skillsmith

Wires GitHub Actions to pull secrets from 1Password at run time instead of storing long-lived copies in GitHub — using the 1Password load-secrets action with op:// references and a scoped service-account token, so CI reads secrets on demand and 1Password masks them in logs. Use this skill when the user says "load secrets from 1Password in GitHub Actions", "stop pasting secrets into GitHub repo settings", "use a 1Password service account in CI", or wants a workflow that resolves op:// references during a job. Not for local runtime injection (see op-secrets) or an interactive human setup script (see the wizard skill).

Moves a project's secrets out of plaintext and into 1Password secret references (op:// URIs) that resolve at runtime via the op CLI, producing a safe-to-commit .env template and an op run launch path so no real credential ever lands on disk. Use this skill when the user says "use 1Password for my env vars", "replace my .env secrets with op references", "set up op run for this project", "stop storing API keys in plaintext", or wants credentials injected from a 1Password vault at run time. Not for building an interactive service-setup script that captures values from a human (see the wizard skill), or for pushing secrets into GitHub Actions (see op-github-secrets).

Converts Mermaid diagram source into editable tldraw shapes using tldraw's official @tldraw/mermaid package, so a flowchart or graph written as Mermaid text becomes real, movable nodes and arrows on a tldraw canvas rather than a static image. Use this skill when the user says "convert this mermaid to tldraw", "turn my mermaid flowchart into editable tldraw shapes", "import mermaid into tldraw", or has Mermaid source they want as a hand-editable canvas. Not for authoring Mermaid text itself, rendering Mermaid to an image, or building a tldraw file from a prose description (see tldraw-diagram).

Adds motion to a tldraw canvas — animating shape position, rotation, and props over time with easing, animating the camera through a canvas, and authoring durable requestAnimationFrame loops embedded in a tldraw-offline document so the canvas keeps animating whenever it is opened. Use this skill when the user says "animate this tldraw diagram", "make these shapes move", "add an animation to my tldraw canvas", "create a tldraw animation loop", or "animate the camera through my board". Not for generating a static .tldr (see tldraw-diagram), exporting a canvas to an image (see tldraw-export), or CSS / web / video-file animation outside tldraw.

Generates a tldraw canvas file (.tldr / .tldraw JSON) from a described diagram or outline — boxes, arrows, text, frames, and notes positioned on the infinite canvas — so it opens directly in tldraw or tldraw-offline as editable shapes, with no browser or render step. Use this skill when the user says "make me a tldraw diagram", "generate a .tldr file", "turn this architecture into a tldraw whiteboard", "build an editable canvas of this flow", or wants a hand-editable tldraw document rather than a flat image. Not for rendering a canvas to PNG/SVG (that needs a browser — see tldraw-export), converting Mermaid source (see mermaid-to-tldraw), or authoring Mermaid/Graphviz text diagrams.

Renders a tldraw canvas or .tldr file to a static image — SVG, PNG, JPEG, or WebP — by driving tldraw's browser-based export APIs from a headless browser, producing a shareable picture from an editable canvas. Use this skill when the user says "export my tldraw file to PNG", "render this .tldr as an SVG", "turn my tldraw canvas into an image", or needs a flat image out of a tldraw document. Not for generating an editable .tldr from a description (see tldraw-diagram), converting Mermaid (see mermaid-to-tldraw), or exporting from the tldraw desktop app's own File menu.

Converts Mermaid diagram source into editable tldraw shapes using tldraw's official @tldraw/mermaid package, so a flowchart or graph written as Mermaid text becomes real, movable nodes and arrows on a tldraw canvas rather than a static image. Use this skill when the user says "convert this mermaid to tldraw", "turn my mermaid flowchart into editable tldraw shapes", "import mermaid into tldraw", or has Mermaid source they want as a hand-editable canvas. Not for authoring Mermaid text itself, rendering Mermaid to an image, or building a tldraw file from a prose description (see tldraw-diagram).

Wires GitHub Actions to pull secrets from 1Password at run time instead of storing long-lived copies in GitHub — using the 1Password load-secrets action with op:// references and a scoped service-account token, so CI reads secrets on demand and 1Password masks them in logs. Use this skill when the user says "load secrets from 1Password in GitHub Actions", "stop pasting secrets into GitHub repo settings", "use a 1Password service account in CI", or wants a workflow that resolves op:// references during a job. Not for local runtime injection (see op-secrets) or an interactive human setup script (see the wizard skill).

