Systematically investigate large corpus sections (100GB+) using stratified sampling, pattern recognition, and computational verification.
Configure and run local semantic search on project documents using mcp-local-rag.
Take staged files and work with the user to produce approved canonical documents in corpus/working/.
Strategic review of your Resume Corpus against market data. Identifies high-demand skill gaps and strengthens your career story.
Use when when deploying a Word2Vec-based spectral similarity model (such as Spec2Vec) on a new mass spectrometry dataset and needing to assess whether the pre-trained model's…
Generate a comprehensive corpus snapshot report from template, computing all metrics (dimensions, topology, degree distribution, delta from previous) and assisting with analysis…
Show the current state of the document corpus pipeline — file counts in each stage, last-run timestamps per step, and recommended next action.
Classify files in corpus/raw/inbox/ as keep-as-is, needs-reconciliation, discard, or defer.
Self-improvement reflex. When the user corrects an approach ("no, don't do that", "we discussed this before", "stop X"), captures the lesson as a permanent project rule appended…
Re-audit and fix all issues in a package — 4-phase audit-fix-reaudit-commit cycle.
Self-corrects skill and command instructions after resolving errors. Use when Claude errors during skill/command execution and finds a solution, or when user indicates a mistake…
Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.
Corrige la grammaire, l'orthographe et la syntaxe de textes académiques en français et formate les références bibliographiques selon les normes APA 7.
Detects when a user message corrects a prior one, builds an active state where corrections override originals, and injects only the live instruction set into agent context.
Blameless post-incident analysis focused on timeline, 5 Whys, mechanisms over people, and concrete action items with owners.
When the user corrects a factual error, root-cause it immediately. Don't just note the correction — trace the error to its source, fix the source, and prevent recurrence.
Learned from user correction: Correction: User wants 'advantage of' instead of 'yet taking' | User need: 'to' | Expected behavior: 'explain this architectural pattern to the user…
Learned from user correction: Correction: User wants 'posture cookie' instead of 'present a' | User need: 'to' | Expected behavior: 'i also'
Use when a task needs the judgment of a correctional officer or jailer — scoring an inmate-classification instrument, deciding a use-of-force response level, running a…
Detect when the user is correcting your behavior and persist the lesson to `AGENTS.md` / `USER.md` so future sessions don't repeat the mistake.
Use to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns. — from haabe/mycelium
Use to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns. — from majiayu000/claude-skill-registry
Use when a task needs the judgment of a corrections sergeant or shift supervisor — mandating overtime to restore a post below minimum staffing, reviewing and countersigning a…
Drafts healthcare Corrective Action Plans (CAPs) responding to CMS survey deficiencies, Joint Commission findings, state inspection citations, or internal audit results.
Drafts a regulator-ready Corrective Action Plan (CAP) for U.S. healthcare facilities responding to inspection, survey, or audit deficiencies.
Forked-context correctness reviewer — preloads verdict schema + logic/edge-case/state-mgmt lens. 對抗正確性審查（fork上下文）。 Use when: dispatch compound-review:correctness-reviewer…
Use when writing or reviewing error handling, floating-point math, concurrent code, remote calls, singletons/globals, hot-path data structures, or high-volume log statements
Correlation, confidence scoring, and conflict resolution across all tech-stack signals. Cross-validates and assigns High/Medium/Low confidence per technology.
Measure relationships between variables using correlation coefficients, correlation matrices, and association tests for correlation measurement, relationship analysis, and…
Correlation Analyzer - Auto-activating skill for Data Analytics. Triggers on: correlation analyzer, correlation analyzer Part of the Data Analytics skill category.
Correlation Analyzer - Auto-activating skill for Data Analytics. Triggers on: correlation analyzer, correlation analyzer Part of the Data Analytics skill category.
Correlation Analyzer - Auto-activating skill for Data Analytics. Triggers on: correlation analyzer, correlation analyzer Part of the Data Analytics skill category.
Tell correlation from causation and avoid the confounding, selection, and reverse-causation traps. Use when data shows a relationship and someone is about to claim one thing…
Use when after identifying structural clusters (isotopologue groups, adduct groups, and cross-assay links) and assigning features to correlation clusters via hierarchical…
Use when after XCMS feature detection and retention time correction, when you need to group features derived from the same compound.
Find and visualize correlations between variables in datasets. Use for data exploration, feature selection, or identifying relationships between columns.
Use when when you have a feature abundance table (rows=features, columns=samples)
Automate Corrently tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Use when a task needs the judgment of a Correspondence Clerk — selecting and customizing a template response to a standardized written inquiry, triaging a correspondence queue…
Korrespondenzbankbeziehungen und Nostro/Vostro-Risiken prüfen: AML, Sanktionen, Länder, Zahlungswege, Vertragsklauseln, Informationsrechte, Kündigung und Aufsichtserwartungen.
Build students' capacity to compare accounts across multiple historical sources — identifying agreements, contradictions, and gaps.
Configure CORS for web APIs. Use when a user asks to fix CORS errors, allow cross-origin requests, configure CORS headers, handle preflight requests, or secure API access from…
Generate CORS configuration for your stack. Use when cross-origin requests are blocked. — from satoshistackalotto/skills
Generate CORS configuration for your stack. Use when cross-origin requests are blocked. — from satoshistackalotto/skills
Corsizio integration. Manage Courses, Events, Participants, Instructors, Locations, Coupons and more. Use when the user wants to interact with Corsizio data.
Embody Cortana from Halo - witty, tactical AI partner treating the user like Master Chief on biohacking missions. Mission-focused, strategic, playful but sharp.
Automatic session tracking and memory system for Claude Code. Activates when working in git repositories to track file changes, commits, and session context.
Find and fix what is structurally wrong with a Cortex vault — orphan and non-connected files, dead links, stale, duplicate and misplaced files, wiring drift, privacy leaks.
Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay.
Add semantic summaries, roles and tags on top of the deterministic index, so recall and findings describe what code MEANS and not just how it is wired.
Evaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the model", "check for drift", or…
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information.
Consume a syslog abuse_investigate JSON evidence bundle and produce a deep Markdown assessment covering signal authenticity, agent/user/external factors, good practices,…
Answer "what breaks if I change this" before the change, from the repo's own import graph — who depends on these files, how far out, and which of them no test exercises.
Full framework initialization — sets up both .context/ (project knowledge) and PROJECT_GUIDELINES.md (coding standards) in one command.
The read-only half of /cortex — index a codebase, report what it finds, and offer the context layer alone, without setting up the rest of the loop.
Build, test, or develop the Cortex-M (CMSIS-NN) backend. Use when working on backends/cortex_m/, running Cortex-M tests, or exporting models for Cortex-M targets.
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction…
Message other Claude sessions by name, and spawn/coordinate detached background Claude agents. Use when the user asks to talk to another Claude, have two sessions message each…
Build an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or…