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
dominikwozniak/claude-kit/skills/session-handoff Skill
1★ repoCompact the current conversation into a handoff document so another agent (fresh Claude Code session, Codex, etc.) can continue the work. Trigger phrases: "session handoff", "handoff", "summarise for next session", "prepare context for another agent", "wrap up so someone can pick this up".
Yesterday-AI/skills/plugins/personal-agent/skills/agent-swarm Skill
1★ repoOrchestrate specialized coding agents in isolated worktrees for parallel development tasks.
Yesterday-AI/skills/plugins/personal-agent/skills/agentic-news-digest Skill
1★ repoEnd-to-end skill for curated team news digests. Covers the full pipeline: team inbox (manual submissions & co-authored drafts), source aggregation (RSS, Twitter, GitHub, web search), research & fact-checking, relevance scoring, article formatting (5 templates), and scheduled delivery to Slack/Discord/WhatsApp. Handles the critical handoff between conversational sessions (where links are received) and isolated cron sessions (where digests are built).
Yesterday-AI/skills/plugins/webflow/skills/webflow Skill
1★ repoManage Webflow sites via the official Webflow MCP server -- pages, CMS, assets, components, styles, variables, custom code, comments, localization, and publishing. Covers the headless Data API tools and the Designer API tools (which need the Webflow Designer open in the foreground). Use when: reading, auditing, or editing a Webflow site; building or duplicating pages; managing CMS collections or assets; or adding legal/marketing pages. This plugin ships the Webflow MCP server; just authenticate (OAuth).
Yesterday-AI/skills/skills/capabilities/memory/para-memory-files Skill
1★ repoFile-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.
Yesterday-AI/skills/skills/productivity/figma-console-mcp Skill
1★ repoConnect AI agents to Figma via the Figma Console MCP server. Enables design system extraction, UI component creation, variable/token management, visual debugging, FigJam boards, and Slides presentations. Use when an agent needs to read, create, or modify Figma designs programmatically.
Yesterday-AI/skills/skills/productivity/miro-board Skill
1★ repoCreate and read Miro board content via MCP tools. Diagrams (flowcharts, mindmaps, UML, ER), documents (markdown), tables, and context extraction. Use when: user asks to create or read diagrams, documents, or tables on Miro boards, or to extract structured content from existing boards. Requires: Miro MCP server connected (npx miro-mcp).
stephenrogan/leadership-skills/skills/agent-eval-design Skill
1★ repoDesigns practical evals for leadership and management agent skills, including realistic prompts, expected outputs, assertions, negative tests, boundary tests, and human grading rubrics. Use when creating or improving agent skills, workflows, or AI worker scorecards.
stephenrogan/leadership-skills/skills/agent-improvement-backlog Skill
1★ repoConverts agent failures, user corrections, eval misses, review notes, and workflow friction into a prioritized improvement backlog. Use when improving agent skills, prompts, tools, memory, evals, or operating procedures over time.
stephenrogan/leadership-skills/skills/agent-output-review Skill
1★ repoReviews AI agent outputs for correctness, evidence, completeness, safety, decision boundaries, and usability before a leader relies on them. Use when evaluating reports, drafts, code, research, strategy memos, customer responses, or autonomous agent deliverables.
stephenrogan/leadership-skills/skills/agent-performance-management Skill
1★ repoEvaluates AI agent performance over time using task outcomes, acceptance rate, revision causes, error patterns, latency, cost, risk incidents, and user trust. Use when managing AI workers, agent workflows, or autonomous loops as part of a leadership operating system.
stephenrogan/leadership-skills/skills/agent-risk-governance Skill
1★ repoCreates governance for AI agents with risk classes, approval gates, audit logs, access controls, red lines, incident response, and rollback rules. Use before deploying agents into leadership, customer, people, financial, or external-facing workflows.
