70 skills · sorted by relevance
Post-mortem on what the user has already published - which posts actually worked, why, and what to stop doing. Use when the user pastes their LinkedIn analytics or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to double down on.
The English summary is being prepared. Showing the original description.
Post-mortem on what the user has already posted - which reels actually worked, why, and what to stop making. Use when the user pastes their Instagram insights or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to do more of.
The English summary is being prepared. Showing the original description.
Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management. Masters incident command, blameless post-mortems, error budget management, and system reliability patterns. Handles critical outages, communication strategies, and continuous improvement. Use IMMEDIATELY for production incidents or SRE practices.
The English summary is being prepared. Showing the original description.
Audit whether prior learnings actually fired, then install mechanisms for this run's recurrences. No finding without an install path and a firing test. Triggers: retrospective, reflect, what did we learn, patterns, post-mortem, why does this keep happening.
The English summary is being prepared. Showing the original description.
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
The English summary is being prepared. Showing the original description.
Adversarial thinking partner that stress-tests plans, prepares board meetings, and surfaces blind spots. Use when you need plan validation, board prep, hard-decision frameworks, or pre/post-mortem failure analysis.
The English summary is being prepared. Showing the original description.
Orchestrate a campaign lifecycle: briefs, budget models, UTMs, post-mortems. "set up UTM naming conventions"
The English summary is being prepared. Showing the original description.
Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from my results", "post-mortem on my campaign".
The English summary is being prepared. Showing the original description.
Dung khi campaign DA KET THUC va can rut ra bai hoc dung cho lan sau — scorecard so lieu vs target, cai gi hieu qua, cai gi khong va vi sao co bang chung, bat ngo ngoai du doan, cap nhat playbook va Brand Hub, action item co nguoi chiu trach nhiem. Kich hoat khi user nhac 'retro campaign', 'retrospective', 'post-mortem', 'tong ket chien dich', 'bai hoc tu campaign', 'campaign vua roi rut ra gi', 'lan sau lam khac the nao'. Khong dung cho — bao cao so lieu dinh ky cho sep hoac khach thi dung skill 07-bao-cao-marketing; danh gia hieu suat tung nhan su thi dung skill 65-team-performance-review; ke hoach ads ky tiep thi dung skill 57-next-ads-plan.
The English summary is being prepared. Showing the original description.
Dung khi thuong hieu DANG bi tan cong hoac campaign gay phan ung xau — phan loai 5 cap L1 den L5, quy trinh 4 gio dau, template phan hoi tung tinh huong, ai duoc phat ngon, danh sach TUYET DOI khong lam va post-mortem sau khung hoang. Kich hoat khi user nhac 'khung hoang truyen thong', 'crisis', 'bi bao xau', 'review 1 sao lan rong', 'content gay phan ung', 'khach to tren mang', 'dang bi tay chay', 'phai xin loi the nao'. Khong dung cho — theo doi va canh bao som khi chua co su co thi dung skill 15-social-listening; campaign kem ve so lieu chu khong phai su co thi dung skill 03-danh-gia-hieu-suat; tong ket bai hoc sau khi da yen thi dung skill 63-campaign-retrospective.
The English summary is being prepared. Showing the original description.
Use when a campaign has ENDED and the team needs a structured retrospective — a scorecard against target, what worked, what did not, and why with evidence, surprises, process review, lessons written back into the playbook and Brand Hub, and action items with owners. Trigger on 'campaign retrospective', 'campaign retro', 'post-mortem', 'campaign debrief', 'what worked and what did not', 'the campaign is over, what did we learn'. Also use when a campaign underdelivered and the team is arguing about why. Not for — a periodic performance report, see `07-marketing-report-global`; diagnosing live numbers mid-flight, see `03-performance-eval-global`; the next period ads plan, see `57-next-ads-plan-global`.
The English summary is being prepared. Showing the original description.
Use when a brand faces a communications CRISIS or a campaign is failing in public — L1 to L5 severity classification, a first-four-hours process, response templates by type, an escalation matrix, a do-not-do list, holding statements, and a post-mortem. Trigger on 'PR crisis', 'crisis playbook', 'a complaint is going viral', 'bad reviews are spreading', 'our content caused backlash', 'we are getting attacked online'. Also use when the user forwards an angry thread and asks what to do right now. Not for — monitoring before anything blows up, see `15-social-listening-global`; diagnosing weak performance numbers, see `03-performance-eval-global`; the routine post-campaign review, see `63-campaign-retrospective-global`.
