Context & AI engineering
25,729 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
steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/subagent-driven-development Skill
no license1★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/agent-teams/skills/team-composition-patterns Skill
no license1★ repoDesign optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-standard workflow such as a migration or security audit.
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/backend-development/skills/saga-orchestration Skill
no license1★ repoImplement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building event-driven saga coordinators for travel booking systems that must roll back hotel, flight, and car rental reservations atomically, or debugging stuck saga states in production where compensation steps never complete.
Workflow orchestration patterns
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/backend-development/skills/workflow-orchestration-patterns Skill
no license1★ repoDesign durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
The same file is in 1 other repository
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/block-no-verify/skills/block-no-verify-hook Skill
no license1★ repoConfigure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
The same file is in 3 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/incident-response/skills/on-call-handoff-patterns Skill
no license1★ repoMaster on-call shift handoffs with context transfer, escalation procedures, and documentation. Use this skill when transitioning on-call responsibilities between engineers and ensuring the incoming responder has full situational awareness, when writing a shift summary that captures active incidents, ongoing investigations, and recent changes, when handing off mid-incident so a fresh engineer can take over the incident commander role without losing context, when onboarding a new engineer to the on-call rotation for the first time, or when auditing and improving the quality of existing handoff processes across teams.
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/llm-application-dev/skills/embedding-strategies Skill
no license1★ repoSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
The same file is in 2 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/llm-application-dev/skills/llm-evaluation Skill
no license1★ repoImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
The same file is in 2 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/llm-application-dev/skills/prompt-engineering-patterns Skill
no license1★ repoMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
The same file is in 2 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/llm-application-dev/skills/rag-implementation Skill
no license1★ repoBuild Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
The same file is in 1 other repository
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/protect-mcp/skills/protect-mcp-setup Skill
no license1★ repoConfigure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions.
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/reverse-engineering/skills/memory-forensics Skill
no license1★ repoMaster memory forensics techniques including memory acquisition, process analysis, and artifact extraction using Volatility and related tools. Use when analyzing memory dumps, investigating incidents, or performing malware analysis from RAM captures.
The same file is in 1 other repository
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/review-agent-governance/skills/review-agent-setup Skill
no license1★ repoConfigure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/systems-programming/skills/memory-safety-patterns Skill
no license1★ repoImplement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
The same file is in 1 other repository
Superpowers subagent driven development
steph-frtech/cdesign-expo/.claude/skills/superpowers__subagent-driven-development Skill
no license1★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
steph-frtech/cdesign-expo/skills/expo-from-claude-design Skill
no license1★ repoConvert a Claude Design handoff bundle, HTML/CSS mockup, or design screenshot into production-ready Expo React Native code with NativeWind. ALWAYS use this skill when the user provides any of the following for an Expo/React Native project — a Claude Design link or bundle ID, a design screenshot/image, an HTML/CSS snippet, a Figma export, or any visual UI reference they want implemented as a mobile screen or component. Use even when the user does not explicitly mention Expo if the project context (CLAUDE.md, package.json with expo dependencies, app/ directory) indicates Expo Router. Use also when converting web UI code to React Native, or when the user mentions "transformer ce design", "implémente cette maquette", "code cet écran", "make this mobile".
metallurgical/ogre-runner/skills/exec Skill
no license1★ repoAlias of the `execute` skill - execute the next incomplete checklist item from an approved Ogre plan using Claude or Codex, one step at a time. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre exec ...", "use ogre exec for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
metallurgical/ogre-runner/skills/execute Skill
no license1★ repoExecute the next incomplete checklist item from an approved Ogre plan using Claude or Codex, one step at a time. MUST trigger whenever the user's own message literally names Ogre (e.g. "ogre execute ...", "ogre exec ..."). That explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
metallurgical/ogre-runner/skills/rescue Skill
no license1★ repoRun a standalone hotfix/task with Claude or Codex, with no plan or issue involved - for a freeform ask like "fix error in login backend" or "implement forgot password page" where creating an Ogre plan first would be overkill. MUST trigger whenever the user's own message literally names Ogre (e.g. "ogre rescue ...", "use ogre for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
metallurgical/ogre-runner/skills/run Skill
no license1★ repoAlias of the `rescue` skill - run a standalone hotfix/task with Claude or Codex, with no plan or issue involved, for a freeform ask like "fix error in login backend" or "implement forgot password page" where creating an Ogre plan first would be overkill. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre run ...", "use ogre run for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
Tedydev-web/llm-wiki-skills/skills/wiki-memory Skill
1★ repoOptional add-on: capture Claude Code session transcripts as wiki sources for later ingest. Off by default. Subcommands: enable, disable, status, flush, logs.
