US. Never lectures or minimizes the user's experience.
-
gptomics Bundle Bio Spatial Transcriptomics Spatial Data IoLoads spatial transcriptomics data from Visium, Visium HD, Xenium, MERFISH/MERSCOPE, CosMx, Slide-seq/Curio, and Stereo-seq into AnnData or SpatialData using spatialdata-io and Squidpy. Use when deciding which platform class is in hand (imaging/in-situ vs sequencing/capture), which reader matches the platform (spatialdata_io.xenium/merscope/cosmx vs squidpy.read.visium/vizgen/nanostring), whether to work from the per-transcript molecule table (the re-segmentable source of truth) or the segmentation-derived per-cell matrix (quality-filtered, inherits all segmentation error), whether a molecule table even exists (spot platforms have none), and how to keep coordinate frames and units (pixel vs micron) registered to histology.
-
gptomics Bundle Bio Spatial Transcriptomics Spatial DomainsIdentify spatially coherent tissue domains (regions like cortical layers, tumor vs stroma) in Visium, Visium HD, Xenium, MERFISH, Slide-seq, and Stereo-seq data with Squidpy, BANKSY, BayesSpace, STAGATE, and GraphST. Use when distinguishing a domain (a region with many cell types) from a cell type (one cell's identity) and a niche (local cell-type composition); choosing a domain method by tissue geometry (laminar/continuous vs high-resolution imaging vs non-contiguous); tuning the spatial-weight knob (BANKSY lambda, BayesSpace smoothing, SpaGCN histology weight, GNN graph radius) to avoid over-smoothing into blobs or under-smoothing into salt-and-pepper; choosing the number of domains k as a biological decision with k+-1 sensitivity; and reading the Yuan 2024 benchmark with the DLPFC continuous-laminar caveat.
-
sboghossian-mini-claude-for-legal Skill Workflow Full Due Diligence PackUse when orchestrating a full legal due diligence exercise for an M&A transaction, private equity investment, or acquisition financing. Covers ten parallel workstreams (corporate, commercial contracts, employment, IP, real estate, litigation, regulatory, tax, data privacy, financial), with MENA-specific flags for change-of-control, foreign ownership restrictions, PDPL readiness, and open-source IP compliance. Produces a structured DD report with green/amber/red workstream ratings.
-
autohandai-community-skills Bundle Nvidia Nemoclaw Contributor Update DocsScan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages and refresh generated user skills for release prep. Use when docs have fallen behind code changes, after a batch of features lands, during daily release prep, or when preparing a release. Trigger keywords - update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift, release prep docs, refresh user skills.
-
gptomics Bundle Bio Methylation CallingExtracts per-cytosine methylation calls from aligned bisulfite/EM-seq reads with bismark_methylation_extractor (Bismark BAM) or the aligner-agnostic MethylDackel/BISCUIT (bwa-meth BAM), producing the beta value M/(M+U) as a coverage file, bedGraph, or genome-wide cytosine report across CpG/CHG/CHH context. Covers conversion-rate QC as the first gate, the 5mC vs 5hmC summed caveat, variant-aware calling so a C/T SNP does not masquerade as unmethylation, paired-end --no_overlap double-counting, symmetric CpG dyad collapse, and the 0-based vs 1-based coordinate trap. Use when extracting methylation levels from a bisulfite/EM-seq alignment, choosing an extractor for a non-Bismark BAM, QC-ing conversion efficiency, or producing coverage/cytosine-report input for testing. For long-read MM/ML modification calling see long-read-sequencing/nanopore-methylation; for the upstream BAM see bismark-alignment; for per-CpG statistics see differential-cpg-testing.
-
sboghossian-mini-claude-for-legal Skill Kb Immigration Residency Uae Golden VisaUse when a matter involves long-term UAE residency, the UAE Golden Visa (10-year renewable), the Green Visa (5-year self-sponsored), or investor/talent residency pathways. Covers eligibility categories (investors, entrepreneurs, specialized talent, researchers, students), documentation requirements, family inclusion rules, and the impact of Golden Visa status on employment, real estate ownership, and banking. Also covers the distinctions between the Golden Visa, Green Visa, and standard employer-sponsored residency. Triggers on UAE Golden Visa eligibility, Green Visa UAE, long-term UAE residency, or UAE investor visa questions.
-
sboghossian-mini-claude-for-legal Skill Efirm Finance Wip Aging ReportUse when a law firm finance team needs to identify and act on unbilled work-in-progress (WIP) that is aging beyond acceptable thresholds. The skill lists all unbilled time and expenses by age bucket, matter, attorney, client, and practice area; highlights write-off candidates and clients requiring interim bills; and produces partner-facing action emails. Relevant to all law-firm jurisdictions.
-
jmagly-ai-writing-guide Skill Radar ReportAggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
-
jmagly-ai-writing-guide Skill Radar StatusReport which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
-
sboghossian-mini-claude-for-legal Skill Public Tool Nda Generator PublicUse when a user needs to generate a one-way or mutual NDA in approximately 60 seconds via a guided form — the primary free lead-generation tool for Louis. Takes jurisdiction (KSA, UAE, DIFC, ADGM, LB, English law, US), party names, purpose, term, and optional industry add-ons as inputs; outputs a PDF and DOCX download with referral watermark. Works across all supported jurisdictions; drives conversion to registered accounts via email capture and variation unlocking.
