Claude Skills by pjt222

Preserve and conserve library and archival materials. Covers environmental controls (temperature, humidity, light), handling procedures, book repair techniques (torn pages, loose spines, foxing), acid-free storage, digitization for preservation, and disaster recovery planning. Use when establishing preservation practices for a new or existing collection, when materials show signs of deterioration, when setting up environmental controls for storage, when planning digitization to preserve fragi...

Probe the runtime state of a named feature flag in a CLI binary. Covers the four-pronged evidence protocol (binary strings, live invocation, on-disk state, platform cache), the four-state classification (LIVE / DARK / INDETERMINATE / UNKNOWN), gate-vs-event disambiguation, conjunction-gate handling, and skill-substitution scenarios where a flag appears DARK but the capability is delivered by other means. Use when verifying whether a documented or inferred capability has rolled out, when audit...

Prove geometric theorems using Euclidean axiomatic methods, coordinate geometry, or vector methods with rigorous step-by-step logical structure. Covers direct proof, proof by contradiction, coordinate proofs, vector proofs, and handling of special cases and degenerate configurations. Use when given a geometric statement to prove, verifying a conjecture, establishing a lemma, converting geometric intuition into a rigorous proof, or comparing the effectiveness of different proof methods.

Provision and manage cloud infrastructure using Terraform with HCL modules, remote state backends, workspaces, and plan/apply workflow. Implement infrastructure as code patterns with variable management, output values, and state locking for team collaboration. Use when provisioning new cloud infrastructure, migrating from ClickOps or CloudFormation to declarative IaC, managing multi-environment infrastructure, versioning infrastructure changes alongside application code, or enforcing standard...

Audit, classify, and selectively forget stored memories. Covers memory enumeration and classification by type/age/access frequency, staleness detection for outdated references, fidelity checks using external anchors, a decision tree for selective withdrawal, tombstoned deaccession so removed content stays recoverable, counter-memory inoculation for failed strategies that would otherwise be re-derived, preemptive filtering rules for what should never become memories, and an audit trail so forg...

Purify water from wild sources using boiling, filtration, and chemical methods. Covers source assessment and priority ranking, sediment pre-filtering, method selection (boiling, chemical, UV, filter), altitude-adjusted boiling procedure, chemical treatment dosages, and safe storage practices. Use when needing drinking water in a wilderness setting, when available water sources are of unknown quality, in an emergency survival situation where dehydration is a risk, or when making water safe for...

Qualify a vendor or supplier of GxP-relevant software or services. Covers vendor risk classification, assessment questionnaire design, desk and on-site audit approaches, quality agreement evaluation, SLA review, and ongoing monitoring cadence definition. Use when selecting a new vendor for a GxP-critical system, onboarding a cloud provider for regulated data, performing a periodic re-qualification, when a vendor audit finding requires re-assessment, or when EU Annex 11 or ICH Q10 requires sup...

Read a CONTINUE_HERE.md continuation file at session start and resume from where the prior session left off. Covers detecting the file, assessing freshness, parsing the structured handoff, confirming the resumption plan with the user, and cleaning up after consumption. Optionally configures a SessionStart hook and CLAUDE.md instruction for automatic pickup. Use at the start of a session when a continuation file exists, when bootstrapping after an interrupted session, or when setting up automa...

Observe and assess a garden using a structured sensory protocol adapted from Coordinate Remote Viewing. Covers pre-entry clearing (meditate checkpoint), Stage I gestalt impression, Stage II sensory layer (leaf, stem, root, soil), Stage III pattern recognition with AOL management, and garden health triage matrix (heal checkpoint). Use before any intervention, when plants show stress symptoms, at seasonal transitions, when evaluating a new garden site, during regular health monitoring, or after...

Navigate the Kabbalistic Tree of Life (Etz Chaim) — explore the ten sephirot, twenty-two paths, four worlds, and three pillars. Covers correspondences, contemplative exercises, and structural analysis. Use when exploring a sephira's attributes and divine names, studying structural relationships between sephirot, learning the four worlds (Atzilut through Assiah), tracing a path's Hebrew letter and tarot attributions, or using the Tree as a symbolic map for understanding a concept or system.

Redact reverse-engineering findings for public disclosure while preserving methodology, generalizable patterns, and teaching value. Covers the private-vs-public repo split, deny-list pattern maintenance, orphan-commit publish pattern that prevents `git log` leaks, category-based redaction calibration (methodology/pattern/version-finding/internal), and the `check-redaction.sh`-style CI gate that blocks merges when a deny-listed pattern appears. Use when publishing findings about a CLI harness ...

