create-hardware-specBuild a structured hardware specification and BOM for a project. Walks the user through goals, constraints, and functional requirements, then produces a markdown spec plus a structured BOM (parts, quantities, rationale) saved into the project directory.generate-budget-approximationEstimate the total cost of a project's BOM. Reads bom.json from a project, applies typical price ranges per vendor (informed by the user's preferred suppliers and location), and produces low/mid/high cost envelopes plus shipping considerations.generate-pcb-designProduce a PCB design starting point from a project's BOM and wiring spec — schematic netlist, board stack-up and layout guidance, and ESP32-specific rules (antenna keep-out, strapping pins, decoupling). Output is KiCad/EasyEDA-ready design input, not finished…generate-wiring-diagram-specProduce a textual wiring specification — pin map, connection table, and power distribution — suitable for handoff to a diagram tool (Fritzing, KiCad, Wokwi, draw.io) or for direct use during breadboarding. Not a graphical diagram itself.research-componentsLive web research for a project's components. Starting from a defined objective (integrations, radios, sensors) or an existing BOM, searches the web and the user's preferred marketplaces (AliExpress, Adafruit, Mouser, etc.) for real candidate parts with…suggest-sourcing-optionsRecommend specific vendors for each BOM line, biased by the user's location and preferred suppliers. Produces a sourcing plan with vendor, expected lead time, and trade-offs (price vs. authenticity vs. speed).bom-from-project-ideaStart from a free-form project description and work backwards to a candidate BOM. Lighter-weight than create-hardware-spec — used when the user wants a quick parts list to evaluate feasibility before committing to a full spec.check-inventoryQuery a user-defined MCP-connected inventory system to check live stock for a project's BOM. Use this when the user has a real inventory backend (warehouse management system, parts database, home-lab inventory) wired up via MCP, rather than a static on-hand…
仓库浏览
danielrosehill · 仓库与代表性 skills - 第 2 页
按仓库查看 192 个 GitHub 仓库中的 1,248 个已收集 skills。
denoise-deepfilterUse when the user wants to denoise audio using modern ML-based filtering. DeepFilterNet produces cleaner speech than traditional FFT/rnnoise methods — no watery/hollow artifacts. Wraps `deepFilter` binary for podcast/voice cleanup.extract-vocalsUse when the user wants to quickly extract vocals (or isolated instrumentals) from a song or recording. Convenience wrapper around 2-stem `demucs` mode. Fastest stem separation for the common case.separate-stemsUse when the user wants to separate an audio file into vocal and instrumental stems (or 6-stem separation). Wraps `demucs` for isolating drums, bass, vocals, and other instruments. Common uses — karaoke prep, podcast remixing, music production.detect-cuesUse when the user wants automatic cue/chapter timestamps based on acoustic features (onsets, energy spikes, silence boundaries, beat positions, pitch changes) rather than transcript content. Wraps the `aubio` CLI tools to emit a sidecar JSON with timestamps…install-depsProvision the plugin's tools — system binaries via the host package manager, all Python tools into a plugin-owned uv venv at <data-dir>/venv/. Idempotent doctor — run before onboard or any time a command reports a missing dep. Never touches system Python or…time-stretchUse when the user wants to speed up or slow down audio while preserving pitch — podcast tightening (1.05–1.15× is common), slow-talker correction, fitting an episode to a target duration, or de-chipmunking a sped-up source. Wraps `rubberband-cli` for…silence-cut-edlUse when the user wants the silence-cut decisions as an editable timeline (Kdenlive / Final Cut Pro / Premiere / Shotcut XML) rather than a baked audio file, so they can review and adjust cuts in a video/audio editor before committing. Wraps `auto-editor`…silence-cutUse when the user wants to remove silent sections from a recording with real cuts (not just collapsed gaps), producing a tightened audio file. Wraps `auto-editor` for podcast/voice cleanup. Distinct from `truncate-silence` — that collapses internal silences…