stephenrogan/leadership-skills/skills/agent-workforce-architecture Skill
1★ repoDesigns a human-plus-agent workforce architecture with roles, work classes, autonomy levels, escalation paths, tool access, memory boundaries, and operating cadence. Use when a leader wants to scale management leverage through AI agents without creating chaos or shadow automation.
stephenrogan/leadership-skills/skills/context-memory-ops Skill
1★ repoDesigns context, memory, and knowledge flows for agent-managed work: what agents should know, retrieve, remember, forget, cite, and never store. Use when agent quality depends on durable context, sensitive information boundaries, or cross-session continuity.
stephenrogan/leadership-skills/skills/delegation-brief Skill
1★ repoConverts fuzzy delegation into a crisp ownership brief with outcome, context, constraints, decision rights, checkpoints, risks, and success criteria. Use when handing work to a direct report, project owner, team lead, or cross-functional partner.
stephenrogan/leadership-skills/skills/human-agent-team-design Skill
1★ repoDesigns how humans and AI agents collaborate inside a team, including roles, handoffs, rituals, shared artifacts, escalation norms, trust-building, and anti-patterns. Use when a manager is turning a conventional team into a human-agent operating unit.
qiuyiwu1989-star/openclaw-xiaokai-cto/skills/roles/10-seo-llm-engineer Skill
1★ repo搜索引擎优化、AI分发优化。触发场景:(1) 需要SEO优化 (2) 需要LLM可引用性优化 (3) 需要元标签/结构化数据 (4) 需要流量增长方案
barseghyanartur/dot-agents/skills/skill-authoring Skill
1★ repoCreate and modify repository-specific SKILL.md policy files in strict compliance with AGENTS.md and existing project skills.
Xrenya/safe-agent-skills/skills/context-engineering Skill
1★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Xrenya/safe-agent-skills/skills/using-agent-skills Skill
1★ repoDiscovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
zaixincheng174-ai/codex-agent-governance-skills/core/skills/handoff-brief Skill
1★ repoCreate a concise, redacted handoff brief for continuing work in a future session or another agent. Adapted from handoff; writes to temp or .scratch by default and preserves evidence and verdict boundaries.
zaixincheng174-ai/codex-agent-governance-skills/core/skills/prompt-eval-harness Skill
1★ repoBuild a constrained prompt evaluation harness with rubric, test cases, adversarial cases, prompt variants, scoring, failure analysis, evidence confidence, and final recommendation. Adapted from TerminalSkills prompt-tester; never replaces prompts or governance automatically.
zaixincheng174-ai/codex-agent-governance-skills/skills/agent-governance Skill
1★ repoAgent Governance Skill entrypoint. Points to the canonical Codex governance override and included governance skills without rewriting protected source content.
NjoyimPeguy/augments/plugins/augments/skills/dispatching-parallel-agents Skill
1★ repoUse when more than one piece of work sits in front of you and they don't touch the same files — separate failing tests, unrelated bugs, parallel research threads. Skip when one task needs another's output (sequence them with executing-plans), or when there's just one thing to do.
NjoyimPeguy/augments/plugins/augments/skills/handoff Skill
1★ repoUse when a session is ending or work is passing to a fresh session or another agent — so the next one resumes without re-deriving goal, state, decisions, and the next step. Skip for a finished, self-contained task that needs no continuation.
NjoyimPeguy/augments/skills/common/dispatching-parallel-agents Skill
1★ repoUse when more than one piece of work sits in front of you and they don't touch the same files — separate failing tests, unrelated bugs, parallel research threads. Skip when one task needs another's output (sequence them with executing-plans), or when there's just one thing to do.
NjoyimPeguy/augments/skills/common/handoff Skill
1★ repoUse when a session is ending or work is passing to a fresh session or another agent — so the next one resumes without re-deriving goal, state, decisions, and the next step. Skip for a finished, self-contained task that needs no continuation.