Redact rendered visual artifacts — Mermaid diagrams, SVGs, and HTML dashboards — before public disclosure, using an ordered longest-first mapping table (specific label, then namespace label, then catch-all placeholder) that swaps sensitive identifiers for descriptive stand-ins while preserving structure, node ids, and teaching value. Covers whole-word identifier replacement, node-label-vs-node-id discrimination, re-rendering the derived image from the redacted source, and verifying the result...

Redact a network/MITM capture directory — JSONL, JSON, logs, HAR-style dumps — in place before it can be referenced publicly, scrubbing credential tokens, API keys, service ids, UUIDs, emails, home paths, usernames, and device or session hashes while preserving token-class prefixes for analysis and leaving public identifiers untouched. Covers class-preserving substitution, an idempotent re-runnable pass, distinguishing a secret from a public id, and verifying the scrubbed capture through the ...

AI pressure redirection — handling conflicting demands, tool failures, and competing constraints by blending with incoming force then reframing. Use when receiving contradictory instructions from different sources, during tool failure cascades where the planned approach becomes unviable, when scope pressure threatens to expand the task beyond what was asked, or when user frustration or correction needs to be absorbed rather than deflected.

Refactor an over-long or poorly structured SKILL.md by extracting examples to references/EXAMPLES.md, splitting compound procedures, and reorganizing sections for progressive disclosure. Use when a skill exceeds the 500-line CI limit, when code blocks dominate the skill body, when a procedure step contains multiple unrelated operations, or after a content update pushed the skill over the line limit.

Register trained models in MLflow Model Registry with version control, implement stage transitions (Staging, Production, Archived) with approval workflows, and manage model lineage with comprehensive metadata and deployment tracking. Use when promoting a trained model from experimentation to production, managing multiple model versions across development stages, implementing approval workflows for governance, rolling back to previous versions, or auditing model changes for compliance.

Release a new version of an R package including version bumping, NEWS.md updates, git tagging, GitHub release creation, and post-release development version setup. Use when a package is ready for a new patch, minor, or major release, after CRAN acceptance to create the corresponding GitHub release, or when setting up the development version bump immediately after a release.

Guide a person through a Coordinate Remote Viewing (CRV) session following the Stargate/SRI protocol. AI acts as the monitor/tasker role, managing protocol progression, catching Analytical Overlay (AOL), and redirecting the viewer through stages I-VI. Use when a person wants to practice CRV and needs a monitor to manage the session protocol, when training a viewer through the staged CRV process, facilitating a structured intuitive perception exercise, or developing non-local awareness skills ...

AI intuitive exploration for approaching unknown codebases, problems, or systems without preconceptions. Adapts the Coordinate Remote Viewing protocol to AI investigation: cooldown (clear assumptions), staged data gathering (raw signals → dimensional → analytical), AOL management (separating observations from premature labels), and structured review. Use when investigating an unfamiliar codebase with unknown architecture, debugging a problem where premature hypotheses could mislead, exploring...

Configure render settings, compositing nodes, output formats, and execute renders via Cycles or EEVEE engines using Python API or command-line interface. Use when automating render execution for batch processing, configuring quality and performance trade-offs, setting up compositing pipelines for post-processing, generating multiple output formats from a single render, or producing final output for publication or presentation.

Run the viz pipeline to render icons from existing glyphs. Entry point for the viz subproject covering palette generation, data building, manifest creation, and icon rendering for skills, agents, and teams. Always use build.sh as the pipeline entry point — never call Rscript directly.

Produce publication-ready 2D graphics with proper DPI, color profiles, typography, and export formats for print and digital media. Use when preparing figures for academic journal submission, creating graphics for print publications, ensuring graphics meet publisher technical specifications, exporting visualizations for web with proper optimization, or creating multi-format exports from a single source.

Render the jigsawR Quarto documentation site for GitHub Pages. Supports fresh renders (clearing cache), cached renders (faster), and single-page renders. Uses the bundled render script or direct quarto.exe invocation from WSL. Use when building the full site after content changes, rendering a single page during iterative editing, preparing documentation for a release or PR, or debugging render errors in Quarto .qmd files.

