All authors
Claude Skills by CarlosCaPe
github.com/CarlosCaPe234 skills1 installs304 views
- Market Research FrameworkConsulting-grade market research framework, 12 modules from sizing to entry strategy. Triggers on 'market research', 'TAM/SAM/SOM', 'analisis competitivo', 'segmentacion de clientes', 'SWOT', 'Porter', 'pricing', 'go-to-market'.Votes: 0GitHub stars: 17
- Mcp Stack SetupInstalls and configures an arm's MCP stack while respecting Arm Isolation: cloud MCPs go to user scope, database MCPs to .mcp.json inside the client repo. Triggers on 'setup MCP para X', 'agregar MCP al arm', or when onboarding a new arm.Votes: 0GitHub stars: 17
- Model Routing By ComplexityRoutes work by complexity across the model ladder (mechanical, bulk, build, judgment), vendor-agnostic. Load when fanning out sub-agents or when picking the model override in a Workflow/Agent.Votes: 0GitHub stars: 17
- Multi Object Rename ConvergenceMulti-Object Rename ConvergenceVotes: 0GitHub stars: 17
- Multi Specialist Doc AuditAudit a long technical document for hallucinations and uncited claims by dispatching N specialist agents in parallel, each scoped to a domain. Each returns a severity-tiered table; the orchestrator consolidates and decides surgical-fix vs full-rebuild.Votes: 0GitHub stars: 17
- News Article CurationDaily loop over AI RSS feeds (Willison, OpenAI, DeepMind, arXiv cs.AI): filters the articles that teach something the brain does not know yet. Promotes a keeper to a real skill with /news-promote.Votes: 0GitHub stars: 17
- No History In DocsDocuments carry only current content; git is the version history. Never strikethrough to mark what is done, never old text next to the new one 'for the record', never sections commented out 'for reference'. Applies to every document edit or revision.Votes: 0GitHub stars: 17
- Octorato HarmonyWhen the same value reads 10 in one place and 12 in another, converge both to a canonical one referenced everywhere, never forked. Triggers when editing design tokens, styles or conventions across several files, and on 'converge' or 'armoniza'.Votes: 0GitHub stars: 17
- Octorato IsomorphismOctorato's three anchors (octopus, Linux, tesseract) are one structure shown three times, not three brands glued together. Names the abstraction method. Invoke when explaining why they cohere or when adding a new anchor.Votes: 0GitHub stars: 17
- Octorato SymbolismThe two symbolic anchors of the Octorato framework — the 8 → ∞ (lay the octopus's eight arms sideways and you get the lemniscate, the unbounded) and the Tesseract → 4D (the four-phase paradigm is the 4-dimensional analog of a cube). Invoke when explaining naming rationale, brand identity, the philosophical layer, or when authoring launch comms / talks / podcasts that touch the framework's depth.Votes: 0GitHub stars: 17
- OpenstockOpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for evVotes: 0GitHub stars: 17
- Orchestrated PlanningCreate and execute phased implementation plans with documentation discovery and subagent delegation. Use when asked to plan a feature, execute a multi-step task, or when 2D Delegate determines the task needs structured planning before execution.Votes: 0GitHub stars: 17
- Orphan Detection Fk RolloutOrphan Data Detection & FK RolloutVotes: 0GitHub stars: 17
- Ownership By AuthorshipDetermine code/file ownership by git authorship (log/blame), never by which repo it lives in. Load before assigning work, escalating a fix to "another team", or routing a problem by repo location — the author may be on your own team. Repo location is not ownership.Votes: 0GitHub stars: 17
- Pages Function Checkpoint DebugWhen a Cloudflare Pages Function (or any Worker-style serverless handler) returns a generic 502/500 hiding the actual error, instrument the handler with a `?debug=1` query param + an in-memory checkpoint array that accumulates step markers and gets returned in the response body. Lets you bisect "which step crashed" in 1-2 deploy/retest cycles instead of guessing for hours.Votes: 0GitHub stars: 17