RubenGlez/harness/skills/handoff Skill
1★ repoCompact the current conversation into a handoff document so the next agent or session can continue without reading the history. Use at the end of any phase, or when the user is wrapping up and wants a clean starting point for the next session.
RubenGlez/harness/skills/write-a-skill Skill
1★ repoCreate new harness skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
nyxx-stack/agent-skills/skills/gpt-pro-bridge Skill
1★ repoPackage the repo and generate an optimized prompt for GPT 5.5 Pro (web) to analyze the codebase — for audits, debugging, refactors, architecture reviews, or any analysis task. GPT's output is constrained to produce a structured Claude Code execution prompt that can be pasted back and run locally. Use this when the user explicitly mentions GPT, ChatGPT, or GPT 5.5 Pro, says things like "ask GPT", "bridge to GPT", "GPT review", or wants to upload the repo to ChatGPT for analysis. Do NOT trigger for "second opinion" or "external review" requests that don't mention GPT specifically — those likely want a Codex or code-review workflow instead.
roebi/sw-dev-agent-framework/skills/orchestrate-sw-dev-en Skill
no license1★ repoOrchestrates the full software development lifecycle as an agentic pipeline. Delegates each phase to a focused sub-skill in order: gather requirements, design architecture, implement with TDD, review code, and release. Use when a user or agent wants to build a software project from a goal statement to a released artifact using a structured, test-driven process. Activate for trigger phrases like: "build a software project", "develop this from scratch", "orchestrate sw development", "run the full dev pipeline", or "implement this end to end".
zkeviny/MGC-Blackbox/mgc_skill/data-analyst-secure-suite Skill
no license1★ repoA secure data analysis workflow suite based on MGC Blackbox, providing credential protection, zero-exposure script application, script sealing collaboration, and knowledge management. Also includes a Data Analyst Agent system prompt template.
thevibethinker/vibe-thinker-skills/claude-code-window-primer Skill
no license1★ repoOptimizes Claude Code Pro/Max usage by priming the 5-hour rolling window early morning, ensuring resets align with peak work hours for maximum Opus availability.
thevibethinker/vibe-thinker-skills/prompt-to-skill Skill
no license1★ repoConvert complex prompts into reusable skills. Assess whether a prompt should become a skill, then scaffold a cleaner starter structure with stronger defaults and less template slop.
SamuelBostic29/claude-skills/skills/skill-builder Skill
1★ repoTurn a brief problem statement plus optional repo context into a complete, repo-quality skill scaffolded from the template. Use when asked to build, create, or scaffold a new skill, or when someone describes a recurring task they want handled as a reusable skill. Researches the repo, scopes to one job, fills every template layer, scaffolds evals — then stops for review.
Mission control agent graph workflows
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-agent-graph-workflows Skill
1★ repoDesign graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-agent-stuck Skill
1★ repoDiagnose a stuck Mission Control agent. Use when an agent shows no output, repeats errors, times out, asks for the same approval repeatedly, or stops making progress events.
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-agents-md Skill
1★ repoGenerate or review AGENTS.md from Mission Control understanding. Use when the user wants AGENTS.md proposed from the codebase map, existing instructions reviewed, or a safe draft prepared before writing.
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-approve Skill
1★ repoRelay Mission Control approvals and questions to the user. Use when there are pending command approvals, tool approvals, write permissions, Manager questions, swarm approvals, recovery decisions, or handoff review gates.
Mission control benchmark comparison
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-benchmark-comparison Skill
1★ repoCompare before-and-after performance evidence through Mission Control without turning benchmark claims into theater.
Mission control claude cli mode
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-claude-cli-mode Skill
1★ repoUse or prefer Claude CLI runner mode through Mission Control. Use when the user explicitly wants Claude CLI if configured and Codex should verify availability and fallback rather than assuming setup exists.
Mission control continue handoff
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-continue-handoff Skill
1★ repoContinue work after a Mission Control handoff without losing continuity. Use when the user wants another iteration, wants limitations preserved, or needs the next change request to build on the previous handoff and evidence.
