Context & AI engineering
25,745 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
raja21068/AutoResearch/skills/aris/auto-review-loop-llm Skill
2★ repoAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/comm-lit-review Skill
2★ repoCommunications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/aris/paper-illustration-image2 Skill
2★ repoGenerate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to `paper-illustration`, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/skills-codex/auto-review-loop-llm Skill
2★ repoAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/skills-codex/research-review Skill
2★ repoGet a deep critical review of research from GPT using a secondary Codex agent. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
The same file is in 1 other repository
raja21068/AutoResearch/skills/paper-pipeline/agent-research-aggregator Skill
2★ repoPre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimental_log.md). TRIGGER when the user says "aggregate my agent logs for paper writing", "extract experiments from my coding agent history", "prepare PaperOrchestra inputs from my cache", "turn my agent logs into a paper", mentions a folder or directory they want to use as the basis for a paper, or wants to run PaperOrchestra but only has scattered agent experiment histories rather than structured inputs. Run this BEFORE paper-orchestra. Also called automatically by paper-orchestra when workspace/inputs/idea.md or workspace/inputs/experimental_log.md are missing.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/paper-pipeline/content-refinement-agent Skill
2★ repoStep 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".
The same file is in 1 other repository
raja21068/AutoResearch/skills/paper-pipeline/literature-review-agent Skill
2★ repoStep 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the related work", or "build the bibliography".
The same file is in 2 other repositories
raja21068/AutoResearch/skills/paper-pipeline/outline-agent Skill
2★ repoStep 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper structure".
The same file is in 2 other repositories
raja21068/AutoResearch/skills/paper-pipeline/plotting-agent Skill
2★ repoStep 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
The same file is in 3 other repositories
raja21068/AutoResearch/skills/paper-pipeline/section-writing-agent Skill
2★ repoStep 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges everything into the template that already contains Intro + Related Work from Step 3. TRIGGER when the orchestrator delegates Step 4 or when the user asks to "write the methodology and experiments sections" or "fill in the rest of the paper".
The same file is in 3 other repositories
oryanmoshe/agent-skills/skills/managing-agents-md Skill
no license2★ repoCreates and maintains AGENTS.md documentation files that guide AI coding agents through a codebase. Use when adding a significant new feature or directory, changing project architecture, setting up a new project or monorepo, noticing a codebase has no AGENTS.md, or after major refactors that change project structure. Also triggers on "document this for agents", "update agents.md", or "create agents.md".
The same file is in 2 other repositories
ryan-scheinberg/harness/skills/harness-skillset/updating-ai-knowledge Skill
2★ repoGuidance for updating agent-facing files (skills, AGENTS.md, subagent definitions) when you discover they are wrong, incomplete, or stale. Use when you've solved a problem that revealed a gap, or when the user says to update a skill, AGENTS.md, or agent. The trigger is friction; you learned something the knowledge base should have told you
Makiya1202/ai-agents-skills/skills/copilot-docs Skill
no license2★ repoConfigure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on Copilot instructions, copilot-instructions.md, GitHub Copilot config.
Makiya1202/ai-agents-skills/skills/langchain Skill
no license2★ repoBuild LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval, agent chain.
SkillMedev/creator-studio/skills/video-hook-writer Skill
2★ repoWrites the spoken line plus visual frame combination for the first 3 seconds of a short-form video, delivering labeled variants built from six proven hook formulas and matched to TikTok, Reels, or Shorts. Use when someone says "write a hook for this video", "my Shorts die in the first seconds", "give me openers for this TikTok", or "how should this Reel start". Do NOT use for the first line of a written post, thread, or caption - use social-hook-generator instead; do NOT use to build the full thread after the opener - use tweet-thread-builder instead; do NOT use for the 30-second intro of a long-form YouTube video - use youtube-script-writer instead; do NOT use to design the clickable image for a video - use thumbnail-concept instead.
