OSYM kalite skoru + taxonomy coverage + CLT skoru tek raporda
Query expansion, HyDE, and multi-query generation for improved retrieval
Use the rai-sds CLI tool (bundled with this skill) to interact with the Rendered.ai Synthetic Data Studio platform.
Rasa NLU pipeline configuration and training for intent and entity extraction
Randomized benchmarking skill for gate fidelity characterization
Structured root cause analysis for incidents and problems
Read-only exploration, inspection, and reporting without modifications.
This skill should be used when the user asks to "rebase dependabot PRs", "rebase dependabots", "refresh stale dependabot branches", or wants to comment "@dependabot rebase" on…
Construct and verify polynomial-time reductions between computational problems
Refresh the recent-operational cachevalue numbers in a guarded doc (e.g. docs/integrations/fable5-more-usage-for-free.md) when this-week's telemetry has moved on.
Validate the canonical .ai/ YAML and regenerate all
Regenerative braking system design and blending expertise
Use this skill to register an existing file as context in CLAUDE.md so content skills can discover and load it for future work.
Skill for comprehensive regression analysis and modeling
Regulatory Drafting agent for healthcare workflows.
Analyze and organize related work for theoretical CS papers
צ'קליסט לפני קומיט קונפיג, יצירת ZIP, פרסום, או שיתוף קבצים עם גורם חיצוני
This skill should be used when the user asks to "repair an agent", "audit an agent", "fix my agent", "review agent quality", "check if my agent is well-written", "diagnose agent…
This skill should be used when the user asks to "fix my skill" or "audit this skill". Make sure to use this skill whenever the user mentions skill quality, structural issues,…
Skill for assessing feasibility of study replication
This skill should be used when the user says "repo-align", "align the repo", "clean up the repo", "check for drift", "is the repo in good shape", "find contradictions", "what's…
Reputation measurement and benchmarking platform integration
Automotive requirements management and traceability expertise
Skill for systematic requirements capture, decomposition, and traceability
Skill for aerospace requirements verification and validation matrix management
Structure point-by-point referee responses for the sewage-house-prices paper. Classifies each comment (NEW ANALYSIS / CLARIFICATION / REWRITE / DISAGREE / MINOR), produces a…
Resume work from previous session with full context restoration — from NafisRayan/100x-Agent-Toolkit
This skill should be used when the user asks to "check retirement readiness", "retirement projection", "am I saving enough for retirement", "pension gap analysis", "Rentenlücke",…
Generate retrospective formats and analyze improvement actions
Review and promote backlog items to active milestone — from daddia/skills
This skill should be used for CONTEXT.md artifact reviewer — validates that all discussion points are resolved (locked decision or Claude's Discretion), decisions are specific…
This skill should be used for DESIGN.md artifact reviewer — validates design quality against the SB design template: required sections, non-empty screen/component fields, behavior…
This skill should be used for INGESTION_MANIFEST.md artifact reviewer — validates that all source artifacts are listed, statuses are accurate, failed artifacts have corresponding…
This skill should be used when the user says "review my plan", "audit this plan", "check my implementation plan", "is this plan complete", "what's missing from my plan", "validate…
This skill should be used for REQUIREMENTS.md artifact reviewer — validates requirements quality: required sections, REQ-ID format and uniqueness, testable acceptance criteria,…
This skill should be used for SPEC.md artifact reviewer — validates spec quality against the SB spec template: required sections, non-empty overview, user story format, testable…
This skill should be used for UAT.md artifact reviewer — validates that every SPEC.md Acceptance Criterion has a UAT row, evidence is substantive (not 'looks good'), spec-version…
This skill should be used for VERIFICATION.md artifact review -- validates that verification evidence is fresh, substantive, traceable, and sufficient for SB completion claims.
Revit API interface skill for element extraction, creation, and automation
RingLead data quality and deduplication platform
Surface failure modes, missing tests, and unsafe assumptions
RL training for robot control using simulation with sim-to-real transfer
Comprehensive skill for rocket engine design and performance analysis
Hardware abstraction and controller management using ros2_control framework
Maintain /do routing tables when skills or agents change.
Create session retrospective with AI diary and lessons learned. Use when user says "rrr", "retrospective", "wrap up session", "session summary", or at end of work session.
Measurable criteria translating qualitative debate to quantitative scores
Run one exact Ticket through recovery, autonomous work, and its required landing, then write DONE or ESCALATED evidence back to that same Ticket.
This skill should be used when the user asks to "check error handling", "find silent failures", "fix silent errors", "add input checks", "fail fast", "make this safer", "check for…
Skill for structured safety assessment following ARP4761 guidelines
Navigate and understand SAP Customizing (SPRO/IMG). Use when the user asks about customizing settings, SPRO activities, configuration tables, maintenance views, view clusters, or…
Full lifecycle for SAP function groups: check existence, create, re-activate, query PROGDIR state, and delete.
Full-repo SAP CC Go compliance audit against review standards.
Monte Carlo simulations for exit scenarios, return distributions
Manages schema evolution and compatibility across data systems
Build, lint, ingest, compose Drescher-style schemas
Design and implement scoped permission models
A learning system that gets better over time by learning from errors.
Missing state triggers repair, not failure.
LLM-powered semantic analysis of code diffs to detect business-logic trojans