The English summary is being prepared. Showing the original description.
Configure and collect crash dumps for modern .NET applications. USE FOR: enabling automatic crash dumps for CoreCLR or NativeAOT, capturing dumps from running .NET processes, setting up dump collection in Docker or Kubernetes, using dotnet-dump collect or createdump. DO NOT USE FOR: analyzing or debugging dumps, post-mortem investigation with lldb/windbg/dotnet-dump analyze, profiling or tracing, or for .NET Framework processes.
The English summary is being prepared. Showing the original description.
Debugging: guided diagnosis of application bugs, and post-mortem of failed agent sessions.
The English summary is being prepared. Showing the original description.
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers, agents), or pick LlamaIndex vs LangChain / Haystack / raw vector store for a coding task. Encodes the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical RAG bootstrap SOP from baseline `VectorStoreIndex` through hybrid + reranker + eval-loop hardening, the official 13-failure-mode checklist, and 5 dilemma cases distilled from docs, GitHub issues, and 2025 production post-mortems.
The English summary is being prepared. Showing the original description.
Production incident response automation. Reads logs, checks recent deploys, identifies root cause, suggests fixes, drafts incident comms, creates post-mortem templates. Severity classification (SEV1-4), escalation paths, status page updates. Generates incident-report.md with timeline, root cause, impact assessment, remediation steps, and prevention measures.
The English summary is being prepared. Showing the original description.
Post-mortem analysis when a client churns. Takes client history, engagement data, support tickets, usage logs, and exit feedback to produce a comprehensive churn autopsy with root cause classification, timeline of decline, and preventive measures.
The English summary is being prepared. Showing the original description.
Post-engagement knowledge harvest AND harness retrospective - after a box/bugbounty/pentest/CTF is completed, first diff how the engagement was EXECUTED against the skills/hooks that governed it (what discipline was skipped) and improve the harness, then sweep the whole engagement for GENERIC reusable knowledge NOT already in wiki/ and land it via the leak-gated stage->promote pipeline. Use at close-out or when asked to "extract learnings", "what did we learn", "harvest lessons into wiki", "distill this engagement", "post-mortem into the wiki", "what did we do wrong", "improve the harness from this box".
The English summary is being prepared. Showing the original description.
OI-3 spike harness — heavy consumer skill, INLINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow via an inline (non-forked) guidance skill. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.
The English summary is being prepared. Showing the original description.
OI-3 spike harness — heavy consumer skill, BASELINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow by reading a file directly, with NO Skill-tool call. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.
The English summary is being prepared. Showing the original description.
OI-3 spike harness — heavy consumer skill, FORKED arm. Builds an incident post-mortem and sources the readability standard mid-workflow via a forked (context fork) guidance skill. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.
The English summary is being prepared. Showing the original description.
Summarizes the complete lifecycle of a bug across code versions, tracking its introduction, detection, fixing attempts, and regression history. Use when users need to: (1) Understand how a bug evolved over time, (2) Trace when and how a bug was introduced, (3) Analyze fix attempts and their effectiveness, (4) Identify regression patterns, (5) Generate bug lifecycle reports for documentation or post-mortems. Takes a repository, bug identifier, and version history as input.
The English summary is being prepared. Showing the original description.
吃一堑长一智 — 走完 5 步交互式反思（堑 → 自动输出 → 旧权重 → 新参数 → 替代动作），从「情绪复盘」推进到「行为训练」，把第一反应这一层 L3 权重练新。Use when 王建硕 reflects on a personal setback, mistake, or recurring pattern (反思, 复盘, 回顾, 总结教训, 吃一堑, 长一智, "这次又栽了", "怎么又这样", "为什么我总是…", "想开点都做不到", "知道道理但做不到"). For the user as a human, not for Claude's task post-mortems.
The English summary is being prepared. Showing the original description.
Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
The English summary is being prepared. Showing the original description.