The same file is in 1 other repository
paulieb89/bouch-plugins/plugins/foundations/skills/deal-screener Skill
no license2★ repoScreen a UK property investment deal from a Rightmove URL or address. Pulls comps, yield, EPC, stamp duty, and rental data, then applies underwriting criteria to produce a BUY/WATCH/PASS decision with reasoning. Use when someone says "should I buy this?", "screen this property", "is this a good deal?", or pastes a Rightmove URL. Requires the Property MCP server (property-shared) to be connected.
paulieb89/bouch-plugins/plugins/foundations/skills/legal-research Skill
no license2★ repoResearch a UK legal question and produce a structured brief. Finds relevant legislation with section text, case law, OSCOLA citations, and a plain English summary. Use when someone asks about UK law, compliance, case law, or "what does the law say about X". Requires the UK Legal MCP server.
paulieb89/bouch-plugins/plugins/foundations/skills/pitch-research Skill
no license2★ repoResearches a UK company you want to pitch to and drafts a credible cold outreach email with a specific, verifiable opening hook. Combines Companies House data (profile, officers, PSC, insolvency, VAT, land registry) with a web sweep for recent press, hires, launches, and public statements. Produces two outputs: a scannable research brief and a first draft email under 150 words. Use when the user says "help me pitch X", "draft a cold email to X", "research X for outreach", "I want to approach X about Y", "prep me to pitch X", "write an outreach email to X", or similar outbound prospecting requests. Requires the UK Due Diligence MCP server. UK companies only (non-UK targets get web-only research with a caveat).
paulieb89/bouch-plugins/plugins/legal-os/skills/bailii-case-law Skill
no license2★ repoSearch BAILII for UK case law and retrieve full judgment text. Use when someone asks to find a case, search for case law on a topic, read a judgment, or check how courts have ruled on an issue. Covers UKSC, EWCA, EWHC, Upper Tribunal, EAT, and more. Requires the BAILII MCP server running locally (BAILII blocks cloud IPs).
paulieb89/bouch-plugins/plugins/legal-os/skills/hmrc-tax-vat Skill
no license2★ repoLook up UK tax guidance, VAT rates, and Making Tax Digital status. Summarises HMRC guidance in plain English with key thresholds, rates, and practical next steps. Use when someone asks "what's the VAT on X?", "do I need to register for MTD?", or any UK tax question. Requires the UK Legal MCP server.
paulieb89/bouch-plugins/plugins/legal-os/skills/legal-how-to Skill
no license2★ repoA practical guide for UK lawyers and legal researchers using Claude with the UK Legal MCP server. Explains the five core research workflows — legislation lookup, case law drill-down, citation tracing, parliamentary intent, and HMRC guidance — with example prompts and real output. Use when a lawyer wants to understand what the tools can do or how to structure a legal research session.
paulieb89/bouch-plugins/plugins/legal-os/skills/legal-research Skill
no license2★ repoResearch a UK legal question and produce a structured brief. Finds relevant legislation with section text, case law, OSCOLA citations, and a plain English summary. Use when someone asks about UK law, compliance, case law, or "what does the law say about X". Requires the UK Legal MCP server.
paulieb89/bouch-plugins/plugins/legal-os/skills/legislation-lookup Skill
no license2★ repoLook up a UK Act of Parliament or Statutory Instrument and retrieve a specific section. Returns the section text, in-force status, and territorial extent. Use when someone asks "what does the law say about X?" or "find me the section on X". Requires the UK Legal MCP server to be connected.
paulieb89/bouch-plugins/plugins/legal-os/skills/policy-briefing Skill
no license2★ repoResearch the parliamentary landscape around a policy topic and produce a structured briefing. Searches Hansard, identifies key MPs, runs a parliamentary reception assessment, and maps related legislation. Use when someone says "what's parliament saying about X", "policy briefing on X", "will this policy pass", "who's spoken about X in parliament", or needs to understand the political landscape around a proposal. Requires the UK Legal MCP server (uk-legal-mcp) to be connected.
paulieb89/bouch-plugins/plugins/property/skills/deal-screener Skill
no license2★ repoScreen a UK property investment deal from a Rightmove URL or address. Pulls comps, yield, EPC, stamp duty, and rental data, then applies underwriting criteria to produce a BUY/WATCH/PASS decision with reasoning. Use when someone says "should I buy this?", "screen this property", "is this a good deal?", or pastes a Rightmove URL. Requires the Property MCP server (property-shared) to be connected.
paulieb89/bouch-plugins/plugins/property/skills/investment-summary Skill
no license2★ repoGenerate a property investment summary from a Rightmove URL. Pulls the listing details, area comparables, rental market, and key financials into a structured investment brief. Use when someone shares a Rightmove link and wants to know if it's worth buying, what the yield would be, or how it compares to the area. Requires the Property MCP server.