data-reportingProduce a parametric PDF report describing a dataset — size, schema, distributions, key statistics, and findings from other skills — compiled via Typst. Use when the user wants a shareable, print-ready document about their data, not a one-off markdown summary.sample-sizeDescribe and assess the sample size of a dataset — not just row count, but effective sample size per question the user wants to answer. Flags underpowered segments, imbalanced classes, small-n group cells, and gives a concrete "you can / cannot reliably claim…standard-deviationCompute and interpret standard deviation (and related spread measures — variance, IQR, MAD, CV) for numeric columns in a dataset. Handles sample vs. population formulas, grouped/stratified computation, and flags columns where SD is misleading (heavy skew,…data-enrichmentIdentify what the user is trying to analyse, diagnose gaps in the current dataset, propose external data sources that could fill them, then plan and implement the enrichment. Use when the dataset alone can't answer the user's question and extra context…forensic-sweepScan a dataset for signs that it has been pre-cleaned, normalised, imputed, smoothed, deduplicated, or otherwise processed before the user received it — data that is "suspiciously clean". Flag findings so the user knows whether they're analysing raw reality…multivariate-analysisTest relationships among three or more variables simultaneously — partial correlations, controlled effects, multicollinearity, interaction terms, and dimensionality reduction. Use when a pairwise correlation sweep isn't enough and the user wants to know how…setup-data-workspaceSet up a "talk to your data" workspace in the current repo — discover local data files, load them into a DuckDB database, and append a CLAUDE.md block telling future Claude sessions how to query it. Use when the user wants to make a repo's data…type-consistency-sweepScan one or more datasets for data-type inconsistencies that would block analysis or relational/graph database loading — mixed types within a column, the same logical field typed differently across files, string-encoded numbers/dates, inconsistent null…
categorize-corpusAssign each document in a corpus to one of N user-defined categories. Use when the user has a fixed taxonomy (e.g. 10-20 labels) and wants every note/document routed into exactly one (or top-k) of them. Supports zero-shot classifiers, local LLMs, and cloud…choose-approachDecide whether a corpus analysis task should use classical NLP, a local LLM, or a cloud LLM (OpenRouter) given corpus size, task complexity, and cost tolerance. Use first, before any other skill in this plugin, especially when the corpus is large (thousands+…correlation-analysisCorrelate metadata (timestamps, tags, source, author) with content features (topics, entities, length, sentiment) to surface non-obvious patterns. Use when the user asks "does X correlate with Y in my corpus" or wants to discover relationships between…define-taxonomyBuild a multi-level taxonomy (categories → tags → sub-categories) from a text corpus. Use when the user wants more than a flat category list — e.g. "give me a hierarchical taxonomy for my tech notes" or "categories, tags, and sub-tags for this corpus of…ner-extractionExtract named entities (people, places, organizations, dates, products) from a text corpus. Use when the user wants to know "who and where is mentioned" or needs a list of entities for downstream indexing, linking, or trend analysis.parametric-analysisCompute summary statistics over a text corpus — average word length, words/doc, sentences/doc, lexical diversity, readability scores, token length distributions. Use when the user wants a quantitative description of the corpus shape rather than its content.recommend-toolsRecommend well-maintained external libraries and tools for text corpus analysis beyond what this plugin ships — classical NLP, topic modeling, corpus indexing, aspect-based sentiment, multilingual analysis. Use when a task calls for something this plugin…setup-local-llmAudit what local LLM runtimes are installed (Ollama, llama.cpp, vLLM, LM Studio) and suggest/install a model suitable for corpus analysis tasks — classification, labeling, summarization. Use when a skill in this plugin wants a local-LLM lane but nothing is…
create-workspaceCreate a private GitHub repository from the Spec-Led-Certification template and clone it, as the durable home for one certification search. Use when the user wants the search backed by a repo rather than a local folder — "make a repo for this", "set up a…scaffold-workspaceCreate the directory structure a spec-led certification search writes into — profile/, scorecard/, research/, report/ — by copying the plugin's bundled template into the working directory. Idempotent and non-destructive: it never overwrites a file that…rerun-searchSecond and later runs — archive the previous run, confirm the profile is still current, re-survey the market and report what changed since last time. Use when the intake is already on file and the user wants to know whether the market has moved, or whether an…spec-led-certificationEntry point for the whole workflow — reads the state on disk and routes