Tedydev-web/llm-wiki-skills/skills/wiki Skill
1★ repoSet up a new LLM Wiki — an Obsidian-based knowledge base where the LLM reads raw sources and compiles them into structured interlinked pages. Use when the user wants to create a wiki, initialize a vault, set up a personal knowledge base, second brain, or says "onboard". Guides through an interactive wizard to configure vault name, location, domain, agent support, and tooling.
MariusGithub13/open-deal-kit/agents/customer-concentration-agent Skill
1★ repoStress-test revenue quality and customer risk, concentration, stickiness, the 'what if we lost the top customer' scenario, and the gaps to close. Use whenever you have customer or revenue-mix data, or when asked to 'check customer concentration', 'how fragile is this revenue', or 'what's the churn risk'.
MariusGithub13/open-deal-kit/agents/go-no-go-agent Skill
1★ repoForce a clean go / no-go before committing real diligence time, case for, case against, what must be true, and a recommendation with confidence. Use at the end of screening, or when asked to 'should I proceed', 'go or no-go on this deal', or 'make the call'.
viktor-milev/claude-skills/prompt-architect-fable Skill
1★ repoFable-variant prompt architect — classifies a task against a 10-bucket taxonomy with an execution-mode overlay (interactive vs. agentic), decides output architecture (single-turn vs. chained multi-stage), and produces a technique-grounded v1 draft prompt calibrated for Claude Fable 5, with surface-aware run settings (chat app, Claude Code, Cowork, harness). Verdicts are SINGLE-TURN, SINGLE-TURN (CEILING), or CHAIN (README + Project orchestrator + per-stage prompts). Fires ONLY on explicit Fable invocation — trigger phrases include "architect this for Fable 5", "help me prompt this for Fable", "draft a Fable 5 prompt for". Do NOT trigger on unqualified requests ("help me prompt this", "draft a prompt for") — those route to prompt-architect (Opus sibling). Do NOT trigger when a draft prompt already exists — that's prompt-optimizer-fable. Do NOT trigger for tasks covered by a dedicated domain skill — route to that skill instead.
viktor-milev/claude-skills/prompt-architect Skill
1★ repoClassifies a task against a 10-bucket taxonomy, decides output architecture (single-turn vs. chained multi-stage), and produces a technique-grounded v1 draft prompt. Verdicts are SINGLE-TURN, SINGLE-TURN (CEILING) with a strain note, or CHAIN producing a README + Project orchestrator + per-stage prompts. Use when you describe a non-trivial task but have no prompt written yet. Trigger phrases include "help me prompt this", "set up a prompt for", "draft a prompt for", "how should I ask Claude to", "architect a prompt for", "I'm about to start work on X — help me frame it". Also trigger for multi-step analytical tasks (research, knowledge document, design, decision support) where no draft exists. Do NOT trigger when a draft prompt already exists — that's prompt-optimizer. Do NOT trigger for tasks already covered by a dedicated domain-specific skill — route to that skill instead.
viktor-milev/claude-skills/prompt-optimizer-fable Skill
1★ repoFable-variant rigorous prompt optimizer — audits a polished prompt and rewrites it to elicit state-of-the-art output from Claude Fable 5, with surface-aware run settings (chat app, Claude Code, Cowork, harness). Triages into OUT OF PURVIEW / BORDERLINE / IN PURVIEW; decides output architecture (single-turn vs. chained multi-stage) and produces a chain deliverable (README + orchestrator + stage prompts) when signals fire. Fires ONLY on explicit Fable invocation — trigger phrases include "PO this for Fable", "optimize this prompt for Fable 5", "fable-optimize this", "run the fable optimizer". Do NOT trigger on unqualified requests ("PO this", "optimize this prompt") — those route to prompt-optimizer (Opus sibling). Do NOT trigger for messy dictated or flow-state input (use prompt-optimizer-flow), and do NOT trigger when the user wants the prompt EXECUTED rather than optimized.