paulieb89/bouch-plugins/plugins/property/skills/property-quick-comps Skill
no license2★ repoGet comparable sales data for a UK postcode. Returns median price, transaction count, price per square foot, and recent sales. Quick lookup — one tool call. Use when someone asks "what are houses going for in [postcode]?" or "comps for [area]". Requires the Property MCP server (property-shared) to be connected.
paulieb89/bouch-plugins/plugins/property/skills/reduced-listings Skill
no license2★ repoFind motivated sellers in a UK postcode. Pulls reduced Rightmove listings, benchmarks against Land Registry comps, and assesses motivation signals. Use when someone asks about reduced properties, motivated sellers, price drops, bargains, or who has been on the market longest. Requires the Property MCP server (property-shared) to be connected.
paulieb89/bouch-plugins/plugins/property/skills/rightmove-investment-finder Skill
no license2★ repoSearch Rightmove for investment properties matching your criteria, then analyse each for yield, comps, and stamp duty. Produces a ranked shortlist with BUY/WATCH/PASS ratings. Use when someone asks "find me investment properties in [area]" or "what's available under 200k?". Requires the Property MCP server. Optional: UK Legal MCP for BTL tax and leasehold checks.
paulieb89/bouch-plugins/plugins/property/skills/rightmove-quick-search Skill
no license2★ repoSearch Rightmove and compare asking prices against recent sales data. Shows what is on the market and whether asking prices look fair. Use when someone asks "what's on Rightmove in [area]?" or "show me properties under [price]". Requires the Property MCP server.
the-hugin/RSIm/skills/migrate-claude-md Skill
no license2★ repoRecursively Self-Improving Module — persistent memory + structured improvement loop for Claude Code
the-hugin/RSIm/skills/multi-agent-patterns Skill
no license2★ repoMaster orchestrator, peer-to-peer, and hierarchical multi-agent architectures
the-hugin/RSIm/skills/skill-creator Skill
no license2★ repoRecursively Self-Improving Module — persistent memory + structured improvement loop for Claude Code
the-hugin/RSIm/skills/validate-claude-md Skill
no license2★ repoRecursively Self-Improving Module — persistent memory + structured improvement loop for Claude Code
varunk130/ai-workflow-playbooks/skills/multi-agent-collaboration Skill
2★ repoCoordinate effectively when multiple AI agents work on the same codebase or feature.
mostafa-drz/claude-skills/code/skill-creator Skill
2★ repoCreates new Claude Code skills interactively, enforcing every convention in SKILLS_GUIDE.md plus the learning, configurability, and feedback patterns used by the best in-tree skills (svg-art, should-i-buy, step-through). Asks contextual questions about purpose, side effects, tools, and workflow, then generates a complete SKILL.md with three-tier preferences (Defaults / Profile / Learned), a feedback subcommand, a session log, and a feedback journal — unless the skill is genuinely stateless. Use when creating a new skill or scaffolding one.
mostafa-drz/claude-skills/code/workflow-advisor Skill
2★ repoAnalyzes recent Claude Code conversations and local Claude state (skills, settings, memory files, CLAUDE.md), researches the latest Claude Code features and best practices online, and suggests one workflow improvement at a time with reasoning and a concrete action item. Can save accepted suggestions to memory for tracking. Use when you want to discover underused Claude Code features, improve your development workflow, stay current with the latest Claude Code capabilities, or get a periodic workflow health-check.
Rijul1204/rashedul-agentic-engineering/skills/handoff Skill
2★ repoCompact the current conversation into a structured handoff document (saved to the OS temp directory) so a fresh agent can continue the work without losing context. Use when the user invokes /handoff, says "create a handoff doc", "write a handoff document", "compact this for another agent", "pass off to another session", "what will the next session focus on", or generally wants to checkpoint the conversation state before a context-window break. Always references existing artifacts (design docs, plans, PRs, commits, memory entries) by path/URL — never duplicates their content. Includes a mandatory "suggested skills" section. Redacts API keys, passwords, PII.
Rijul1204/rashedul-agentic-engineering/skills/pair-agent-harness Skill
2★ repoHarness two AI agents (typically Claude + OpenAI Codex, or two Claudes, or an agent + human reviewer) into a Reviewer / Implementor pair that collaborate asynchronously through a shared markdown thread. One agent reviews / critiques / asks pointed questions; the other implements / responds / drives the code changes; the file mediates. Use when the user says "pair another agent on this", "harness Codex on this", "review this with Codex", "open a Codex thread", "respond to Codex", "open a peer review", "monitor this review file", names a *-review-thread.md or *-dialogue-thread.md, or wants to coordinate structured async back-and-forth between two AI agents on a code or design question. Seeds the file from a template if missing, appends a numbered Claude response under its own section header, arms a file-mtime monitor so each peer append triggers a fresh read + response, drives the pyramid-principle response shape (position first, justification second), detects consensus markers like "Final ACK" / "No further objections", and implements + quality-gates any code changes the thread converges on.