- Peer Review LifecyclePeer Review Lifecycle for Technical DocumentsVotes: 0GitHub stars: 17
- Peripheral Parallel DispatchDecision rule for WHEN to fan work out to N parallel sub-agents/arms vs solve it centrally, and HOW the center reconciles divergent results without becoming the bottleneck. Use before launching multiple agents or a Workflow, or when one context can't hold the whole job.Votes: 0GitHub stars: 17
- Pg Cron Scheduled Maintenancepg_cron Scheduled MaintenanceVotes: 0GitHub stars: 17
- Pg Stat Statements Observabilitypg_stat_statements Query ObservabilityVotes: 0GitHub stars: 17
- Phi Aware Rag IngestionMulti-stage RAG ingestion pipeline for regulated content. Fetch → text-normalize → PHI-screen → chunk → embed → route → store → digest. Default-deny routing (local LLM for tainted, cloud LLM only for allowlisted clean sources). Per-user folder isolation via sha256(email)[:12]. Manual slash-command trigger principle for sensitive workloads.Votes: 0GitHub stars: 17
- Post Check VerificationPost-Check VerificationVotes: 0GitHub stars: 17
- Pr First On Auto Deploy MainOn repos where pushing to main auto-deploys to production, default to PR-based workflow even for self-authored changes — PR adds the safety pass that a direct push skipsVotes: 0GitHub stars: 17
- Pre Merge Qa GateBefore merging a PR that touches production code, dispatch a QA specialist agent against an explicit test/user-case spec for the diff, then merge directly, pinned to the commit it reviewed. Build-passes ≠ correct. The merge is the mechanism, not the gate.Votes: 0GitHub stars: 17
- Primary Key Coverage IdentityPrimary Key Coverage & Identity ColumnsVotes: 0GitHub stars: 17
- Procedure Rebuild Pg Get FunctiondefProcedure Rebuild via pg_get_functiondefVotes: 0GitHub stars: 17
- Production Bug Fix Stored FunctionsProduction Bug Fix in Stored FunctionsVotes: 0GitHub stars: 17
- Progressive Code ExplorationToken-optimized code exploration using index-first, fetch-on-demand principle. Reduces token consumption 4-8x vs reading full files. Use when exploring large codebases, navigating files over 100 lines, or when token budget matters.Votes: 0GitHub stars: 17
- Project Timeline ReportGenerate a "Journey Into [Project]" narrative report analyzing a project's entire development history from git log, CHANGELOG, and release notes. Use when user asks for a timeline report, project history analysis, development journey, full project report, or "what's the story of this project?". No external dependencies.Votes: 0GitHub stars: 17
- Prompt MasterGenerates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.Votes: 0GitHub stars: 17
- Qa Deployment PromptsQA Deployment PromptsVotes: 0GitHub stars: 17
- Querymaster AdxChild skill of querymaster for Azure Data Explorer. ADX uses KQL, NEVER SQL. azure-kusto-data connection with SSO, plus best practices for real-time telemetry. Activates when the resolved engine is ADX.Votes: 0GitHub stars: 17
- Querymaster DatabricksChild skill of querymaster for Databricks. PLACEHOLDER: no workspace or cluster provisioned yet, only the connection template with databricks-sql-connector. Completed once access exists.Votes: 0GitHub stars: 17
- Querymaster PostgresqlChild skill of querymaster for PostgreSQL (standard, Azure Database, Aurora): psycopg2 and Node connection patterns, read-only session and query best practices. Activates when the resolved engine is PostgreSQL.Votes: 0GitHub stars: 17
- Querymaster SnowflakeChild skill of querymaster for Snowflake: connection via Browser SSO, OAuth and service user/password, REST SQL API and warehouse best practices. Activates when the resolved engine is Snowflake.Votes: 0GitHub stars: 17
- Querymaster SqliteChild skill of querymaster for SQLite: local file databases, Optuna storage, analytical sweeps and embedded use, with WAL and foreign_keys PRAGMA. Activates when the resolved engine is SQLite.Votes: 0GitHub stars: 17
- Querymaster SqlserverChild skill of querymaster for SQL Server and Azure SQL (Database, Managed Instance, on-prem): pyodbc connection with an Azure AD token and T-SQL best practices. Activates when the resolved engine is SQL Server.Votes: 0GitHub stars: 17
- QuerymasterMulti-engine master router: takes a natural-language prompt, identifies the engine (PostgreSQL, Snowflake, SQL Server, ADX, SQLite, Databricks), generates the query and runs it with dry-run by default. Triggers when asked to query a database, run SQL or inspect a schema.Votes: 0GitHub stars: 17
- Range Partitioning Growth TablesRange Partitioning for Growth TablesVotes: 0GitHub stars: 17
- Reflexes Over DisciplineWhen a rule or gate is chronically ignored, when designing enforcement for a new policy, or when the operator says a rule keeps failing. Teaches how to convert a passive "mental check" into a mechanical hook (ganglion) that fires without the central brain invoking it.Votes: 0GitHub stars: 17
- Repo Deep LearnDeep analysis of ONE GitHub repo: inventories the code, extracts patterns that could become a skill and writes a report to ~/.claude/knowledge/repo-deep-learn/. Use it when the operator hands you a repo and asks what can be learned from it.Votes: 0GitHub stars: 17
- Repo WatchDaily monitor over a watchlist of GitHub repos: compares the HEAD SHA against the previous snapshot and writes a digest to ~/.claude/knowledge/repo-watch/. Use it to track the pulse of competitors without watching GitHub all day.Votes: 0GitHub stars: 17
- Repomix Codebase PackerPacks a whole repo, local or remote, into a single LLM-optimized file, with Tree-sitter compression (~70% fewer tokens) and secret scanning. For auditing an entire repo or preparing subagent context.Votes: 0GitHub stars: 17
- Research Checklist DisciplineResearch Checklist DisciplineVotes: 0GitHub stars: 17
- Runtime Adaptation Over Source EditDecision rule for WHERE a new behavior or lesson belongs — the runtime layer (skill / memory / config / hook) vs the core source (CLAUDE.md). Default to the runtime layer; touch the core only when the change is a true invariant. Use whenever a lesson, preference, or new capability arrives and you must decide what to edit.Votes: 0GitHub stars: 17
- Sandbox SdkBuild sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.Votes: 0GitHub stars: 17
- Save TranscriptRecovers the COMPLETE transcript of a meeting recording (Microsoft Stream, SharePoint) from its URL, and delivers a clean .txt with provenance, ready to share. Triggers on 'save-transcript', 'baja el transcript', 'saca el transcript de esta junta', 'transcript de <URL>'. For raw audio with no rendered transcript use transcribe.Votes: 0GitHub stars: 17
- Schema As Code Three Layer SyncKeeps the three layers of a schema-as-code project in sync: ER diagram, data dictionary and the declarative SQL. Defines the chain of truth and the diff flow when they drift.Votes: 0GitHub stars: 17
- Schema Row CountsGet exact row counts per table in a given schema — PostgreSQL primary, with notes for other engines. Two-column result: table_name, row_count.Votes: 0GitHub stars: 17
- Schema Separation Orm ControlSchema Separation for ORM/Scaffolding ControlVotes: 0GitHub stars: 17
- Sdd ArchiveSDD step 7. Close a feature: require the converge verdict, update docs/project.md with the feature and any architecture decisions, and write a README in the spec directory. Specs already live in docs/specs/<yyyymmddHHMM>-<feature-name>/ and are not moved; legacy root files are. Use after /sdd-review is complete and the feature is ready to merge.Votes: 0GitHub stars: 17