-
jmagly-ai-writing-guide Skill Provenance ReportGenerate provenance coverage dashboard and statistics
-
jmagly-ai-writing-guide Skill Regression ReportGenerate comprehensive regression analysis reports combining bisect, baseline, and metrics data with actionable recommendations
-
jmagly-ai-writing-guide Skill Claims ValidatorValidate documentation for unsupported claims, made-up metrics, and unverifiable statements
-
sboghossian-mini-claude-for-legal Skill Voice Multimodal Signature Page DetectorUse when processing a legal document (PDF, image, or OCR output) to detect signature pages, validate that all required signatures and witness blocks are present, and flag missing or incomplete execution elements. This skill covers detection patterns for wet signatures, electronic signatures, notary stamps, and MENA-specific instruments (Tawqi3i, Ministry attestation), plus per-jurisdiction validation of witness and notarization requirements.
-
autohandai-community-skills Bundle Building Incident Timeline With TimesketchBuild collaborative forensic incident timelines using Timesketch to ingest, normalize, and analyze multi-source event data for attack chain reconstruction and investigation documentation.
-
jmagly-ai-writing-guide Skill Profile StatusReport research-corpus entity profiles (PROF-P/O/G/F) past their refresh cadence. Computes staleness via the shared cadence helper, sorted most-overdue-first. Runs via `aiwg corpus profile-status`.
-
jmagly-ai-writing-guide Skill Vision ExtractTranscribe scanned page images into per-page + combined Markdown source text for induction, via a provider-neutral vision adapter (codex CLI or a generic command template for Claude/any vision tool). Resumable, with retry + `# Page N` validation + extraction-status markers; optionally rasterizes a PDF to page PNGs first. Runs via `aiwg corpus vision-extract`.
-
jmagly-ai-writing-guide Skill Check TraceabilityVerify the full refinement chain from use cases through behavioral specs, pseudo-code specs, code, and tests — report coverage at each layer and identify gaps
-
sboghossian-mini-claude-for-legal Skill Public Tool Contract Redline PublicUse when a user uploads or pastes a short commercial contract (up to 3 pages in the free tier) and needs an automated red-flag analysis plus suggested redline language in track-changes format. Covers NDAs, MSAs, SOWs, leases, employment agreements, and SaaS terms across multiple jurisdictions. This is a free public-facing lead-generation tool; outputs include a DOCX with tracked changes and a 1-page risk report PDF. Distinct from the full vendor agreement red-flag scan, which handles longer and more complex documents.
-
sboghossian-mini-claude-for-legal Skill Public Tool Statute Explainer PublicUse when a user provides a statute or regulation reference (e.g., "UAE FDL 33/2021 Article 42") and needs the verbatim text, a plain-English explanation, typical fact patterns where the article applies, recent amendments or interpretations, and cross-references to related articles. Covers UAE federal laws, KSA Royal Decrees, Lebanon major codes, Egyptian codes, EU regulations and directives, and US federal law (USC). Free public tool; outputs a PDF with citation and Louis branding.
-
jmagly-ai-writing-guide Skill Validate MetadataValidate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints
-
jmagly-ai-writing-guide Skill Workspace RealignReorganize and update .aiwg/ documentation to reflect current project reality
-
sboghossian-mini-claude-for-legal Skill Conversation Intake Divorce PetitionUse before drafting a divorce petition or advising on family-law proceedings to gather 10 required inputs — jurisdiction, marriage details, children, assets, debts, support expectations, grounds, safety concerns, living arrangements, and available documentation. Handles the intake with appropriate sensitivity. Provides MENA-specific guidance on confessional court jurisdiction in Lebanon, religious personal status courts in UAE and KSA, and the treatment of civil marriages contracted abroad. Refuses to assist with asset-hiding strategies or fault prejudgment.
-
jmagly-ai-writing-guide Skill Corpus SnapshotGenerate a corpus snapshot report — computes dimensions, topology, degree distribution, delta from previous. Helps with cluster, chain, and gap analysis sections.
-
sboghossian-mini-claude-for-legal Skill Efirm Finance Budget Vs Actual MatterUse when a law firm needs to track and report on budget versus actual spend for an open matter. Produces a dashboard showing budget by phase, actual hours and fees by phase, variance (absolute and percentage), burn rate, projected-at-completion estimate, and recommended management actions. Triggers automatic alerts when the budget threshold is exceeded or burn rate is off plan. Designed for use by billing partners and matter supervisors to catch overruns before they become client-relationship problems.
-
sboghossian-mini-claude-for-legal Skill Efirm Finance Ewallet Balance CheckerUse when a law firm needs to check and report on client advance retainer or e-wallet balances — displaying the current retainer balance held in trust, recent debits and credits, projected runway at current burn rate, and generating a top-up request email when the balance falls below the replenishment threshold. Must be used with trust-account compliance rules (IOLTA / client money rules); see the related trust-account-reconciliation skill for compliance layer.
Frequently asked questions
What are Docs & Writing agent skills?
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
Which Docs & Writing skills are most installed?
Popular Docs & Writing skills on SkillMD right now include pharmgx-reporter, bio-imaging-mass-cytometry-quality-metrics, bio-spatial-transcriptomics-spatial-data-io. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Docs & Writing skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.