viktor-milev/claude-skills/prompt-optimizer-flow Skill
1★ repoFlow mode prompt optimizer — transforms rough, dictated, or stream-of-consciousness thoughts into a state-of-the-art Claude keystone prompt in seconds, without breaking the user's flow. Produces a finished, paste-ready prompt with no placeholders or template variables. Skips diagnostic theater, infers intent aggressively from messy input. Use whenever the user pastes or dictates messy unstructured input and wants it turned into a polished prompt fast. Trigger phrases include "quick prompt", "dictating", "rough thoughts", "thinking out loud", "PO this fast", "flow mode", "PO flow", "make this a prompt", "turn this into a prompt", "draft a prompt for", "starting a new chat about". Also trigger on dictation artifacts (rambling, self-corrections, "um", "uh", "actually wait") or when starting a new chat and needing a starter prompt. For polished prompts needing rigorous evaluation, use prompt-optimizer instead. Do NOT trigger when the user wants the prompt EXECUTED.
viktor-milev/claude-skills/prompt-optimizer Skill
1★ repoRigorous mode prompt optimizer — audits a polished prompt, decides output architecture (single-turn vs. chained multi-stage), and rewrites it to elicit state-of-the-art output from Claude. Triages every input into OUT OF PURVIEW / BORDERLINE / IN PURVIEW; rigorous optimization (architecture decision, 9-dim diagnostic, archetype detection, capability activation) applies ONLY to IN PURVIEW. When chain signals fire, produces a chain deliverable (README + Project orchestrator + per-stage prompts) instead of a single-turn prompt. Simple prompts return substantially unchanged with a triage note. Use when the user asks to optimize, audit, score, diagnose, sharpen, or level up a prompt; trigger phrases include "optimize this prompt", "PO this", "run this through the optimizer", "sharpen this prompt". For messy dictated or flow-state input, a separate flow-mode counterpart exists. Do NOT trigger when the user wants the prompt EXECUTED rather than optimized.
longyenkai83/personal-marketing-kit/skills/2-content/hook-swipe-library Skill
no license1★ repoSearch and remix proven viral hooks from curated banks (currently 72 Vietnamese hooks for women-biz-vn niche, sourced from Kallaway 18-topic × 4-temperature framework). Use when user needs to quickly find a hook by niche/topic/temperature/framework, remix existing hooks, or feed hook bank into content-engine Stage 3. Triggers — "tìm hook có sẵn", "swipe hook", "hook bank", "remix hook", "lấy hook viral".
longyenkai83/personal-marketing-kit/skills/2-content/kallaway-hook-master Skill
no license1★ repoViết hook video ngắn (TikTok/Reels/Shorts) + caption FB/IG theo phương pháp Kallaway — 6 Hook Frameworks (Fortune Teller/Experimenter/Teacher/Magician/Investigator/Contrarian) × 5 Dream Outcome Formats (About Me/If I/To You/Can You/He-She Just Did) × 4 Component Alignment (Spoken+Text+Visual+Audio). Use when user wants to write hook for short-form video, viết hook video, viết caption mở đầu, brainstorm hook viral, audit hook cũ, hoặc apply Kallaway framework. Vietnamese-first. Triggers — "viết hook", "hook kallaway", "kịch bản reels", "hook viral", "audit hook video".
longyenkai83/personal-marketing-kit/skills/6-meta/subagent-architect Skill
no license1★ repoBuild (scaffold) hoặc audit (review) custom Claude Code subagents theo spec chính thức tại https://code.claude.com/docs/en/sub-agents. BUILD mode hỏi 6 câu trong 1 message rồi sinh file .md đúng spec, ghi vào ~/.claude/agents/ hoặc .claude/agents/. AUDIT mode review file có sẵn theo 10 best-practice gate. Vietnamese-first. Use when user says "tạo subagent", "build subagent", "audit subagent file", "review my subagent", "scaffold agent for X", "convert prompt to subagent", or invokes /subagent-architect.
Fantasymax/easy-build-skills/plugin/user-research-for-ai-config/skills/user-research-for-ai-config/templates/mode-b/orchestration/orchestrator Skill
no license1★ repoOrchestrate a {N}-step workflow that {B1 一句话定义}. This is the entry point — when the user says any of {B7 ① 顶层触发原话 1–2 句}, this skill walks them through {sub-skills 列表} in order. Trigger especially when the user mentions {B7 整体触发原话} or wants to "do the whole flow". Do NOT use for: single-step requests (use the corresponding sub-skill directly).
