Referenten: Zahlen, Schwellenwerte und Berechnung im Legistik (Gesetzgebungstechnik): 1. Welche Rolle hat die fragende Person und wer ist Gegenüber? 2.
Erstellt einen vollstaendigen Referentenentwurf des Bundes oder Landes. Format gemaess HdR. Deckblatt Bezeichnung Inhaltsuebersicht A Problem und Ziel B Loesung C Alternativen D…
Solo-Selbstständige: prüft Referenznutzung, Logo, Case Study und Geheimhaltung; mit Abfrage von Tätigkeit, Status, Belegen, Fristen, Geldfolge und konkretem nächstem…
Klausel-Spezialskill für Referenznennung: prüft, redlined und entwirft die Klausel mit Risikoampel, Verbraucher-/B2B-Unterscheidung und praxistauglicher Ersatzfassung.
ReferralHero integration. Manage data, records, and automate workflows. Use when the user wants to interact with ReferralHero data.
ReferralRock integration. Manage data, records, and automate workflows. Use when the user wants to interact with ReferralRock data.
When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.
Reference collection of official Anthropic skills for learning and best practices study.
Refersion integration. Manage Affiliates, Products, Offers. Use when the user wants to interact with Refersion data.
Compute the month a refinance actually starts saving money — payment delta, breakeven month, and total interest on both paths including the term-reset trap.
Leasingrefinanzierung: Forderungsabtretung, ABS-Strukturen, True Sale, Servicing, stille Abtretung und Schuldnerschutz nach § 407 BGB im Leasingrecht.
Refine a GitHub issue with extra validation and triage detail; use for high-impact issues or cross-team work.
Reframes implementation descriptions into outcome statements. Invoked by launch commands during outcome refinement.
Refines a v1 project plan into agent-ready tasks with clear context, implementation steps, and validation criteria. Use after /plan-project has produced a v1 plan.
Deep plan refinement that writes an HTML spec with all unanswered questions collected at the bottom for batch answers
Transforms vague prompts into precise, structured AI instructions. Use when asked to refine, improve, or sharpen a prompt, do prompt engineering, write a system prompt, o — from…
Iteratively review and revise a prompt plan until no new findings survive evaluation. Runs /review-prompt-plan, /evaluate-findings, /apply-findings, then re-runs itself until…
Transforms any rough, vague, or underperforming prompt into a clear, structured, high-performing AI instruction.
Refine vague or unclear prompts into precise, actionable instructions. Use when user asks to clarify or improve instructions or when input is vague.
Iteratively refine Discovery artefacts (plans, epics, stories) when feedback, ambiguity, or uncertainty is detected.
Analyze and refine existing Claude Code Skills for conciseness and effectiveness. Use when asked to "review", "refine", "improve", "optimize" Skills, or when user mentions "skill…
Use when distilling, refining, or reviewing accumulated skill feedback — "refine skills", "distill feedback", "promote feedback", "compound my skills".
Refine a task into a complete, autonomous-ready spec with SMART acceptance criteria, technical context, and AI-readiness checks.
Refine a Jira/Linear ticket before planning — 'refine ticket', 'tighten AC on PROJ-123', 'ist das Ticket klar?' — rewritten ticket, Top-5 risks, persona voices, sub-skills…
Carefully curated, modern minimal style with elegant serif typography and understated, sophisticated palettes. — from bergside/awesome-design-skills
Iteratively enriches incomplete JIRA Epics into estimation-ready, technically-validated specs. Five modes: batch readiness scan, RD discovery (Phase 0), PM elaboration (Phase 1),…
Automate Refiner tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
DMA merge queue pattern for sequential, deterministic merge request processing. Checks out branches, rebases onto main, runs tests, merges, and pushes.
Use when a task needs the judgment of a Petroleum Pump System Operator, Refinery Operator, or Gauger — diagnosing a product quality failure when every individual temperature and…
Use when the user corrects you on Odoo specifics, when you notice a skill missed a real case, or when skills/_journal.md has accumulated 5+ entries.
Use when anything misbehaves - a failing test, a production bug, a build break, flaky or unexpected behavior - before proposing or attempting any fix.
Append to daily notes and create notes in Reflect. Use for capturing thoughts, todos, or syncing information to your knowledge graph.