Rijul1204/rashedul-agentic-engineering/skills/tri-agent-loop Skill
2★ repoOrchestrate a plan → review → implement delivery loop across three PLUGGABLE agent roles — planner, reviewer, implementer — where any agent can fill any role in any order. One agent drafts an artifact (SRS / design / per-task plan), a second adversarially reviews it through a shared markdown thread until convergence (Final ACK), and a third implements; the orchestrator (the agent running this skill) relays handoffs, monitors the review thread, and reviews the resulting PR. Use when the user asks to "run the planner / reviewer / implementer loop", "tri-agent loop", "plan-review-implement", "use X to plan, Y to review, Z to implement" (any permutation, e.g. Claude plans, Codex reviews, Cursor implements), or wants the docs-first / Codex-reviewed / Cursor-implemented workflow from feedback_planner_reviewer_codex_loop generalized to arbitrary agents.
wunamesst/skills/skills/sync-rules Skill
2★ repoIteration closeout knowledge routing for AI-assisted development. Use when the user asks to summarize changed function points into a knowledge base, update project docs or generated superpower docs after code changes, sync rules, distill lessons from an iteration, record durable decisions, or remember user preferences. Routes distilled knowledge to personal notes (K1), project docs (K2), agent memory suggestions (K3), or project instructions such as AGENTS.md and CLAUDE.md (K4), with preview and safety checks before writing.
arch3rPro/ark-space/plugins/ark-space/skills/firecrawl-agent Skill
2★ repoUse when running Firecrawl Agent for structured extraction, schema-guided web data collection, or ArkSpace structured_extract routing that selects Firecrawl.
arch3rPro/ark-space/plugins/ark-space/skills/orchestrator Skill
2★ repoUse when a user invokes ArkSpace, asks for general help, a cross-domain task, role selection, skill selection, provider routing, web search/fetch through ArkSpace, or when task scope is unclear.
arch3rPro/ark-space/skills/firecrawl-agent Skill
2★ repoUse when running Firecrawl Agent for structured extraction, schema-guided web data collection, or ArkSpace structured_extract routing that selects Firecrawl.
arch3rPro/ark-space/skills/orchestrator Skill
2★ repoUse when a user invokes ArkSpace, asks for general help, a cross-domain task, role selection, skill selection, provider routing, web search/fetch through ArkSpace, or when task scope is unclear.
hssh8917/cc-skills/skills/snyk-agent-scan-compliance Skill
2★ repoCompliance expert for snyk-agent-scan — the agent skill file scanner — NOT for other Snyk CLI tools (snyk test, snyk code SAST, snyk iac, snyk container). Fixes alerts through content restructuring, never by suppressing or deleting information. Covers every file in a skill directory: SKILL.md, references/, assets/, and any secondary markdown. Apply when authoring a new skill, editing an existing one, triaging a failed snyk-agent-scan run locally or in CI, or unblocking a PR held by agent scanner failures. Not applicable to dependency vulnerabilities, code security findings, or infrastructure misconfigurations — those are out of scope.
The same file is in 1 other repository
easyinplay/harnessed/workflows/task/deliver Skill
2★ repotask-deliver workflow v3 — Stage ③.d 子任务交付 sub-workflow (harnessed 自有 completion-gate + Agent Teams conditional escalation + R20.10 explicit max_iterations_exceeded fallback)。2-phase composition: 01-deliver (completion-gate with completion_promise verbatim "COMPLETE" + parallelism judgments.parallelism-gate.completion-gate-wrapper.fires + fallback emit_warning_and_halt exit_code 1) → 02-progress-mark (Claude Code plugin /plan mark subtask complete in progress.md)。 schema_version: harnessed.workflow.v3 with disciplines_applied [6] + tools_available [completion-gate, verification-before-completion, agent-teams-create, agent-teams-send-message, agent-teams-shutdown, planning-with-files]. Triggered by harnessed CLI `harnessed task-deliver --task <text>` or slash command `/task-deliver` after `harnessed setup`.