Moves a project's secrets out of plaintext and into 1Password secret references (op:// URIs) that resolve at runtime via the op CLI, producing a safe-to-commit .env template and an op run launch path so no real credential ever lands on disk. Use this skill when the user says "use 1Password for my env vars", "replace my .env secrets with op references", "set up op run for this project", "stop storing API keys in plaintext", or wants credentials injected from a 1Password vault at run time. Not for building an interactive service-setup script that captures values from a human (see the wizard skill), or for pushing secrets into GitHub Actions (see op-github-secrets).

Adds motion to a tldraw canvas — animating shape position, rotation, and props over time with easing, animating the camera through a canvas, and authoring durable requestAnimationFrame loops embedded in a tldraw-offline document so the canvas keeps animating whenever it is opened. Use this skill when the user says "animate this tldraw diagram", "make these shapes move", "add an animation to my tldraw canvas", "create a tldraw animation loop", or "animate the camera through my board". Not for generating a static .tldr (see tldraw-diagram), exporting a canvas to an image (see tldraw-export), or CSS / web / video-file animation outside tldraw.

Generates a tldraw canvas file (.tldr / .tldraw JSON) from a described diagram or outline — boxes, arrows, text, frames, and notes positioned on the infinite canvas — so it opens directly in tldraw or tldraw-offline as editable shapes, with no browser or render step. Use this skill when the user says "make me a tldraw diagram", "generate a .tldr file", "turn this architecture into a tldraw whiteboard", "build an editable canvas of this flow", or wants a hand-editable tldraw document rather than a flat image. Not for rendering a canvas to PNG/SVG (that needs a browser — see tldraw-export), converting Mermaid source (see mermaid-to-tldraw), or authoring Mermaid/Graphviz text diagrams.

Renders a tldraw canvas or .tldr file to a static image — SVG, PNG, JPEG, or WebP — by driving tldraw's browser-based export APIs from a headless browser, producing a shareable picture from an editable canvas. Use this skill when the user says "export my tldraw file to PNG", "render this .tldr as an SVG", "turn my tldraw canvas into an image", or needs a flat image out of a tldraw document. Not for generating an editable .tldr from a description (see tldraw-diagram), converting Mermaid (see mermaid-to-tldraw), or exporting from the tldraw desktop app's own File menu.

Organizes a body of content or a pile of files into a structure a stranger can navigate — deciding what splits into its own file, how pieces nest, what lands up front versus on demand, and how each is named, ordered, and linked. Use this skill when a document or README has grown into one long dump, when a folder or repo has become a flat or "misc"-ridden pile, or when the user says "organize these files", "this doc should be split up", "where should this live", "give this a sensible structure", or "the information architecture is a mess". Not for authoring the visual elements inside a document (see doc-visuals), writing the prose, or reviewing technical correctness.

Organizes a body of content or a pile of files into a structure a stranger can navigate — deciding what splits into its own file, how pieces nest, what lands up front versus on demand, and how each is named, ordered, and linked. Use this skill when a document or README has grown into one long dump, when a folder or repo has become a flat or "misc"-ridden pile, or when the user says "organize these files", "this doc should be split up", "where should this live", "give this a sensible structure", or "the information architecture is a mess". Not for authoring the visual elements inside a document (see doc-visuals), writing the prose, or reviewing technical correctness.

Orchestrates a heavyweight fan-out research harness: decomposes a broad question into independent angles, runs parallel investigators across distinct source modalities, adversarially verifies every load-bearing claim, and synthesizes one cited, dated report. Use this skill when the user says "do deep research on X", "research this thoroughly", "fan out and research", "give me a comprehensive fact-checked report", or asks a broad or contested question that no single search thread can cover. Not for a single volatile fact, a bounded question one investigator covers end to end, or summarizing material the user supplies.

Extracts a brand voice specification from existing copy samples: identifies tone, vocabulary patterns, sentence structure, and anti-patterns, then produces a durable voice spec other content can be checked against. Use this skill when the user says "extract our brand voice", "document our tone of voice", "what is our writing style", "create a voice guide from our copy", "our content sounds inconsistent — define our voice", or provides copy samples and wants a reusable voice standard. Not for rewriting existing content to match a voice, scoring content quality, or creating general style guides for code or documentation.

Researches and generates distinct content angles for a topic: maps what is already saturated, identifies underserved perspectives, and produces a ranked set of angles each with a one-paragraph execution brief. Use this skill when the user says "what should I write about", "find angles for", "research content ideas", "generate topic variants", "what's the best spin on", "help me ideate content", or wants to pick the strongest take before writing. Not for writing the full piece, auditing existing content for quality, or deep academic research.