Captures user corrections from a session, validates them semantically, and writes approved learnings to the most specific persistence target (skill file, project CLAUDE.md, or…
Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples
Clear specific learnings from CLAUDE.md Skill Memories section. Activates for reflect clear, clear learning, remove learning, delete memory.
Reflect on a session to identify learnings, friction points, and improvements. Captures valuable insights for future sessions and system evolution.
Pattern for producing quality reflections after completing work. Required for all agent outputs.
Standalone routine skill for interval-triggered scheduled checks. Runs one due check, gates findings through reflection-judge + proposal-triage, applies state, and logs.
Guide an end-of-session reflection to capture learnings and feelings. Use when finishing a work session, after completing a challenging task, when wanting to consolidate what was…
Agent-Selbstreflexions-Coach. Aktivieren wenn ein Agent einen Error / Tool-Failure / Exit-Code-Knall trifft. Klassifiziert in 3 Schritten (NORMAL/VERMEIDBAR/TECHNISCH) + ggf.
Use when completing a plan, finishing a development branch, wrapping up a session, or at any natural transition between work phases — reviews skill-bus telemetry to identify…
個人のふりかえりを対話で伴走するコーチスキル。KPT（Keep/Problem/Try）を 「事象評価の4象限（価値×蓋然性）」と「根本的な帰属の誤り」というレンズで再解釈し、 成功を能力に紐付けすぎ／失敗を状況に紐付けすぎる認知バイアスを矯正しながら、 学習の指向性（偶然を実力に変える水平方向、行動を改善する垂直方向）を引き出す。…
Maintain a reflection practice — daily, weekly, quarterly — that turns experience into nameable, retrievable lessons.
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them
Call a C# method by reflection — including private methods. Requires a method schema obtained via 'reflection-method-find'.
Find C# methods across every loaded assembly by name / type / parameters — including private methods.
Use when the user notices a recurring pattern they want the system to learn ("I keep doing X", "every time Y happens", "make this automatic", "remember to always"), or when…
Use for self-correcting implementation. Implements the reflexion loop: implement, validate, self-critique, retry (max 3 iterations).
Soros's theory of reflexivity applied to financial markets. Covers the cognitive and manipulative functions, boom-bust dynamics, feedback loops in credit/equity/currency markets,…
Roslyn-powered semantic query CLI for C# solutions. Use when you need to find references, callers, implementations, dependencies, members, or trace call chains in a C# codebase —…
Use when targeting 《改革》(Reform — 重庆社会科学院主管主办的改革政策类 CSSCI 月刊, 1988 年创刊, 不收版面费) or deciding whether a Chinese social-science/econ/management manuscript fits this journal.
Für Reform: Mandantenkommunikation und Entscheidungsvorlage: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Mandantennachricht oder Entscheidungsvorlage.
Use when targeting 《经济体制改革》(Reform of Economic System — 四川省社会科学院主管主办的经济理论 CSSCI 双月刊, 1983 年创刊, FounderSS 在线投审稿) or deciding whether a Chinese social-science/econ/management…
Runs mdformat to rewrite Markdown into a consistent CommonMark-oriented layout or check mode in CI. Use it when an agent needs deterministic Markdown diffs before review,…
반복된 패치가 먹히지 않거나 같은 불만이 계속 들어올 때 멈추고 문제를 다시 이해한다. 사용자가 "아닌데", "이게 아니야", "그거 아니라고", "왜 자꾸 그래", "다시 생각해", "/reframe" 등 현재 수정 방향에 불만을 표현하면 사용.
Use when the user asks for an opinion on an already-compiled scene — "how does this look?" / "is this good?" / "review this" / "make it better" / "any feedback?" / "polish" — OR…
Use when the user asks for multiple pages, a full site, a sitemap, a group like "home + pricing + about + 404", or resumes a partial site (baton on disk).
Force-refresh the claudit knowledge cache from official Anthropic documentation
Synchronizes your local `~/.claude/skills/`, `~/.claude/agents/`, and `~/.claude/blueprints/` installation against the canonical Agent OS skill, agent, and blueprint library.
Re-fetches metadata for catalog sources (`skill-sources.json`) and updates fields like `last_updated`, star counts, latest commit sha, and license.