easyinplay/harnessed/workflows/verify/code-review Skill
2★ repoStage ④.b verify sub-workflow — code-review 多 agent 并行 fan-out 高置信度 finding (subagent default per bundled parallelism gate — Task / Agent 工具 spawn 多 subagent fan-out, context 隔离, token 敏感)。 schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available (code-review) + 1 phase (parallelism ref judgments.parallelism-gate.subagent-default.fires)。 Triggered by slash command `/verify-code-review` after `harnessed setup`.
easyinplay/harnessed/workflows/verify/eval-review Skill
2★ repoStage ④ verify sub-workflow — GSD /gsd-eval-review AI phase eval 覆盖审计 (has_ai_phase 触发, 可选 conditional; pairs with plan 侧 gsd-ai-integration-phase AI-SPEC eval strategy). schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available (gsd-eval-review) + 1 phase (gate ref has_ai_phase conditional)。 Triggered by slash command `/verify-eval-review` after `harnessed setup`.
easyinplay/harnessed/workflows/verify/multispec Skill
2★ repoStage ④.h verify sub-workflow — 4-specialist Agent Team Pattern C 多维度审查 (关键发布 / 大重构 PR 升级, code-review + gstack-review + gstack-cso + gstack-qa 4 teammate 互相 SendMessage 质询, NOT fire-and-forget subagent fan-out; bundled Agent Teams Pattern C routing). Cleanup mandatory: shutdown_request + TeamDelete (bundled cleanup discipline). schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available (agent-teams 3 + 4 specialist capability) + 2 phase (01-team-create on critical-release invoke / 02-team-cleanup mandatory shutdown)。 Triggered by slash command `/verify-multispec` after `harnessed setup`.
tonychen15/xReview/codex/commands/xreview-refactor Skill
2★ repoRefactor code with xReview peer review. Codex is the developer, a peer LLM agent reviews your work. Use when: /refactor, refactor code with review
stuartshields/claude-setup/skills/clean-worktrees Skill
2★ repoRemove stale agent worktree directories and their orphaned branches. Run after parallel agent work or when .claude/worktrees/ accumulates cruft.
stuartshields/claude-setup/skills/handoff Skill
2★ repoWrite or update a handoff document so the next agent with fresh context can continue this work.
stuartshields/claude-setup/skills/review-memory Skill
2★ repoReview auto-memory for the current project. Shows accumulated learnings, identifies noise, and helps promote permanent patterns to CLAUDE.md, rules, or skills.
risadams/skills/handoff Skill
no license2★ repoCompact the current conversation into a handoff document for another agent to pick up.
ChizhongWang/veriglow-agent-map-skill/skills/veriglow-agent-map Skill
2★ repoLook up VeriGlow Agent Map for any website URL to discover its data functions, internal APIs, browser automation recipes, and agent reliability reports. Use when you need to extract structured data from a website, call a website's hidden API, or automate browser interactions with a web page.
The same file is in 2 other repositories
mouchegmouradian/claude-code-skills/skills/orchestrator Skill
2★ repoCoordinate large, multi-feature implementations by acting as an orchestrator that spawns focused sub-agents — one per RFC or feature area — while managing phasing, parallelization, and integration verification. Use this skill when a task spans 3+ independent features, multiple RFCs, or requires parallel implementation across different areas of the codebase. Also triggers on phrases like "orchestrate this", "spawn sub-agents", "implement all RFCs", "parallel implementation", "multi-agent", or "build the full app". Do NOT use for single-feature or single-file tasks — those should be implemented directly.
AdityaVasireddy/agent-skills/session-handoff Skill
2★ repoUse when the user says "session handoff", "wrap up session", "hand off", "handoff summary", "let's wrap up", "summarize before I clear", or wants a structured end-of-session summary before clearing context. Also use proactively when the user says they are about to /clear and no handoff has been produced yet. Generates a handoff document saved as a file (in the project's docs/handoffs/ directory, or as a downloadable file in chat environments) with required sections (objective, status, decisions + rationale, key files, next action) plus situational sections included only when they apply, so a fresh agent can continue seamlessly without re-deriving lost context.
Shuwanito/SkillsMP/.claude/skills/nexus-data-ml Skill
no license2★ repoML engineering and LLM fine-tuning agent. Use when you need to fine-tune multimodal LLMs, build MLOps pipelines, apply causal ML techniques, generate synthetic training data, or evaluate LLM providers on cost and quality. Detects overfitting, data leakage, and incorrect metrics.