Expert-panel scoring discipline for marketing content: assembles a panel of 7-10 domain experts, scores each dimension, and iterates toward a 90/100 aggregate in up to 3 rounds. Use this skill when the user says "expert panel this", "score my content", "rate these variants", "run this through the panel", "quality check my copy", or wants rigorous multi-angle criticism before publishing. Not for grammar or spelling checks, SEO keyword audits, or brand voice enforcement.

Designs statistically sound A/B experiments and interprets results: defines hypothesis and primary metric, calculates required sample sizes, flags confounds, and—given results—applies the appropriate significance test and states a clear conclusion. Use this skill when the user says "design an A/B test", "is this result significant", "how long should I run this experiment", "analyze my experiment results", "help me set up a test", or wants to avoid underpowered or inconclusive tests. Not for multi-armed bandits, qualitative usability research, or instrumentation and tracking implementation.

Builds and optimizes cold outbound sequences: researches the prospect segment, drafts multi-touch email cadences with subject line variants, and tightens each touchpoint for reply rate. Use this skill when the user says "build me a cold email sequence", "write cold outreach", "create an outbound cadence", "optimize my cold email", "write a prospecting sequence", or needs a targeted multi-step sequence for a specific role or company type. Not for nurture emails to existing subscribers, event invitations, product announcements, or newsletter copy.

Converts a podcast episode or transcript into a set of platform- ready content assets: a long-form blog post, an email newsletter section, LinkedIn and X posts, and a pull-quote set. Use this skill when the user says "turn my podcast into content", "repurpose this episode", "podcast to blog", "extract clips from this transcript", "create content from my podcast", or wants maximum distribution from one recording. Not for writing podcast scripts from scratch, video editing guidance, or episode transcription.

Produces a keyword-anchored content brief: classifies search intent, identifies what top-ranking content covers and what it misses, and outputs a structured brief with H2 outline, secondary keywords, target length, and a meta description draft. Use this skill when the user says "write an SEO brief for", "create a content brief for the keyword", "what should I cover to rank for", "brief out this topic for SEO", or wants a research-backed structure before writing. Not for writing the full article, auditing existing content for ranking, or keyword research from scratch without a target keyword.

Orchestrates a heavyweight fan-out research harness: decomposes a broad question into independent angles, runs parallel investigators across distinct source modalities, adversarially verifies every load-bearing claim, and synthesizes one cited, dated report. Use this skill when the user says "do deep research on X", "research this thoroughly", "fan out and research", "give me a comprehensive fact-checked report", or asks a broad or contested question that no single search thread can cover. Not for a single volatile fact, a bounded question one investigator covers end to end, or summarizing material the user supplies.

Extracts a brand voice specification from existing copy samples: identifies tone, vocabulary patterns, sentence structure, and anti-patterns, then produces a durable voice spec other content can be checked against. Use this skill when the user says "extract our brand voice", "document our tone of voice", "what is our writing style", "create a voice guide from our copy", "our content sounds inconsistent — define our voice", or provides copy samples and wants a reusable voice standard. Not for rewriting existing content to match a voice, scoring content quality, or creating general style guides for code or documentation.

Researches and generates distinct content angles for a topic: maps what is already saturated, identifies underserved perspectives, and produces a ranked set of angles each with a one-paragraph execution brief. Use this skill when the user says "what should I write about", "find angles for", "research content ideas", "generate topic variants", "what's the best spin on", "help me ideate content", or wants to pick the strongest take before writing. Not for writing the full piece, auditing existing content for quality, or deep academic research.

Expert-panel scoring discipline for marketing content: assembles a panel of 7-10 domain experts, scores each dimension, and iterates toward a 90/100 aggregate in up to 3 rounds. Use this skill when the user says "expert panel this", "score my content", "rate these variants", "run this through the panel", "quality check my copy", or wants rigorous multi-angle criticism before publishing. Not for grammar or spelling checks, SEO keyword audits, or brand voice enforcement.

Designs statistically sound A/B experiments and interprets results: defines hypothesis and primary metric, calculates required sample sizes, flags confounds, and—given results—applies the appropriate significance test and states a clear conclusion. Use this skill when the user says "design an A/B test", "is this result significant", "how long should I run this experiment", "analyze my experiment results", "help me set up a test", or wants to avoid underpowered or inconclusive tests. Not for multi-armed bandits, qualitative usability research, or instrumentation and tracking implementation.

Builds and optimizes cold outbound sequences: researches the prospect segment, drafts multi-touch email cadences with subject line variants, and tightens each touchpoint for reply rate. Use this skill when the user says "build me a cold email sequence", "write cold outreach", "create an outbound cadence", "optimize my cold email", "write a prospecting sequence", or needs a targeted multi-step sequence for a specific role or company type. Not for nurture emails to existing subscribers, event invitations, product announcements, or newsletter copy.