Find and fix broken internal links, dead external URLs, stale imports, missing cross-references, and orphaned files. Ensures all project references remain valid and up-to-date. Use when documentation contains broken internal links, external URLs return 404 errors, import statements reference moved or deleted modules, cross-references between files are out of sync, or files exist but are never referenced anywhere in the project. Also use in index mode for a directory of markdown notes with a d...

Implement regenerative recovery using triage, scaffolding, and progressive rebuild. Covers damage assessment, wound classification, emergency stabilization, scar tissue management, and resilience strengthening for systems that have sustained structural damage. Use when a system has suffered an incident needing structured recovery, when a failed transformation left the system in a damaged intermediate state, when accumulated technical debt has caused partial failure, or when a system is functi...

Research the etymology of a word by tracing proto-language roots, identifying cognates across language families, documenting semantic drift with dated attestations, and flagging folk etymologies. Use when investigating word origins, comparing cognate sets across related languages, charting historical meaning changes, or debunking popular but unsupported origin stories.

Resolve merge and rebase conflicts with safe recovery strategies. Covers identifying conflict sources, reading conflict markers, choosing resolution strategies, and continuing or aborting operations safely. Use when a git merge, rebase, cherry-pick, or stash pop reports conflicts, when a git pull results in conflicting changes, or when you need to safely abort and restart a failed merge or rebase operation.

AI intentional non-action — deliberate stopping without clearing, assessment, or rebalancing. Recognition that sometimes the most productive response is no response. Every other self-care skill produces output; rest produces silence. Use when all tending skills feel like more activity rather than less, when the system is functioning well but at high utilization, after sustained intensive work, or when the impulse to optimize is itself the problem.

Restore legibility to an auto-generated graph diagram that has outgrown its canvas - rendering at single-digit percent scale with sub-pixel labels. Covers the levers that measurably reduce layout units (source-level label wrapping, invisible chain links so unconnected nodes stop spreading into one row, per-cluster splitting, layout direction picked by rendering both and measuring) and the rejected ones (raising the render font is a no-op because layout engines measure in text units; a topolog...

Multi-phase deep codebase review with severity ratings and structured output. Covers architecture, security, code quality, and UX/accessibility in a single coordinated pass. Produces a prioritized findings table suitable for direct conversion to GitHub issues via the create-github-issues skill.

Review a data analysis for quality, correctness, and reproducibility. Covers data quality assessment, assumption checking, model validation, data leakage detection, and reproducibility verification. Use when reviewing a colleague's analysis before publication, validating an ML pipeline before production deployment, auditing a report for regulatory or business decision-making, or performing a second-analyst review in a regulated environment.

Review a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.

Conduct a peer review of research methodology, experimental design, and manuscript quality. Covers methodology evaluation, statistical appropriateness, reproducibility assessment, bias identification, and constructive feedback. Use when reviewing a manuscript, preprint, or internal research report, evaluating a research proposal or study protocol, assessing evidence quality behind a claim, or reviewing a thesis chapter or dissertation section.

Review a SKILL.md file for compliance with the agentskills.io standard. Checks YAML frontmatter fields, required sections, line count limits, procedure step format, and registry synchronization. Use when a new skill needs format validation before merge, an existing skill has been modified and requires re-validation, performing a batch audit of all skills in a domain, or reviewing a contributor's skill submission in a pull request.

Review software architecture for coupling, cohesion, SOLID principles, API design, scalability, and technical debt. Covers system-level evaluation, architecture decision record review, and improvement recommendations. Use when evaluating a proposed architecture before implementation, assessing an existing system for scalability or security, reviewing ADRs, performing a technical debt assessment, or evaluating readiness for significant scale-up.

Review user experience and interface design using Nielsen's heuristics, WCAG 2.1 accessibility guidelines, keyboard and screen reader audit, user flow analysis, cognitive load assessment, and form usability evaluation. Use when conducting a usability review before release, assessing WCAG 2.1 accessibility compliance, evaluating user flows for efficiency, reviewing form design, or performing a heuristic evaluation of an existing interface.

Review web design for layout quality, typography, colour usage, spacing, responsive behaviour, brand consistency, and visual hierarchy. Covers design principles evaluation and improvement recommendations. Use when reviewing a design mockup before development, assessing an implemented site for design quality, providing feedback during a design review session, evaluating brand consistency, or checking responsive behaviour across breakpoints.

Escalate blocked scraping campaigns with provider-neutral proxy rotation — decide between datacenter, residential, and mobile pools, integrate rotation with scrapling, configure session stickiness for stateful flows, monitor cost and health, and stay inside legal and ethical boundaries. Use as the next step after `headless-web-scraping` client-side stealth (StealthyFetcher, rate limiting, robots.txt) is insufficient and traffic is legitimate.