Mission control evals observability
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-evals-observability Skill
1★ repoDesign or run evaluation, tracing, callback, telemetry, and regression-observability workflows for Mission Control agents.
Mission control handoff audit burst
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-handoff-audit-burst Skill
1★ repoUse when Mission Control should recommend a read-only handoff audit burst for run instructions, validation evidence, limitations, docs quality, and security caveats.
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-handoff Skill
1★ repoRetrieve and present the final Mission Control handoff. Use when the user asks for the finished result, final summary, what changed, how to run it, evidence, limitations, or next tasks.
Mission control knowledge base map
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-knowledge-base-map Skill
1★ repoBuild or inspect a graph-style map of docs, wiki pages, claims, entities, and relationships through Mission Control.
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-mcp-builder Skill
1★ repoDesign, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke tests.
Mission control memory state policy
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-memory-state-policy Skill
1★ repoDefine memory, state, checkpoints, resumability, and retention policy for Mission Control workflows and agents.
Mission control rag retrieval design
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-rag-retrieval-design Skill
1★ repoDesign retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.
Mission control subagent burst
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-subagent-burst Skill
1★ repoRecommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure diagnosis without replacing the normal worker system.
MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-swarm Skill
1★ repoInspect or adjust Mission Control swarm behavior. Use when the user wants to show the swarm plan, explain agent roles, scale up or down, change strategy, pause dynamic spawning, resume dynamic spawning, or inspect active agents.
Mission control agent contracts
MN755/Codex-Mission_Control/.codex/skills/mission-control-agent-contracts Skill
1★ repoShow or request Mission Control agent contracts. Use when the user wants to inspect a worker mission, allowed paths, forbidden paths, tools, validation obligations, stop conditions, or escalation rules.
Mission control agent graph workflows
MN755/Codex-Mission_Control/.codex/skills/mission-control-agent-graph-workflows Skill
1★ repoDesign graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.
MN755/Codex-Mission_Control/.codex/skills/mission-control-agent-stuck Skill
1★ repoDiagnose a stuck Mission Control agent. Use when an agent shows no output, repeats errors, times out, asks for the same approval repeatedly, or stops making progress events.
MN755/Codex-Mission_Control/.codex/skills/mission-control-agents-md Skill
1★ repoGenerate or review AGENTS.md from Mission Control understanding. Use when the user wants AGENTS.md proposed from the codebase map, existing instructions reviewed, or a safe draft prepared before writing.
MN755/Codex-Mission_Control/.codex/skills/mission-control-approve Skill
1★ repoRelay Mission Control approvals and questions to the user. Use when there are pending command approvals, tool approvals, write permissions, Manager questions, swarm approvals, recovery decisions, or handoff review gates.
Mission control benchmark comparison
MN755/Codex-Mission_Control/.codex/skills/mission-control-benchmark-comparison Skill
1★ repoCompare before-and-after performance evidence through Mission Control without turning benchmark claims into theater.
Mission control claude cli mode
MN755/Codex-Mission_Control/.codex/skills/mission-control-claude-cli-mode Skill
1★ repoUse or prefer Claude CLI runner mode through Mission Control. Use when the user explicitly wants Claude CLI if configured and Codex should verify availability and fallback rather than assuming setup exists.
Mission control continue handoff
MN755/Codex-Mission_Control/.codex/skills/mission-control-continue-handoff Skill
1★ repoContinue work after a Mission Control handoff without losing continuity. Use when the user wants another iteration, wants limitations preserved, or needs the next change request to build on the previous handoff and evidence.
Mission control evals observability
MN755/Codex-Mission_Control/.codex/skills/mission-control-evals-observability Skill
1★ repoDesign or run evaluation, tracing, callback, telemetry, and regression-observability workflows for Mission Control agents.