to start-search, rerun-search or update-profile. Use when the user wants a certification decision and it is not obvious which of the three they need, or when they do not know what state…start-searchFirst run — onboard someone who has never done this, take them through all five intake interviews, freeze the scorecard, survey the market and produce the recommendation. Use when profile/ is unfilled, when the user is starting a search for a new subject, or…update-profileChange what is stored about the user — their position, learning preferences, objectives, budget or subject — without running a search. Re-interviews only the files that changed, re-dates them, and marks the scorecard stale so the next run rebuilds it. Use…benchmark-meEstablish where the user actually stands today against the capability areas in the spec, from evidence they point at — repos, site, CV, published work — rather than self-report alone. Writes profile/benchmark.md. Second stage of the spec-led certification…build-scorecardDerive weighted, anchored scoring criteria and hard filters from the completed profile, then freeze them before any credential is researched. Writes scorecard/criteria.csv, scorecard/filters.csv and scorecard/methodology.md. The pivot of the spec-led…
vscode-hereOpen VS Code at the current working directory. Use when the user asks to "open in vs code", "open in vscode", "vscode here", or "code .".claude-and-shellLaunch a single Konsole window at a target directory split left/right — left pane runs Claude Code, right pane is a raw shell at the same path (no Claude). Use when the user asks for "claude with a terminal", "claude + shell", "claude and a free konsole",…claude-gridLaunch a single Konsole window at a given path containing 2 or 4 split panes, each running a fresh Claude Code session in that path. Use when the user asks for a "claude grid", "2-pane claude", "4-pane claude", "split konsole with claudes", "quad claude", or…sideclaudeCapture a side-task/idea that surfaced mid-thread, save it as a plan file in the repo, and spawn a new Konsole running a fresh Claude Code session at the current cwd with instructions to execute the plan. Use when the user says "sideclaude", "side claude",…clipboard-handoverShort YAML handover displayed in chat and copied to clipboard. No files, no spawn. Use when user says "clipboard handover", "copy handover", "handover to clipboard".handoverEnd-of-session menu — wrap up this Claude session. Logging, YAML handovers, spawning new instances, clipboard. Triggers on "handover", "end session", "wrap up", "hand off", "session transfer".handover-with-tasksWrite a handover document that includes an open task list for the next agent. Use when switching sessions mid-way through a multi-task workload, not just a single in-progress job. Triggers on phrases like "handover with tasks", "task handover", "hand off the…new-claude-atOpen a new Konsole window running a fresh Claude Code CLI session at an arbitrary path. Use when the user asks for "a new claude at <path>", "claude in <other repo>", "spawn claude over in <dir>", or similar. Unlike `new-claude-here`, this takes an explicit…
search-aliexpressSearch AliExpress as an Israel buyer — ILS pricing, Choice-first, with free-shipping / 4★ / ship-from filters, driven in the user's own Chrome.selector-verificationPlugin maintenance — probe the live AliExpress DOM against every selector documented in reference/selectors.md and report which still work. Run when a skill starts returning empty results, or periodically. Not a shopping skill; never invoke it to find or buy…cart-vat-nudgeTrack a running AliExpress cart total in USD and nudge as it nears or crosses Israel's $75 VAT-free de-minimis, where ~18% VAT begins.check-il-compatibilityCheck whether an AliExpress product will actually work — and be importable — in Israel. Plug type (Type H), 230V/50Hz mains, dual-voltage vs 110V-only, wireless bands, and restricted-import categories, read off the listing's own specs.export-cartRead the live AliExpress cart into structured JSON/CSV — items, SKUs, quantities, per-unit and crossed-out prices, sellers, shipping — ready to feed cart-vat-nudge.fetch-listingParse one AliExpress listing into a structured summary with the Israel landed cost — price, ship-to-IL fee, lead time, ratings, seller trust signals, VAT band.find-under-75Hunt AliExpress for items that land in Israel tax-free — item price ≤ $70, free shipping to IL, verified landed cost (item + shipping) under the $75 de-minimis. Search, price ceiling, shipping verification and threshold check in one pass.free-shipping-onlySearch AliExpress showing only listings with free shipping to Israel (server-side freeshipping filter). Thin preset over search-aliexpress.