Fantasymax/easy-build-skills/plugin/user-research-for-ai-config/skills/user-research-for-ai-config/templates/mode-b/plugin-with-hooks Skill
no license1★ repo{B1 一句话定义动词} {B1 对象}, with deterministic enforcement on {B13 触发事件,如 git push / file save / session start}. Use when {B7 ① 触发原话;如自然语言也支持触发}. The hook ensures {B13 + B5 转化的硬拦截规则}, even if Claude Code's model-side reasoning forgets. Do NOT use for: {B7 ③ 反例}.
Fantasymax/easy-build-skills/skill/user-research-for-ai-config/templates/mode-b/orchestration/orchestrator Skill
no license1★ repoOrchestrate a {N}-step workflow that {B1 一句话定义}. This is the entry point — when the user says any of {B7 ① 顶层触发原话 1–2 句}, this skill walks them through {sub-skills 列表} in order. Trigger especially when the user mentions {B7 整体触发原话} or wants to "do the whole flow". Do NOT use for: single-step requests (use the corresponding sub-skill directly).
Fantasymax/easy-build-skills/skill/user-research-for-ai-config/templates/mode-b/plugin-with-hooks Skill
no license1★ repo{B1 一句话定义动词} {B1 对象}, with deterministic enforcement on {B13 触发事件,如 git push / file save / session start}. Use when {B7 ① 触发原话;如自然语言也支持触发}. The hook ensures {B13 + B5 转化的硬拦截规则}, even if Claude Code's model-side reasoning forgets. Do NOT use for: {B7 ③ 反例}.
Songhonglei/build-better-skills/skills/skill-deep-audit Skill
1★ repoGeneric skill-quality auditor for any agent skill (Claude, OpenClaw, Cursor, etc.). Runs a 7-dimension static analysis (D1 process closure & idempotency, D2 tool/command conventions, D3 portability & defense, D4 skill usability, D5 security & op risk, D6 code & doc quality, D7 dependency & footprint) with explicit ERR / WARN severity, 115-point scoring (pass line 90 + zero ERR), and an opt-in `--fix` workflow that always backs up first. Two depths: L1 static (~2 min) and L2 dryRun (~5 min, read-only hub + reachability checks). Strict red lines — read-only by default, never executes the audited skill's writes. Use when the user asks to "audit a skill", "check skill quality", "is this skill ready to ship", "lint my skill", or runs this tool by name. Triggers also: "审计这个 Skill"、"检查 Skill 质量"、"Skill 能上线吗"、 "skill-deep-audit"、"审一下 xxx skill"。
Songhonglei/build-better-skills/skills/skill-release-audit Skill
1★ repoPre-publish quality and safety auditor for AI agent skills (SKILL.md + scripts/ + references/ format used by Claude Code, Cursor, OpenAI Codex, GitHub Copilot, OpenClaw, ClawHub, and compatible SkillHub registries). Six static-check modules (no LLM, no network by default): (1) syntax and logic correctness, (2) feature completeness, (3) edge-case and error handling, (4) data safety (detects files written inside the skill dir that would be lost on update), (5) dependency declaration vs code, (6) SKILL.md documentation standards. Per-registry rule profiles via `--target`. Pure reporter — never edits your files, never publishes. Use when publishing a skill, modifying an existing skill, or diagnosing why a skill behaves unexpectedly — run it as the last machine-checkable gate before release. Trigger phrases: "skill release audit", "audit before publishing", "pre-release check", "release gate", "skill safety check", "发版前检查", "skill 发布检查", "审查这个 skill 能不能发版".
hootbu/llm-wiki-mind/skills/vault-sync Skill
1★ repoProjede yapılan değişikliği llm-wiki-mind vault'una sindir. Git log, commit mesajları ve diff'leri okur; etkilenen wiki sayfalarını (entities, concepts, decisions) günceller; raw/pr-discussions/ altına commit özet dosyası düşer. Proje-vault bağlantısı projenin CLAUDE.md'sinden okunur. Her commit, PR veya haftalık toplu senkron için kullanılır.
