Menu
Skills dans ce dépôt
SkillsMP a collecté 606 skills depuis merceralex397-collab/meta-skill-engineering. Ouvrez un skill pour examiner sa source et ses détails.
merceralex397-collab/meta-skill-engineeringAffichage de 40 skills collectés sur 606.
Extract text, tables, and metadata from text-native PDFs using pdfplumber, PyMuPDF (fitz), tabula-py, or camelot with layout-aware parsing and coordinate-based region selection. Use when pulling structured content from PDFs, extracting specific tables, or…
Langue du texte source : anglais
Create PDF documents from data using ReportLab, WeasyPrint, wkhtmltopdf, or Puppeteer — design layouts, apply templates, insert tables and charts, handle pagination, and produce print-ready output. Use when generating invoices, reports, certificates, or any…
Langue du texte source : anglais
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling…
Langue du texte source : anglais
Plan a multi-stop tour route with waypoint optimization, drive/walk time estimation, and POI discovery along the route using OSM data. Covers geocoding, nearest-neighbor and TSP-based ordering, time/distance matrix calculation, and itinerary generation with…
Langue du texte source : anglais
Load a repository's source-of-truth documents in a deterministic order before planning, editing, or reviewing. Use when starting work in an unfamiliar repo, resuming a session, or when the user asks for a repo-aware plan, fix, or review and the authoritative…
Langue du texte source : anglais
Evaluates real estate investment opportunities through comparable sales analysis, financial modeling (cap rate, cash-on-cash, GRM), area profiling, and due diligence checklists. Trigger: "evaluate this property", "run comps", "rental yield", "cap rate…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Set up a WSL2 development environment on Windows including shell configuration, essential tools, Git, SSH keys, Node.js, Python, and cross-platform path management. Use when setting up a new Windows machine for development, configuring WSL2 for the first…
Langue du texte source : anglais
Read-only shell diagnostics to verify environment state, tool versions, ports, processes, and system resources. Trigger — "check environment", "verify tool versions", "what's running on port", "inspect system state", "check disk space", "diagnose environment…
Langue du texte source : anglais
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.
Langue du texte source : anglais
Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI\u2019s video API using the bundled CLI (`scripts/sora.py`), including requests like \u201cgenerate AI video,\u201d \u201cSora,\u201d \u201cvideo remix,\u201d…
Langue du texte source : anglais
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for…
Langue du texte source : anglais
Enforce structured output from LLMs using JSON schema constraints, Pydantic model binding, function calling extraction, and retry/repair loops for malformed responses. Use when an LLM must produce typed JSON, fill a schema, or return structured data that…
Langue du texte source : anglais
Trigger — "delegate research to a sub-agent", "have an agent look this up", "split the research across agents", "gather evidence from multiple sources", "research question decomposition". Skip — task is a single lookup that takes one tool call; task mutates…
Langue du texte source : anglais
Trigger — "run multiple agents in parallel on this", "scatter-gather across files", "map-reduce the codebase", "fan out agents", "coordinate a swarm", "blackboard pattern". Skip — only one agent is needed; task is sequential with hard data dependencies…
Langue du texte source : anglais
Debug processes with strace, ltrace, gdb, and /proc inspection. Use when tracing syscalls, debugging a hanging process, inspecting /proc for fd leaks, or attaching gdb to a running process. Do not use for app-level logging (prefer observability tools) or…
Langue du texte source : anglais
Diagnose and fix common 3D printing failures through systematic symptom analysis. Covers adhesion, stringing, layer shifts, warping, and under/over-extrusion issues. Use when a print fails during the first layer or partway through, finished prints have…
Langue du texte source : anglais
Build terminal user interfaces across languages using TUI frameworks. Use when building a TUI in Python (Textual/Rich), Rust (Ratatui), or evaluating TUI frameworks for a project. Do not use for Go TUIs (prefer bubbletea-go) or simple CLI flag parsing (prefer…
Langue du texte source : anglais
Write clear, comprehensive technical documentation. Use when creating specs, architecture docs, runbooks, or API documentation. Handles technical specifications, system design docs, operational guides, and developer documentation with industry best practices.