adguard-configureOne-time setup for AdGuard Home integration. Captures the AdGuard Home base URL, credentials, and target blocklist filename, validates connectivity, and persists to corpus/config.json. Use before adguard-push.adguard-pushPush the user's accumulated tracking-pixel + ad-tracker domains from the SpamHole corpus into a self-hosted AdGuard Home instance, using the credentials configured by adguard-configure. Network-layer block — every device on the LAN benefits, not just one…analyse-emailRun the full SpamHole analysis pipeline on a single email — semantic spam reasoning, tracking-pixel detection, sender block, processed-emails log, markdown report. Use when the user wants a deep dive on one email rather than the lighter capture-spam-sample…block-senderCreate a server-side Gmail filter that auto-trashes (or labels + archives) future mail from a sender, via an available email MCP. Falls back to recording the block in the local sender-blocklist.json if no MCP is wired up. Use when the user says "block this…bulk-analyseProcess every unanalysed .eml file in the user's corpus inputs/emails/ directory through the full analyse-email pipeline. Skips files that already have a corresponding analysis report. Use when the user has dropped many .eml files into the corpus at once.capture-spam-sampleCapture an unsolicited email into the user's SpamHole corpus, ask why it's spam (what pattern it represents), copy the raw email into the corpus, suggest a filter pattern, suggest system-prompt tuning to catch similar emails, optionally push a server-side…contribute-blocklistStrip per-recipient identifiers from the user's tracking inventories and prepare a redacted contribution suitable for opening a PR against collaborative public anti-tracking lists (EasyPrivacy, hagezi, oisd, Pi-hole community, AdGuard's tracker filter).…draft-unsubscribe-replyDraft (and optionally send) a manual unsubscribe-request reply to a spam sender — used when the email has no working List-Unsubscribe header or the user wants to make the request human-to-human. Threads on the original message via the available email MCP. Use…
new-workspaceProvision a new purchasing workspace as a standalone repo — scaffold, personalised CLAUDE.md, workspace manifest with a stable id, and a private GitHub repo by default.procurement-reportRender a dated, never-overwritten report (markdown + PDF) from whichever spec, conformance and pricing artefacts a workspace holds.technical-sourcingRun a technical purchasing investigation end to end — spec as code, manufacturer documentation, part-number equivalence across regions, conformance evaluation, bill of materials, RFQ. Use when a purchase turns on specifications rather than on price or…workspace-folderAdd a purchase-decision folder inside an existing procurement repo instead of a standalone repo — same scaffold and manifest, never a nested git. The repo sibling is new-workspace.market-evaluatorRank the candidates that survived conformance evaluation and produce a purchase recommendation — a top three in order, each with product, price and where to actually buy it, followed by category picks such as best budget, best overall and best for features.…spec-variantsRun several parallel either/or versions of one spec — a budget bar and a premium bar for the same purchase — each independently versioned, and diff what actually differs between them. Use when the answer is "it depends how much we want to spend", when a…bom-buildBuild a bill of materials — a shopping list written as requirements rather than as products, with stable line ids, quantities, substitution rules and optional references to a spec. Use when a purchase is several items rather than one, when kitting out a space…evaluation-matrixGenerate the evaluation-criteria brief from a spec, judge candidates against it one requirement at a time, and render the conformance matrix. Use when candidates have to be checked against a defined requirement set rather than ranked, when several candidates…