bydeng01/phd-application-skill/skills/phd-copilot Skill
1★ repoOrchestrate the end-to-end PhD application process and route to the right sub-skill. Use this as the front door whenever the user expresses a broad PhD-application intent without naming a specific step — e.g. "help me apply for PhDs", "be my PhD application copilot", "where am I with my applications and what should I do next?", "I want to start applying to PhD programs", or "what's the next thing I should work on?". Surveys the knowledge base to see what stage each opportunity is at, recommends the highest-value next action, and kicks off the matching skill. Trigger for orientation, planning, or whole-pipeline requests; defer to the specific skill when the user already names a concrete task (e.g. "write a cold email to Prof X" → outreach-email).
kostiantyn-matsebora/canopy/skills/canopy Skill
1★ repoAuthors, validates, improves, scaffolds, and refactors Canopy skills using a structured control-flow notation (IF, ELSE_IF, ELSE, SWITCH, CASE, DEFAULT, FOR_EACH, BREAK, END, ASK, SHOW_PLAN, VERIFY_EXPECTED). Use when creating, modifying, debugging, or reviewing skills under `.claude/skills/` or `.github/skills/`, when the user mentions canopy, ops, control-flow notation, or skill scaffolding, or asks to convert a regular skill into a Canopy skill (and vice versa). Supports both Claude Code and GitHub Copilot.
kennguyen887/agent-foundation/skills/keep-service-memory-lean Skill
1★ repoUse when a service OOMs / its tasks restart after a PR that added a dependency, when memory-tight replicas (small containers — e.g. 512MB/1GB) die under load or on deploy, or whenever the proposed fix for memory pressure is "just give it more RAM". Also use proactively when ADDING a heavy or optional library (cloud/vendor SDK, PDF/image/ML/crypto lib) to a long-running service. The discipline: keep per-process RSS lean by lazy-loading cold-path dependencies, and treat a memory regression as a code smell to hunt — not a reason to upsize the host. Covers the reservation-vs-actual-RSS + deploy-2x-surge mechanism that turns a small boot-memory regression into a full OOM outage. Principle-first; Node/ESM examples, ports to any language/orchestrator.
punkaze/skills/plugin/skills/worktree-setup Skill
1★ repoUse when starting an isolated task that needs a git worktree on a NEW branch — any project. Triggers — "set up a worktree for X", "start a worktree for this task", "isolate this work in a worktree", or before a subagent-driven / executing-plans run on a repo not already in a linked worktree. Reads a per-project config (in-repo .worktree.json or a registry under $CLAUDE_PLUGIN_DATA/projects) to decide single vs dual/multi-repo scope (identical branch names on coupled repos), cut from the right base branch, copy env files, and run the right install command. No-op when no config matches and you are not asked to init one.
yeshelloAB/investment-analysis-skills/skills/management-quality-agent Skill
1★ repoUse for any question about the people running a company: management quality, CEO track record, capital allocation skill (ROIC vs WACC, M&A history, buybacks), insider ownership and skin in the game, founder-led status, executive compensation and remuneration, insider buying/selling, strategic communication, or how leadership performed under pressure or through a downturn. Invoke whenever the user asks about whether management can be trusted with investor capital, even if framed as a company question rather than a management question explicitly. Do NOT use for moat/competitive advantage analysis, valuation, ESG/ethics assessments, or buy/sell decisions; those belong to other skills.
yeshelloAB/investment-analysis-skills/skills/stock-orchestrator Skill
1★ repoValues-neutral investment orchestrator combining financial fundamentals, competitive moat, management quality, accounting quality, and mechanical/retail dynamics into a single integrated verdict. No ESG or mandate filter applied: chain stock-values-overlay for mandate assessment. Triggers on: holistic requests, complete due diligence, "all the lenses", "full workflow", "run all agents", requests combining moat + management + valuation. Three lenses by default: (A) Fundamentals-only; (B) Base integrated verdict; (C) Risk-tolerant retail with momentum overlay and CONDITIONAL verdict. Suppress Lens C with "skip mechanical dynamics". Do NOT use for single-lens requests: moat-only → strategic-moat-agent; management-only → management-quality-agent; ESG-only → values-esg-agent; valuation/DCF-only → stock-investment-analysis.