Langue du texte source : anglais
Find external skills from public registries, GitHub repos, and official skill collections, then evaluate them for quality, licensing, and fitness for adoption. Use when looking for existing skills before building from scratch, evaluating external skill…
Langue du texte source : anglais
Install a skill package into the local agent client from a GitHub repository, local folder, or archive. Use when the user says "install this skill", "add skill from GitHub", or "list available skills". Do not use for creating new skills (use skill-creator),…
Langue du texte source : anglais
Orchestrate multi-skill pipelines through the CLI. Use when "run the creation pipeline", "execute the improvement workflow", "resume my pipeline", or when chaining multiple skills with decision points. Supports Creation, Improvement, and Library Management…
Langue du texte source : anglais
Bundle one or more completed skill folders into versioned distributable archives with manifests, integrity checksums, and client-specific overlays. Use when a user says "package this skill", "bundle for distribution", "prepare a versioned release", "generate…
Langue du texte source : anglais
Audit and record origin, authorship, evidence basis, license, and trust level for a skill. Use when someone asks "where did this skill come from?", "audit this skill's origin", "document provenance", or when evaluating external skills for adoption or…
Langue du texte source : anglais
Adapt an existing skill to a different repository, stack, team, or project context while preserving the core pattern. Use when asked to "port this skill to Python/Vue/pnpm", "customize this library skill for our project", or "localize this skill for a…
Langue du texte source : anglais
Audit a SKILL.md for structural anti-patterns that reduce routing accuracy, output quality, or maintainability. Use when a user says "check this skill for anti-patterns", "what's wrong with this skill", or "audit this skill before promotion". Also use for…
Langue du texte source : anglais
Compare skill variants head-to-head using pass rate, routing accuracy, and usefulness score to pick a winner. Use when choosing between two skill versions ("which is better?", "did the refinement help?", "benchmark these variants"), measuring whether a change…
Langue du texte source : anglais
Audit a skill library for duplicates, category drift, and discoverability gaps; verify naming conventions, cross-references between SKILL.md files, and description quality across skill directories. Use when: "audit the skill library", "clean up overlapping…
Langue du texte source : anglais
Create new agent skills from scratch and iteratively improve them through test-review-improve cycles. Use this for "create a skill for X", "write a skill that handles Y", "I need a new skill to do Z", "turn this workflow into a skill", or when a repeated task…
Langue du texte source : anglais
Evaluate whether a single skill routes correctly and produces better output than a no-skill baseline — measuring positive trigger rate, negative rejection rate, and output win rate. Use when someone says "is this skill working?", "validate before promoting",…
Langue du texte source : anglais
Improve an existing skill package — tighten routing, sharpen procedure, add or prune support layers, upgrade packaging. Use when the user says "improve this skill", "this skill is weak/vague/bloated", "harden this SKILL.md", or "add evals/references to this…
Langue du texte source : anglais
Manage skill lifecycle states (draft → beta → stable → deprecated → archived) including promotion criteria, deprecation procedures, and maturity audits. Use when a user says "deprecate this skill", "promote this to stable", "retire this", "this is replaced by…
Langue du texte source : anglais
Audit a SKILL.md and its bundled scripts for safety hazards — destructive operations missing confirmation gates, excessive permissions, prompt injection vectors, scope creep, and description-behavior mismatches. Use when a user says "review this skill for…
Langue du texte source : anglais
Build trigger tests and behavior tests for a skill's evals/ directory. Use when "create tests for this skill", "set up evals", "build a test harness", a new skill needs test coverage, or a skill lacks an evals/ directory. Do not use for running existing tests…
Langue du texte source : anglais
Fix skill routing by rewriting the description and trigger boundaries so the right skill fires on the right inputs. Use when "this skill never fires", "wrong skill fired", "fix the triggers", "why isn't this skill being used?", or when a skill's description…
Langue du texte source : anglais
Split a broad skill into focused variants along stack, platform, scope, or domain axes. Use when "this skill does too much", "split this skill", "create variants for X and Y", a skill has disjoint "For X" / "For Y" sections, triggers on unrelated inputs, or…
Langue du texte source : anglais
Adapt an existing skill to a different repository, stack, team, or project context while preserving the core pattern. Use when asked to "port this skill to Python/Vue/pnpm", "customize this library skill for our project", or "localize this skill for a…
Langue du texte source : anglais
Compare skill variants head-to-head using pass rate, token usage, and win rate to pick a winner. Use when choosing between two skill versions ("which is better?", "did the refinement help?", "benchmark these variants"), measuring whether a change improved…
Langue du texte source : anglais
Create new agent skills from scratch and iteratively improve them through test-review-improve cycles. Use this for "create a skill for X", "write a skill that handles Y", "I need a new skill to do Z", "turn this workflow into a skill", or when a repeated task…
Langue du texte source : anglais