Design and execute A/B tests for ML models in production using traffic splitting, statistical significance testing, and canary/shadow deployment strategies. Measure performance differences and make data-driven decisions about model rollout. Use when validating a new model version before full rollout, comparing candidate models trained with different algorithms, measuring business metric impact of model changes, or when regulatory requirements mandate gradual rollout.

Design and execute chaos engineering experiments using Litmus or Chaos Mesh. Test system resilience through controlled fault injection, validate hypothesis-driven tests, and improve failure recovery. Use before major product launches, after architecture changes to validate resilience, during GameDays or disaster recovery drills, to validate assumptions about failure modes, or as part of an SRE maturity program.

Drive a GitHub Copilot (or any bot reviewer) pull-request review to a clean pass without babysitting it: fix each finding in its own commit, reply to the review thread with the fix sha, resolve the thread, re-request the bot, and poll for the async re-review. Covers the thread node-id (PRRT_...) vs comment databaseId distinction, the resolveReviewThread GraphQL mutation, the copilot-pull-request-reviewer[bot] slug, and how to read the bot's verdict (COMMENTED plus a "human review recommended"...

Run the jigsawR test suite via WSL R execution. Supports full suite, filtered by pattern, or single file. Interprets pass/fail/skip counts and identifies failing tests. Never uses --vanilla flag (renv needs .Rprofile for activation). Use after modifying any R source code, after adding a new puzzle type or feature, before committing changes to verify nothing is broken, or when debugging a specific test failure.

Scaffold a new CLI command using Commander.js with options, action handler, three output modes (human-readable, quiet, JSON), and optional ceremony variant. Covers command naming, option design, shared context patterns, error handling, and integration testing. Use when adding a command to an existing Commander.js CLI, designing a new CLI tool from scratch, or standardizing command structure across a multi-command CLI.

Scaffold a new MCP server from tool specifications using the official SDK (TypeScript or Python), including transport configuration, tool handlers, and test harness. Use when you have a tool specification and need a working server, when starting a new MCP server project and want correct structure from the start, when migrating an existing tool integration to the MCP protocol, or when prototyping a tool surface to test with Claude Code before full implementation.

Scaffold a new Next.js application with App Router, TypeScript, and modern defaults. Covers project creation, directory structure, routing setup, and initial configuration. Use when starting a new web application project, creating a React-based frontend with server-side rendering, building a full-stack application with API routes, or setting up a TypeScript web project from scratch.

Scaffold a new Shiny application using golem (production R package), rhino (enterprise), or vanilla (quick prototype) structure. Covers framework selection, project initialization, and first module creation. Use when starting a new interactive web application in R, creating a dashboard or data explorer prototype, setting up a production Shiny app as an R package with golem, or bootstrapping an enterprise Shiny project with rhino.

Scale distributed systems and organizations through colony budding, role differentiation, and growth-triggered architectural transitions. Covers growth phase recognition, age polyethism, fission protocols, inter-colony coordination, and scaling limit detection. Use when a team or system that worked at 10 agents breaks down at 50, when communication overhead grows faster than productive output, when planning a growth phase proactively, or when coordination failures correlate with size such as ...

Screen a proposed trademark for conflicts and distinctiveness before filing. Covers trademark database searches (TMview, WIPO Global Brand Database, USPTO TESS), distinctiveness analysis using the Abercrombie spectrum, likelihood of confusion assessment using DuPont factors and EUIPO relative grounds, common law rights evaluation, and goods/services overlap analysis. Produces a conflict report with a risk matrix. Use before adopting a new brand name, logo, or slogan — distinct from patent pri...

Write Blender Python scripts for procedural modeling, animation, batch operations, and add-on development using advanced bpy API patterns. Use when automating repetitive modeling or animation tasks, generating procedural geometry from algorithms or data, creating batch rendering pipelines with parameter variations, building custom operators or add-ons, or integrating Blender with external data pipelines and APIs.

Search for prior art relevant to a specific invention or patent claim. Covers patent literature, non-patent literature (academic papers, products, open source), defensive publications, and standard-essential patents. Use when evaluating whether an invention is novel and non-obvious before filing, challenging the validity of an existing patent, supporting a freedom-to-operate analysis, documenting a defensive publication, or responding to a patent office action questioning novelty or obviousness.