yeshelloAB/investment-analysis-skills/skills/strategic-moat-agent Skill
1★ repoUse this skill for competitive moat and strategic durability analysis of any listed company or sector. Covers moat type and width, Porter's Five Forces, pricing power, barriers to entry, market position, TAM trajectory, disruption risk, and credible competitive threats. Returns a structured assessment ready for standalone use or multi-agent workflows. Trigger on questions about: competitive advantage, how defensible a business is, whether a company can hold its market position, barriers to entry in an industry, pricing power evidence, who the real competitors are, business model durability, disruption risk, industry dynamics, or strategic positioning. Do NOT use for: valuation or DCF analysis (use stock-investment-analysis), management or CEO quality (use management-quality-agent), ESG or ethics (use values-esg-agent), or full multi-lens stock assessments (use stock-orchestrator).
yeshelloAB/investment-analysis-skills/skills/values-esg-agent Skill
1★ repoAssesses any publicly listed company on values and ESG dimensions: governance & shareholder alignment, stakeholder treatment, ethical conduct, and environmental/sustainability practices. Returns dimension scores and an overall values alignment rating. Use this skill whenever the user asks about a company's ethics, ESG rating, controversies, governance quality, greenwashing, labour practices, environmental footprint, executive pay, insider ownership, stakeholder treatment, or whether they'd be "comfortable holding" a stock. Trigger on any question about company conduct, values alignment, or non-financial behaviour, even if "ESG" isn't mentioned explicitly. Do NOT use for: financial valuation (DCF, undervalued), competitive moat analysis, or combined strategic+values assessments (use stock-orchestrator instead). Management quality questions belong here if framed around ethics or governance; use management-quality-agent if focused on operational execution. When in doubt, use this skill.
wawoodwa/context-kit-skills/skills/context-kit-scaffold Skill
1★ repoScaffold a portable, name-agnostic starter kit for the next project -- any stack (Node.js, Python, PowerShell, ops/admin) -- by mining this project's accumulated docs, conventions, runbooks, agent-testing harness, and engineering strategies into a generic template tree under docs/genericcontext/. Produces a generic CLAUDE.md, stack-appropriate standards, five canonical runbook templates with empty lessons stubs, a sandboxed agent-smoke harness (restricted tester plus independent judge), an unattended-testing permission allowlist, a PORTING cheat-sheet, and a lessons-from-source-project.md that anonymizes and merges the portable strategies. Use whenever the operator wants to carry a project's hard-won patterns into a new one, or says 'generate generic context', 'scaffold next project from this one', 'extract docs as a starter kit', 'create a project template', or 'produce a generic CLAUDE.md'. Skip if the project has fewer than ~5 shipped changes, or back up first if docs/genericcontext/ already exists.
wawoodwa/context-kit-skills/skills/context-kit-steward Skill
1★ repoDesign-before-run meta-skill that keeps the Context Kit skill family coherent and evolving. It owns the shared conventions charter (references/CONVENTIONS.md) that every kit skill must honor -- work-start dating, newest-first ordering, multi-session concurrency, entity vocabulary, reference-don't-embed, hygiene, and skill-authoring limits -- audits each kit skill for drift from the charter, and harvests recurring lessons from real operating context kits to propose updates. Always produces an approval-gated proposal first and emits drop-in skill edits; it never auto-edits skills. Use whenever the operator wants to align, sync, audit, or evolve the context-kit skills, reconcile conventions across them, propagate one lesson into the whole suite, or asks 'keep my kit skills consistent', 'update the charter', 'do my context skills still agree', or 'propagate this across the kit skills'. Run it after changing any one kit skill, or after operating several kits, to catch cross-skill drift before it spreads.
napoler/skill-fix/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
ESR-style/compliance-copilot/skills/gdpr Skill
1★ repoGDPR compliance expert for developers. Explains EU General Data Protection Regulation obligations with article citations, scans code for violations (file:line specific), generates DPAs, privacy policies, DPIAs, and RoPAs. Activate when: writing code that handles EU personal data, designing APIs, reviewing data flows, writing privacy notices, assessing lawful basis, handling data subject requests, or planning breach response. Also useful for: "do I need consent for X?", "how do I implement the right to erasure?", "what are my GDPR penalties if I...?"
ESR-style/compliance-copilot/skills/hipaa Skill
1★ repoHIPAA compliance expert for developers and healthcare technology teams. Explains Privacy Rule, Security Rule, and Breach Notification Rule obligations with 45 CFR citations, scans code for PHI/ePHI handling violations (file:line specific), generates BAA templates, NPPs, risk analysis templates. Activate when: building healthcare software, handling patient data, implementing EHR/EMR integrations, working with FHIR APIs, designing ePHI storage or transmission, reviewing covered entity / business associate relationships, or planning breach response for a healthcare system.