Converts a podcast episode or transcript into a set of platform- ready content assets: a long-form blog post, an email newsletter section, LinkedIn and X posts, and a pull-quote set. Use this skill when the user says "turn my podcast into content", "repurpose this episode", "podcast to blog", "extract clips from this transcript", "create content from my podcast", or wants maximum distribution from one recording. Not for writing podcast scripts from scratch, video editing guidance, or episode transcription.

Produces a keyword-anchored content brief: classifies search intent, identifies what top-ranking content covers and what it misses, and outputs a structured brief with H2 outline, secondary keywords, target length, and a meta description draft. Use this skill when the user says "write an SEO brief for", "create a content brief for the keyword", "what should I cover to rank for", "brief out this topic for SEO", or wants a research-backed structure before writing. Not for writing the full article, auditing existing content for ranking, or keyword research from scratch without a target keyword.

Verifies that a document is self-sufficient for its intended audience — readable and actionable with zero access to the conversation or author. Use this skill before presenting any document someone else will act on (handoffs, work items, runbooks, READMEs, onboarding docs), or when the user asks "will this make sense without me", "check this is self-contained", or "review this for completeness before I send it". Not for correctness review, copyediting, or summarization.

Verifies that a document is self-sufficient for its intended audience — readable and actionable with zero access to the conversation or author. Use this skill before presenting any document someone else will act on (handoffs, work items, runbooks, READMEs, onboarding docs), or when the user asks "will this make sense without me", "check this is self-contained", or "review this for completeness before I send it". Not for correctness review, copyediting, or summarization.

Co-authors a versioned architecture specification through iterative artifact revisions: design invariants, open-decisions register, volatility isolation, and kill/pivot triggers. Use this skill when the user asks to "write an architecture spec", "spec out" a system, "draft a design doc", or turn a technical discussion into a specification. Not for explaining architectural concepts or reviewing an existing document.

Maps an unfamiliar repository fast: deterministic inventory scripts plus parallel subagent scans, synthesized into a path-anchored survey document. Use this skill when the user says "survey this codebase", "help me get oriented in this repo", "map out this project", or has inherited or cloned a codebase and needs orientation. Not for explaining a specific function, finding a specific bug, or reviewing a change.

Crafts the visual layer of technical documents — repository maps, mermaid diagrams, code blocks, and tables — so structure lands at a glance and every element survives its renderer. Use this skill when producing or revising a document that contains a directory tree, an architecture or flow diagram, command examples, or comparison tables, or when the user says "add a diagram", "the repo map is hard to read", "make this README scannable", or "clean up the formatting in this doc". Not for prose editing, verifying a document is self-contained, or reviewing technical correctness.

Co-authors a versioned architecture specification through iterative artifact revisions: design invariants, open-decisions register, volatility isolation, and kill/pivot triggers. Use this skill when the user asks to "write an architecture spec", "spec out" a system, "draft a design doc", or turn a technical discussion into a specification. Not for explaining architectural concepts or reviewing an existing document.

Maps an unfamiliar repository fast: deterministic inventory scripts plus parallel subagent scans, synthesized into a path-anchored survey document. Use this skill when the user says "survey this codebase", "help me get oriented in this repo", "map out this project", or has inherited or cloned a codebase and needs orientation. Not for explaining a specific function, finding a specific bug, or reviewing a change.

Crafts the visual layer of technical documents — repository maps, mermaid diagrams, code blocks, and tables — so structure lands at a glance and every element survives its renderer. Use this skill when producing or revising a document that contains a directory tree, an architecture or flow diagram, command examples, or comparison tables, or when the user says "add a diagram", "the repo map is hard to read", "make this README scannable", or "clean up the formatting in this doc". Not for prose editing, verifying a document is self-contained, or reviewing technical correctness.

Generates an interactive bash wizard that walks a human step by step through a manual procedure — third-party service setup, a one-off migration, an A-to-B state transition — opening each URL, capturing values with confirmation gates, and writing .env entries and GitHub Actions secrets. Use this skill when the user says "make me a setup wizard", "write a script that walks me through setting up" a service, or "turn this runbook into an interactive script". Not for fully automatable work (write a plain script), answering setup questions in chat, or unattended CI automation.

Generates an interactive bash wizard that walks a human step by step through a manual procedure — third-party service setup, a one-off migration, an A-to-B state transition — opening each URL, capturing values with confirmation gates, and writing .env entries and GitHub Actions secrets. Use this skill when the user says "make me a setup wizard", "write a script that walks me through setting up" a service, or "turn this runbook into an interactive script". Not for fully automatable work (write a plain script), answering setup questions in chat, or unattended CI automation.