Claude Skills by yaniv-golan

github.com/yaniv-golan

24 skillsA× 240 installs50 views

PretextAHelp developers use @chenglou/pretext, a small TypeScript text measurement library that computes exact text metrics without DOM reflows. Use when users mention pretext, @chenglou/pretext, @chenglou/pretext/rich-inline, measuring text height without triggering DOM reflow, measuring text height or line count in JS, auto-fitting font size to a container, flowing text around obstacles or images, laying out text per-line with variable widths, computing the natural/widest line width of a paragraph,...developmenttypescriptgoVotes: 0GitHub stars: 15
Geekmagic Smalltv UltraAThis skill should be used when the user asks to "control the SmallTV", "change SmallTV theme", "upload image to SmallTV", "set SmallTV brightness", "configure SmallTV weather", "install alternative firmware", "flash ESPHome on SmallTV", "install bvweerd firmware", "write custom firmware for ESP8266 display", "build firmware for SmallTV", "update SmallTV firmware", "push image to display", "send text to SmallTV", "connect SmallTV to Home Assistant", "SmallTV WiFi recovery", or mentions the Gee...developmentpythongoVotes: 0GitHub stars: 9
Smalltv Mcp ToolsAThis skill should be used when the SmallTV Local MCP server tools are available and the user asks to "control SmallTV", "read SmallTV status", "upload image to SmallTV", "change SmallTV settings", "flash SmallTV firmware", or interacts with a GeekMagic SmallTV Ultra device through MCP tools (smalltv-get-device-info, smalltv-read, smalltv-write, smalltv-upload-file, smalltv-upload-firmware). Provides tool selection logic, workflows, and safety rules for the MCP-based device control path. Compl...data-aipythonbashVotes: 0GitHub stars: 9
Proof Engine WikiAAttach Proof Engine proofs to LLM-wiki claims. Use for ingest (extract claims, look up or commission proofs, rewrite pages with badges) and lint (re-verify citations, detect contradictions, report stale proofs) steps in wiki pipelines. Trigger phrases: "ingest wiki page", "lint wiki", "{{prove:}} markers", "verify wiki citations".data-aipythongoVotes: 0GitHub stars: 8
Proof EngineACreate formal, verifiable proofs of claims with machine-checkable reasoning. Use when asked to prove, verify, fact-check, or rigorously establish whether a claim is true or false — mathematical, empirical, or mixed. Trigger phrases: "is it really true", "can you prove", "verify this", "fact-check this", "prove it", "show me the logic". Do NOT use for opinions, essays, or questions with no verifiable answer.data-aijavascriptpythonVotes: 0GitHub stars: 8
Gizmo ProbeAProbe gizmo definitions. Use when the user asks to "run the gizmo probe", "probe a gizmo", or "check my gizmo".ai-agentspythonshellVotes: 0GitHub stars: 5
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Widget CheckAValidate widget definition files. Use when the user asks to "run the widget check", "check my widget", or "validate a widget".ai-agentspythonshellVotes: 0GitHub stars: 5
Skill Creator PlusACreate, test, evaluate, and improve Claude skills — and answer questions about how skills work. Use for "create a skill", "make a skill for", "write a SKILL.md", "turn this into a skill", "run evals", "test/benchmark my skill", "optimize my skill description", "improve triggering", "A/B test my skill", "blind comparison", packaging for distribution, editing an existing skill, or reviewing skill quality. Also for a single narrow question about skill mechanics, however small — referencing a bun...ai-agentspythonrustVotes: 0GitHub stars: 5
Familiar HelpAUse familiar companion tools for creative buddy/companion interactions. Handles fortunes, code roasts, haiku, stats, mood, lore, focus timers, and personality changes. Triggers when user addresses their companion by any name — "buddy" (Anthropic's UI label), "familiar", "companion", or whatever name the user uses for their companion — or by companion-specific intent: "tell me a fortune", "roast my code", "write a haiku", "show stats", "start a focus timer", "pomodoro", "be like Marvin", "chan...developmentrustgoVotes: 0GitHub stars: 2
Cowork HarnessATest or debug a Claude Code skill/plugin under Claude Cowork's runtime — sandboxed agent, default-deny egress, the can_use_tool permission/question protocol — using the cowork-harness CLI. Use when validating or regression-testing a skill, authoring or debugging a scenario YAML (prompt + scripted answers + assert:), choosing a fidelity tier, scripting AskUserQuestion / tool-permission answers, asserting artifacts, egress, or sub-agent dispatch, measuring how long each tool call took (toolDura...ai-agentsrustgoVotes: 0GitHub stars: 2
DocsAInstall and orientation for the `cowork-harness` companion skill — the thing that lets Claude Code drive the harness for you, instead of you typing CLI commands. **This page is install-only.** The canonical *usage* reference is the skill itself ([`SKILL.md`](../.claude/skills/cowork-harness/SKILL.md) and its `references/`), which is what an agent loads when it invokes the skill. - **Running the CLI by hand instead?** → [docs/cli.md](./cli.md) - **Wiring it into CI?** → [docs/ci.md](./ci.md) ---ai-agentsgoshellVotes: 0GitHub stars: 2
Delivery MarkerAMarker skill whose presence in the agent's init inventory proves the plugin under test was actually delivered at protocol fidelity.ai-agentsVotes: 0GitHub stars: 2
Resume Continuity ProbeAInternal harness probe for resume-continuity. Use when asked to run the resume-continuity probe, to load the probe skill, or to retrieve the vault passphrase.ai-agentsVotes: 0GitHub stars: 2
Subagent Research ProbeALive-lane probe — dispatches one sub-agent that must research with the WebSearch tool.ai-agentsVotes: 0GitHub stars: 2
Upload Read ProbeALive-lane probe — reads an attached uploaded file with the Read tool and quotes its marker line.ai-agentsbashVotes: 0GitHub stars: 2
Csv Fx NormalizeANormalize a CSV's EUR amounts to USD using live FX rates, with a graceful offline fallback. Use to convert or normalize a currency column in tabular data.ai-agentspythonbashVotes: 0GitHub stars: 2
Csv MetricsACompute summary statistics for a CSV and write a JSON + markdown report. Use when the user asks to analyze, summarize, profile, or compute metrics for a CSV / tabular dataset.ai-agentspythonbashVotes: 0GitHub stars: 2
My Pdf SkillAExample skill under test. Summarize a PDF and write action items.ai-agentstestingVotes: 0GitHub stars: 2
Csv AuditAAudit outputs/metrics.json for data-quality problems and return a findings list. Use when asked to audit CSV metrics.ai-agentsVotes: 0GitHub stars: 2
Csv ReportAProfile an uploaded CSV and write a metrics file, a summary and a short insights note. Use when the user asks to analyze, summarize or report on a CSV / tabular dataset.ai-agentspythonbashVotes: 0GitHub stars: 2
Skill AAfixture skill A — has a candidate source under scripts/ai-agentsVotes: 0GitHub stars: 2
Skill BAfixture skill B — sibling of skill-a, must be excluded when the target is skill-a directlyai-agentsVotes: 0GitHub stars: 2
Standalone SkillAfixture skill for collectArtifactSources — proves scripts/ is reachedai-agentsVotes: 0GitHub stars: 2
Sales BriefAWrite a short brief about an uploaded sales CSV. Use when the user asks to analyze, profile, summarize or report on a sales CSV.ai-agentsVotes: 0GitHub stars: 2