ESR-style/compliance-copilot/skills/pci-dss Skill
1★ repoPCI DSS v4.0.1 compliance expert for developers. Explains PCI DSS requirements with specific rule citations, scans payment code for violations (file:line specific with severity), helps with CDE scoping, SAQ type selection, tokenization strategies, and v4.0 new requirements. Activate when: handling payment card data, implementing checkout flows, scoping cardholder data environment, choosing between tokenization and encryption, dealing with TLS requirements, implementing MFA for CDE access (Req 8.4.2 mandatory since March 2025), or dealing with payment page script integrity (Req 6.4.3 mandatory since March 2025). Current version: PCI DSS v4.0.1 — v3.2.1 retired March 31, 2024.
cerebrocybersolutions/libro/skills/memory-attribution-lint Skill
1★ repoValidate and auto-inject the 11-key provenance frontmatter contract on memory files at write time. Use when authoring memory entries, running lint passes on memory directories, or backfilling missing attribution fields. Enforces a uniform provenance schema (name, description, type, source_surface, host, tool, session_id, written_at_utc, source_path, confidence, lifecycle) so every memory entry is traceable to its origin surface, tool, and session.
cerebrocybersolutions/libro/skills/orchestrator-mode Skill
1★ repo[LEGACY 2026-07-26 — retired upstream, shipped for reference only. Do NOT invoke against a live API key: the cloud path bills a real request against a beta unexercised since April 2026, on superseded model pins. The durable tier heuristic is preserved in the banner below.] Sequential chain routing — decomposes a compound task into subtasks, routes each subtask to its optimal tier (via advisor-mode underneath), runs a quality-gate check after each step, and escalates to a higher tier on gate failure. Complements council-mode (parallel comparison). Orchestrator is the "route around failure" thesis applied sequentially: keep each subtask on the cheapest tier that passes, escalate only when the gate fails. Trigger on: "orchestrator mode", "chain this", "break this into subtasks", "route each step", "escalation pipeline", "run this as a chain", "decompose and route", "quality- gated routing", "sequential tier routing", "run the orchestrator".
cerebrocybersolutions/libro/skills/sessionstart Skill
1★ repoSession opening ritual v2.4 — adds Stage 0 session-continuity probe (short-circuits full brief on same-day reopens within 1h break window), single-shot Stage 2 brief loader (one Bash call surfaces dept CLAUDE.md, latest session, pending decisions, dashboard header, memory index, and infrastructure state), runs ground-truth verification against filesystem (including a recursion guard so corrections themselves verify before firing), auto-corrects stale memory, delivers a Department Head Brief plus Infrastructure Snapshot, captures session intent, and renders the same brief to an HTML archive. Use when the user types /sessionstart or says they're getting started, picking up where they left off, or starting a new session.
jajupmochi/agent-harness/setup/init-agent-config Skill
1★ repoScaffold a new project with the relevant subset of agent-harness rules, hooks, skills, recommendations, and templates. Asks about project type, language preferences, and context tags, then composes a project-specific CLAUDE.md, .claude/settings.json, and starter files. Use in a fresh or existing project to apply agent-harness conventions.
jajupmochi/agent-harness/skills/agent-config-adapter Skill
1★ repoAdapt an existing agent configuration or plugin to a new agent or model route. Use when moving agent-harness or another agent setup between Claude Code, Codex, Gemini, Cursor, local models, or non-native model backends such as DeepSeek routed through another agent.
jajupmochi/agent-harness/skills/agent-update-watcher Skill
1★ repoUse to keep up with the fast-moving agent ecosystem (new/updated CLIs, plugins, skills) WITHOUT burning tokens on constant checks. Declares the sources to watch in a config, checks them only when a minimum interval has elapsed, and reports ONLY what actually changed vs the recorded version — you then decide whether to adopt.
jajupmochi/agent-harness/skills/claude-desktop-sessions Skill
1★ repoUse when Claude Code sessions started in the terminal CLI don't appear in the Claude Desktop app's Code tab, when you want to hand a running CLI session to Desktop (and reach it from the phone via Remote Control), or when asked to "import/migrate my CLI sessions into the desktop app". Registers existing sessions in Desktop's sidebar by writing its per-session registry files, which point at the transcript store both apps already share — no transcript is copied or modified. Lists candidates numbered so you can import a chosen subset.