amazon-address-bookRead and change the delivery addresses on the user's signed-in Amazon account - list the address book, correct a wrong street or postcode, add a new address, and change which one is the default ship-to. Use when the user says fix my Amazon address, add my new…amazon-delivery-checkGet the delivery facts that exist only inside the user's signed-in Amazon session - same-day and overnight availability, the Prime basket minimum, the order-within cutoff, coupons and Prime-exclusive pricing - plus a check that the Prime membership is still…amazon-order-cancelCancel an order, or individual items within an order, on the user's signed-in Amazon account - find the order, confirm exactly what is about to be cancelled, submit the cancellation and verify it actually took effect against the order itself. Use when the…amazon-order-historyQuery the user's Amazon order history from their signed-in session - when something was bought, what it cost, what is arriving this week, whether an ASIN has been ordered before, and what the current status of an order is. Use when the user asks have I bought…amazon-fetch-routeChoose the right route for an Amazon.com fetch and prove it actually worked. Use before the first Amazon fetch in a session, when an Amazon page returns an error or an empty-looking result, when a delivery date needs to be trusted, or when a previous Amazon…amazon-listing-checkVerify price, stock, delivery options and their costs, rating, seller and specifications for one or more Amazon ASINs by reading the product page itself rather than a search result. Use when the user names a specific Amazon product or link, asks what…amazon-open-asinOpen one or more Amazon ASINs in the user's own browser, on the right regional storefront, as clean canonical /dp/ URLs with the tracking stripped. Use when the user says open, show me, pull up, or let me look at an Amazon product, or wants to finish a…amazon-searchRun a filtered Amazon US search inside the user's signed-in browser and return a decision table with per-card real delivery dates, Prime-exclusive pricing and brand facets. Use when the answer needs facts that only a signed-in session renders — what arrives…
anything-interestingSurface anything genuinely interesting in a report — original ideas, noteworthy statistics, strong opinions — or confirm there's nothing worth flagging. Use when the user wants a signal-finder pass without committing to a full read or extraction.comprehensive-analysisFull critical analysis of a report — read/skim/skip verdict, opinionated executive summary, quantitative analysis, case-study deep dive, key quotes, synthesis, and metadata. Use when the user wants the complete report-analyst treatment in one bundle, saved to…exec-summaryGenerate a critical executive summary of a report — bottom-line findings plus an evaluation of credibility, originality, and methodology. Use when the user wants a one-page brief that doubles as a skeptical review, not a polite recap.export-analysisRender a markdown report-analyst output to a styled PDF via Typst (preferred) or pandoc (fallback). Use when the user wants the analysis bundle as a shareable document rather than raw markdown.extract-case-studiesPull case studies from a report and group them by what they demonstrate. Use when the user wants the report's examples extracted as a reference, including company/entity context, the point each case supports, and significant quotes.extract-key-snippetsPull memorable, citable passages from a report — soundbites, well-summarised key issues, sharp findings worth quoting on social media or in further writing. Use when the user wants pull-quotes rather than analysis.extract-main-argumentsPull the report's main arguments — core thesis, supporting arguments, evidence strength, counterarguments — into a structured table. Use when the user wants to quickly understand what the authors are trying to prove and how convincingly.extract-noteworthy-findingsPull only the unexpected, contradictory, or paradigm-shifting findings from a report — skipping confirmatory and well-known results. Use when the user wants the surprises rather than the executive summary.
bag-evidenceUse when packaging evidence into a BagIt-compliant archival container.capture-webpageUse when archiving a URL as a self-contained offline HTML file with hash verification.environment-checkUse when assessing whether forensics CLI tools are installed and available.hash-evidenceUse when computing cryptographic hashes (SHA-256, BLAKE3) for files or directories.inspect-metadataUse when extracting and analyzing metadata (EXIF, MediaInfo) from files.install-dependenciesUse when environment-check reports missing tools and you need to install them.onboardUse when setting up the digital-evidence plugin for the first time.reference-lookupUse when searching vendored Digital-Evidence-Toolkit guidance for tool recommendations and legal-procedural context.