Loading…
Showing 5071–5100 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| quality-gatesopsmill/nornir-infrahubShared in-workflow quality gates for code/PR skills — the gate model, trust tiers, and the three primitives (evidence-before-done, independent judge, anti-gaming). DO NOT TRIGGER directly — referenced by consumer skills via relative path. | Stars: 12 | Updated | Claude CodeCodex | Verified | Install |
| workerDanielC000/loomThe operating doctrine for a Loom worker session — a session dispatched by a manager to implement ONE assigned task on an isolated worktree branch. Load at the start of any worker (Dev / Bugfix / Deep-Dive / etc.) agent. Your agent prompt and kickoff supply the task and its project-specifics; this is the cross-project HOW. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| oral-paper-skillAdkid-Zephyr/oral-paper-skillHelp authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection. Use for research storytelling, contribution framing, paper comparison, figure planning, or research retrospectives. Not an acceptance predictor or a routine grammar/citation formatter. | Stars: 599 | Updated | Claude CodeCodex | Verified | Install |
| cli-skillsllama-farm/llamafarmCLI best practices for LlamaFarm. Covers Cobra, Bubbletea, Lipgloss patterns for Go CLI development. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| common-skillsllama-farm/llamafarmBest practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| config-skillsllama-farm/llamafarmConfiguration module patterns for LlamaFarm. Covers Pydantic v2 models, JSONSchema generation, YAML processing, and validation. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| generate-subsystem-skillsllama-farm/llamafarmGenerate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| rag-skillsllama-farm/llamafarmRAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| reflectllama-farm/llamafarmAnalyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this". | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| runtime-skillsllama-farm/llamafarmUniversal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| server-skillsllama-farm/llamafarmServer-specific best practices for FastAPI, Celery, and Pydantic. Extends python-skills with framework-specific patterns. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| temp-filesllama-farm/llamafarmGuidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository. | Stars: 838 | Updated | Claude CodeCodex | Verified | Install |
| code-reviewjohnfkoo951/cmdspace-pluginsDeep code review skill. When triggered by '/code-review', '코드 리뷰', 'review this code', or '코드 품질 점검', this skill performs a thorough code quality review with structured findings, severity ratings, and actionable recommendations. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| decomposejohnfkoo951/cmdspace-pluginsTask decomposition skill. When triggered by '/decompose', '작업 분해', 'break down this task', or '서브태스크로 나눠줘', this skill takes a complex task and recursively decomposes it into atomic, testable subtasks with tier assignments and parallelization opportunities. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| deepsearchjohnfkoo951/cmdspace-pluginsMulti-strategy deep code search skill. When triggered by '/deepsearch', '깊은 검색', 'deep search', or '코드 찾아줘', this skill applies multiple search strategies — structural (AST-like pattern), textual (regex), semantic (by meaning), and historical (git history) — to find code that simple grep can't. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| estimatejohnfkoo951/cmdspace-pluginsTask estimation skill. When triggered by '/estimate', '추정해줘', 'estimate effort', or '이거 얼마나 복잡해?', this skill analyzes a development task and estimates complexity, agent tier distribution, and provides a confidence level for the estimate. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| focusjohnfkoo951/cmdspace-pluginsDeep focus mode using a single high-tier agent for complex problems requiring sustained reasoning. When triggered by '/focus', 'focus mode', '집중 모드', or '깊이 생각해줘', this skill dedicates a single Opus-tier agent to one problem without context switching, multi-agent coordination, or parallelization. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| hudjohnfkoo951/cmdspace-pluginsStatus display and session overview skill. When triggered by '/hud', '상태 표시', 'show status', or '현재 상황', this skill displays a dashboard-style overview of the current project state, active tasks, agent usage, and tier distribution. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| planjohnfkoo951/cmdspace-pluginsImplementation planning skill. When triggered by '/plan', '계획 세워줘', 'create a plan', or '구현 계획', this skill analyzes a development request and produces a structured execution plan with task decomposition, tier assignments, dependency graphs, and time/cost estimates. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| setuptrevhud/roteWalk the user through rote's first run: import the MCP servers they already use, compile one of their skills, and show that the compiled skill gives the same answer, faster and cheaper. Use when the user says "set up rote", "get started with rote", "try rote on my skills", "onboard me", or just installed rote and asks what to do first. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| arrows-post-callArrowsHQ/arrows-sales-skillsPost-call from Sales Skills by Arrows. Run right after a sales call: finds your most recent call on its own, then drafts the follow-up email in your voice and the CRM update from what was said (next step, stage, competitors mentioned, follow-up tasks with dates) using your CRM's own field names. Nothing goes into the CRM until you approve the exact changes; without CRM write access you get a copy-paste version. Adds resources to send only when the buyer asked for something. Use whenever someone says 'Run my Arrows post-call', 'Run post-call on [company]', 'write the follow-up from my last call', 'update the CRM from that meeting', 'log my call', or wants a recap email, CRM notes or follow-up tasks after a meeting. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-sales-methodologyArrowsHQ/arrows-sales-skillsSales methodology from Sales Skills by Arrows. Puts a team's methodology into Claude (MEDDIC or MEDDPICC, BANT, SPICED, Challenger, Sandler, or their own), or helps pick one, then checks the team against it. Reads the CRM, calls and email and saves arrows-methodology.md for every Sales Skill: each element, what counts as proof, its CRM field, what each stage needs, and what reps should ask. Then a visual report: which wins followed the methodology and which losses didn't, the win rate with and without it, how each part is done on open deals, deals moved ahead without what their stage needs, and a view by rep. Use whenever someone says 'Set up our sales methodology', 'add MEDDPICC to Claude', 'we use BANT, check deals against it', 'we don't have a methodology, help me pick one', 'how is my team doing against MEDDPICC', 'are reps following our methodology', or asks what reps should ask at each stage. For follow-ups and quiet deals, use the process gaps report. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-setupArrowsHQ/arrows-sales-skillsSetup for Sales Skills by Arrows. Reads the person's CRM, call recordings, email and calendar, then builds the sales profile every Sales Skill uses: their voice (how they write and talk, with real examples by situation), their sales process (stages, methodology, why they win and lose), their buyers and competitors, and how they work. Sales leaders also get team files their reps can add. About 5–10 minutes, two quick replies. Use this whenever someone says 'Build my sales profile', 'Refresh my sales profile' or 'Set up Sales Skills by Arrows', asks how to get Claude set up for themselves or their sales team, asks Claude to learn how they sell or write to buyers, wants the sales skills personalized to them or their team, or wants their team's sales process captured for Claude. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-win-loss-analysisArrowsHQ/arrows-sales-skillsWin-loss analysis from Sales Skills by Arrows. A deep read of closed deals (every won and lost deal counted, about 25 of each read end to end, calls and email) that answers why the team wins and why it loses: which segments win (size, source, industry, new vs. existing customers), the 3–5 moves that show up on wins and not on losses (with counts) and what's noise, where and why deals really die compared with what the CRM says, who was missing from the buying group on losses, which parts of the sales methodology predict a win, a rep comparison for leaders, and the 3 things to change this quarter. A shareable visual report. Use whenever someone says 'Run my Arrows win-loss analysis', 'why do we win and why do we lose', 'why are we losing deals', 'what do our wins have in common', 'what are our real loss reasons', 'win rate by segment', or wants a win-loss review for a quarterly or board meeting. For open deals slipping right now, use the process gaps report instead. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-post-callArrowsHQ/arrows-sales-skillsPost-call from Sales Skills by Arrows. Run right after a sales call: finds your most recent call on its own, then drafts the follow-up email in your voice and the CRM update from what was said (next step, stage, competitors mentioned, follow-up tasks with dates) using your CRM's own field names. Nothing goes into the CRM until you approve the exact changes; without CRM write access you get a copy-paste version. Adds resources to send only when the buyer asked for something. Use whenever someone says 'Run my Arrows post-call', 'Run post-call on [company]', 'write the follow-up from my last call', 'update the CRM from that meeting', 'log my call', or wants a recap email, CRM notes or follow-up tasks after a meeting. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-sales-methodologyArrowsHQ/arrows-sales-skillsSales methodology from Sales Skills by Arrows. Puts a team's methodology into Claude (MEDDIC or MEDDPICC, BANT, SPICED, Challenger, Sandler, or their own), or helps pick one, then checks the team against it. Reads the CRM, calls and email and saves arrows-methodology.md for every Sales Skill: each element, what counts as proof, its CRM field, what each stage needs, and what reps should ask. Then a visual report: which wins followed the methodology and which losses didn't, the win rate with and without it, how each part is done on open deals, deals moved ahead without what their stage needs, and a view by rep. Use whenever someone says 'Set up our sales methodology', 'add MEDDPICC to Claude', 'we use BANT, check deals against it', 'we don't have a methodology, help me pick one', 'how is my team doing against MEDDPICC', 'are reps following our methodology', or asks what reps should ask at each stage. For follow-ups and quiet deals, use the process gaps report. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-setupArrowsHQ/arrows-sales-skillsSetup for Sales Skills by Arrows. Reads the person's CRM, call recordings, email and calendar, then builds the sales profile every Sales Skill uses: their voice (how they write and talk, with real examples by situation), their sales process (stages, methodology, why they win and lose), their buyers and competitors, and how they work. Sales leaders also get team files their reps can add. About 5–10 minutes, two quick replies. Use this whenever someone says 'Build my sales profile', 'Refresh my sales profile' or 'Set up Sales Skills by Arrows', asks how to get Claude set up for themselves or their sales team, asks Claude to learn how they sell or write to buyers, wants the sales skills personalized to them or their team, or wants their team's sales process captured for Claude. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| arrows-win-loss-analysisArrowsHQ/arrows-sales-skillsWin-loss analysis from Sales Skills by Arrows. A deep read of closed deals (every won and lost deal counted, about 25 of each read end to end, calls and email) that answers why the team wins and why it loses: which segments win (size, source, industry, new vs. existing customers), the 3–5 moves that show up on wins and not on losses (with counts) and what's noise, where and why deals really die compared with what the CRM says, who was missing from the buying group on losses, which parts of the sales methodology predict a win, a rep comparison for leaders, and the 3 things to change this quarter. A shareable visual report. Use whenever someone says 'Run my Arrows win-loss analysis', 'why do we win and why do we lose', 'why are we losing deals', 'what do our wins have in common', 'what are our real loss reasons', 'win rate by segment', or wants a win-loss review for a quarterly or board meeting. For open deals slipping right now, use the process gaps report instead. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| running-exploration-cyclerichfrem/agent-plugins-skillsRuns the business exploration cycle end to end: starts or resumes a session (intake interview, session brief), enforces the Discovery Plan HARD-GATE, routes the four phases (Discovery Plan, Visual Blueprinting, Prototype, Handoff) to the sibling skills and keeps session state. Use when the user says "let's explore this idea", "I have an idea I want to explore", "help me plan this out", "start discovery", "resume my exploration", "where did we leave off", or starts any conversation about a need, problem or idea before building. Not for hardening an existing prototype (use reengineering-vibe-code) or for engineering build work. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| packaging-copilot-cowork-pluginsrichfrem/agent-plugins-skillsCreates, validates and prepares Microsoft 365 Copilot Cowork plugin App Packages containing Agent Skills and optional remote MCP connectors. Use when scaffolding, converting, validating, provisioning, packaging or sharing a Cowork plugin. Not for APM package creation or installation (use packaging-with-apm). | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |