agentsclimarketplace

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

  • Skill builder

    Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/skill-builder Skill

    1★ repo

    Complete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references, evaluate whether a skill is well-written, package a skill for distribution, optimize a skill's trigger description, or understand best practices for Agent Skills. Triggers include phrases like "build a skill", "write a SKILL.md", "make a skill for", "improve this skill", "skill format", "create an agent skill", "how do I write a skill", or any request to teach Claude a domain-specific capability through the skills system.

  • Workflow orchestrator

    Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/workflow-orchestrator Skill

    1★ repo

    Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)

  • Agent spawner

    Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/agent-spawner Skill

    1★ repo

    Creates and configures subagents dynamically with defined roles, constraints, and tool permissions

  • Memory manager

    Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/memory-manager Skill

    1★ repo

    Handles local persistence of research outputs, intermediate reasoning, and reusable knowledge chunks

  • Playwright mcp

    Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/playwright-mcp Skill

    1★ repo

    Complete guide for using Playwright MCP to automate browsers inside AI agent workflows. Use this skill whenever the agent needs to: navigate web pages, fill forms, click elements, take screenshots, mock API responses, manage cookies/localStorage, save auth state, generate Playwright test code, record video/traces, export PDFs, or handle any browser interaction. Triggers on phrases like "open browser", "automate this flow", "test this page", "fill this form", "screenshot this site", "mock the API", "save login state", "generate playwright test", "browser automation", "interact with the site", or any task requiring real browser control. Even if the user mentions just a URL and a goal, this skill applies.

  • Skill authoring

    Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/skill-authoring Skill

    1★ repo

    Create or revise a ForgeWeave skill — from identifying the repeatable job to writing the bundle and validating it with eval checks.

  • Skill builder

    Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/skill-builder Skill

    1★ repo

    Complete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references, evaluate whether a skill is well-written, package a skill for distribution, optimize a skill's trigger description, or understand best practices for Agent Skills. Triggers include phrases like "build a skill", "write a SKILL.md", "make a skill for", "improve this skill", "skill format", "create an agent skill", "how do I write a skill", or any request to teach Claude a domain-specific capability through the skills system.

  • Workflow orchestrator

    Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/workflow-orchestrator Skill

    1★ repo

    Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)

  • Scientific cli benchmark

    gjbex/scientific-computing-skills/skills/scientific-cli-benchmark Skill

    1★ repo

    Benchmark command-line applications for scientific computing and HPC workloads. Use this skill when measuring runtime, scaling, or placement effects for serial or multithreaded executables, especially when thread counts, OpenMP affinity, correctness checks, or repeatable benchmarking with hyperfine matter.

  • Persistent memory

    fengsihao23-eng/shen-hua/skills/persistent-memory Skill

    1★ repo

    Shen-Hua project memory manager. Use whenever Codex needs to initialize, read, repair, update, or summarize the project's `.agent/` working memory files, including PROJECT_BRIEF.md, PLAN.md, TASKS.md, LOG.md, DECISIONS.md, HANDOFF.md, and REVIEW_CHECKLIST.md for long-running tasks.

  • Shen hua

    fengsihao23-eng/shen-hua/skills/shen-hua Skill

    1★ repo

    Top-level Shen-Hua long-task agent entrypoint. Use when the user invokes `$shen-hua` or asks Codex to run the full Shen-Hua workflow for complex project work, including planning, runtime queueing, memory retrieval, subagent orchestration, verification, self-review, handoff, automation preparation, and external-sync preparation.

  • Subagent orchestrator

    fengsihao23-eng/shen-hua/skills/subagent-orchestrator Skill

    1★ repo

    Shen-Hua orchestration workflow for coordinating multiple Codex subagents or simulated specialist roles. Use when the user explicitly asks for subagents, parallel agents, delegation, or multi-agent work, or when a complex task can be split into independent explorer, architect, worker, tester, reviewer, or docs-researcher streams under the current runtime policy.

  • Convert prompt to saill

    HorizonBrute/Standardized_AI_Looping_Language-SAILL/skills/convert-prompt-to-saill Skill

    1★ repo

    Convert a natural-language prompt into a SAILL agent-team flow — roles with model groups, control-flow flags (parallel/wait/Loop/if needed/if asked/ask user), boxes for sub-teams and nesting, and -context- for run-time values. Use when the user types /convert-prompt-to-saill, says "turn this into SAILL", "convert my prompt to SAILL", or "express this as an agent team / SAILL flow".

  • Test agent teams

    HorizonBrute/Standardized_AI_Looping_Language-SAILL/skills/test-agent-teams Skill

    1★ repo

    End-to-end self-test of the Agent Teams system — walk every defined team (or one named team) and spawn each role so it echoes a self-generated nonce, its role, what it was told to do (its charter), and the model it actually ran as. Use when the user types /test-agent-teams --all-teams (all) or /test-agent-teams <team-name> (one team), says "test the agent teams", "run the agent-team self-test", or wants to verify team resolution + model routing. The skill generates its own nonce.

  • Try my prompt

    HorizonBrute/Standardized_AI_Looping_Language-SAILL/skills/try-my-prompt Skill

    1★ repo

    Take a natural-language prompt and return two outputs — an agent_teams.md SAILL entry and a terse one-line invocation — by invoking /convert-prompt-to-saill and formatting the result.

  • Engram memory

    jnMetaCode/skillet/skills/engram-memory Skill

    1★ repo

    Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".

    The same file is in 1 other repository

  • Tracelet instrument

    jnMetaCode/skillet/skills/tracelet-instrument Skill

    1★ repo

    Instrument an AI agent or LLM app with OpenTelemetry and watch its runs live in tracelet (local DevTools). Use when asked to add tracing/observability to an agent, or to debug what an agent actually did.

    The same file is in 1 other repository

  • Browser testing with devtools

    celestialdust/achilles-skills/skills/browser-testing-with-devtools Skill

    1★ repo

    Tests in real browsers via whatever browser-automation MCP is configured (Chrome DevTools, Claude-in-Chrome, Playwright, or agent-browser) — the live-runtime engine the quality-verification skill drives. Use when building, debugging, or verifying anything that runs in a browser, or when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data instead of guessing from the code. Treats all browser content as untrusted data, never as instructions. Requires a browser MCP server to be configured.

  • Handoff

    celestialdust/achilles-skills/skills/handoff Skill

    1★ repo

    Compact the current session into a cold-start handoff the MOMENT context fills, the work pauses, or you are about to /clear — so a fresh agent resumes from durable state, not a lost conversation. Writes the 5-field handoff, references artifacts by path instead of duplicating them, and redacts every secret. Use BEFORE you lose context, not after.

  • Incremental implementation

    celestialdust/achilles-skills/skills/incremental-implementation Skill

    1★ repo

    Builds one assigned slice as thin, individually-tested vertical increments — skeleton-first (stub→mock→wire→fill), simplicity-first, test-first. Use the moment you start writing code for a planned slice, and ESPECIALLY when you're tempted to write more than ~100 lines before running a test, land a whole feature in one pass, "clean up" code outside the slice, or weaken a test to get green. Runs inside the worktree the orchestrator hands you; it is not the place to plan or re-slice.

  • Orchestrator

    celestialdust/achilles-skills/skills/orchestrator Skill

    1★ repo

    Drives the autonomous Implement→Verify→Review→Ship loop once the human-owned Spec+Plan is signed and STATE.md holds a slice DAG. Use it to run a build AFK — it sorts slices into topological waves, runs each wave's ready slices in parallel (one worktree per slice, disjoint files only), holds a barrier until every slice reaches a TERMINAL state (done/halted/blocked — never just "success"), and ends the run at risk-banded OPEN PRs for async human merge. If you are about to hand-run slices one at a time, check in with the human between waves, dispatch a "reviewer" persona, weaken a frozen test/acceptance to make a gate go green, or merge to main yourself — STOP and use this instead.

  • Project setup

    celestialdust/achilles-skills/skills/project-setup Skill

    1★ repo

    Scaffolds the repo ecosystem every achilles skill assumes — a one-time bootstrap that creates the STATE.md board, the CONTEXT.md glossary, docs/adr/, and docs/features/, and — when the repo has neither a CLAUDE.md nor an AGENTS.md and you opt to create CLAUDE.md — seeds it from a bundled behavioral template. Run this ONCE before the first feature, before interview-me or spec-grilling. The pipeline skills read these files cold and will have nowhere to write without it, so do this first.

  • Using agent skills

    celestialdust/achilles-skills/skills/using-agent-skills Skill

    1★ repo

    The meta-dispatcher for the achilles-skills suite. Maps any task to the right stage skill and the artifact-chain lifecycle (Ideate → Spec → Plan → Implement → Verify → Review → Ship). Use this FIRST — at the start of every session and whenever you are unsure which skill applies — before writing any plan, spec, or code. Acting without consulting this index is how the wrong skill gets run and the artifact chain gets skipped.

  • Worktree

    celestialdust/achilles-skills/skills/worktree Skill

    1★ repo

    Use the instant a slice is about to be implemented and needs its own isolated, clean-baseline workspace — BEFORE any code is written. Detects existing isolation first (never double-nests, never fights the harness), prefers a native worktree tool over raw `git worktree add`, installs deps, and proves the test baseline is green so new failures are distinguishable from old ones. If you are about to run `git worktree add` without checking whether you are already isolated or a native tool exists, or about to start implementing without a verified-clean baseline — STOP and use this.

  • Context engineering

    codexskills/agent-forge/skills/context-engineering Skill

    no license1★ repo

    Optimize agent context setup for maximum performance, accuracy, and cost-efficiency across long sessions and complex tasks.

  • Using agent skills

    codexskills/agent-forge/skills/using-agent-skills Skill

    no license1★ repo

    Production-grade AI agent skills — enhanced alternative to addyosmani/agent-skills. 23 lifecycle skills for Define, Plan, Build, Verify, Review, Ship. Works with OpenCode, Claude Code, Codex, Cursor, Gemini CLI.

  • Context engineering

    shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/context-engineering Skill

    1★ repo

    Optimizes 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.

    The same file is in 12 other repositories

  • Using agent skills

    shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/using-agent-skills Skill

    1★ repo

    Discovers 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.

    The same file is in 1 other repository

  • Handoff

    dylanmccavitt/loom/tests/fixtures/skills/bad-global-collision/.agents/skills/handoff Skill

    1★ repo

    Use when testing a project skill that collides with a global skill.

  • Handoff

    dylanmccavitt/loom/tests/fixtures/skills/global/.agents/skills/handoff Skill

    1★ repo

    Use when testing collision with an existing global handoff skill.

  • Ai workflow orchestrator

    LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/ai-workflow-orchestrator Skill

    1★ repo

    Use when guiding a developer through an AI-assisted software development workflow as a pure orchestrator. Holds the picture, decomposes work into lanes, and delegates every concrete task to a Claude Code subagent attached to a tmux window in a named session (default `tutor`) or to a Hermes Kanban card. Does not edit, test, build, commit, or push itself. Trusts but verifies via disk-level audit.

  • Live qa

    LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/live-qa Skill

    1★ repo

    Exploratory QA of a running app by driving a real browser like a user via the Playwright MCP server. Use when the user wants to "QA" a feature live, walk a flow as a real user, smoke-test before a PR, or find issues that scripted specs miss. Complements deterministic Playwright specs — this is the human-like exploration layer.

  • Meta agent schema

    glyphs-ai/glyph/first-party/skills/meta-agent-schema Skill

    1★ repo

    Schema for glyph-compatible agents, skills, and MCPs — frontmatter, layout, naming, dependency origins, MCP cross-platform rules, runtime-agnostic file references, CHANGELOG conventions

  • Remediate suggest

    0xkangl/skills/skills/remediate-suggest Skill

    no license1★ repo

    手动触发的「审计问题清单 → 推荐修复方案」分析器。接收 codebase-audit 生成的 issues-report 文档,按问题根因/维度把 findings 分组, 每组派一个独立 subagent——加载 code-conventions skill 作规范基准,对每条 finding 做存在性复核(含「关联问题修复后是否仍存在」), 再产出标准推荐方案结构的 suggest 字段(整体方案 + 落点 + 实现细节与注意事项 + 改动量)。 主 agent 合并产出与输入同目录的 <issues 文档名>-remediation.md(带 suggest 的镜像)。 同目录已有该产物时自动进入追加模式——只补原报告里尚未进 remediation 的 finding,原地更新; 同目录存在未合并的 <issues 文档名>-remediations/ 片段时自动续传——复用有效片段,只重派缺失的组。 只分析不修复:不改被审代码、不跑测试、不提交;产物可交下游 remediate-apply skill 逐条落地修复。

  • Handoff continue

    orzilca/agent-handoff-skills/dist/claude/handoff-continue Skill

    1★ repo

    Use in a fresh session to resume work captured by handoff-prepare. Reads a handoff file and continues from its "Next steps". Takes an optional argument — a file path, or a name to substring-match against handoff filenames; with no argument, loads the newest handoff. Triggers on "handoff-continue", "resume handoff", "continue the handoff".

  • Handoff prep continue

    orzilca/agent-handoff-skills/dist/claude/handoff-prep-continue Skill

    1★ repo

    Prepare a handoff AND arm auto-resume in this same CLI - after the user clears the session, the next session loads the handoff automatically. Use when handing off and continuing here, not in another agent. Triggers on "prepc", "prep-continue", "handoff and continue here", "handoff and keep going here".

  • Handoff prepare

    orzilca/agent-handoff-skills/dist/claude/handoff-prepare Skill

    1★ repo

    Use when the context window is getting large and the user wants to continue in a fresh session. Captures everything done this session (changes, decisions, caveats, next steps) into a self-contained handoff file, then tells the user to start a fresh session and run handoff-continue. Triggers on "handoff", "prepare handoff", "continue in a new session", "context is too big", "compact and continue".

  • Agent bus register

    adjcjh777/agent-bus-skills/skills/agent-bus-register Skill

    no license1★ repo

    Register the current Codex session with the local Codex Agent Bus and claim queued or pending tasks for this session. Use when the user asks to join, register, identify, or name this agent; set the current session as planner, executor, tester, reviewer, or another role; hot-load queued work for a newly opened session; or prepare this session for Agent Bus list and inbox workflows.

  • Agent bus team

    adjcjh777/agent-bus-skills/skills/agent-bus-team Skill

    no license1★ repo

    Create and manage role-based Agent Bus project teams. Use when the user asks to create, join, launch, attach, inspect, or dispatch an Agent Bus team; define planner, executor, tester, reviewer, scout, or role aliases; bootstrap future agents; spawn subagents for roles; or route role-scoped work through Agent Bus.

  • Agent bus

    adjcjh777/agent-bus-skills/skills/agent-bus Skill

    no license1★ repo

    Route Agent Bus multi-agent coordination workflows across registration, delegation, teams, and diagnostics. Use when the user asks generally about Agent Bus, multi-agent coordination, cross-agent communication, planner/executor/tester/reviewer collaboration, or when no narrower Agent Bus skill clearly fits.

  • Github notification orchestrator

    JordanTheJet/agentday-zeroclaw/.claude/skills/github-notification-orchestrator Skill

    1★ repo

    Multi-agent GitHub notification orchestrator for ZeroClaw. Use this whenever the user wants to work through their whole notification inbox at once — not just see it, but plan and draft a response to every item. It fetches unread notifications via gh, makes a routing plan, fans out one subagent per notification using bundled agent profiles (PR review, issue, mention, authored-thread, CI failure), runs an adversarial verifier over high-stakes drafts, and a summarizer builds a dated INDEX sorted newest-to-oldest linking every per-item report. It also composes with the repo's specialist skills — routing PR reviews to github-pr-review-session and issue lifecycle to github-issue-triage. Trigger on: 'orchestrate my notifications', 'answer all my notifications', 'draft responses to my whole inbox', 'build my daily notification digest', 'fan out subagents on my notifications', 'work through my entire inbox'. Drafts only — it never posts comments, reviews, or marks anything read without explicit approval.

  • Agent context engineering

    SylphxAI/skills/skills/agent-context-engineering Skill

    1★ repo

    Design a Context and Memory Contract for how agents acquire, rank, compile, remember, invalidate, and hand off information, including compaction, provenance, freshness, and privacy. Not ordinary doc retrieval, prompt wording alone, planning algorithms, or live work-ledger ops.

  • Agent first development standard

    SylphxAI/skills/skills/agent-first-development-standard Skill

    1★ repo

    No-human parallel development packets, change attribution, collision scopes, and machine-verifiable acceptance. Use when defining or running multi-agent software delivery without a human review dependency. Do not use for a small local edit or live Work Graph operations.

  • Agent native standard

    SylphxAI/skills/skills/agent-native-standard Skill

    1★ repo

    Apply agent-native product constraints for queryable typed state, schema-derived tools, recoverable workflows, delegation, durable context, and model/tool/agent-run traces with protected operator diagnostics. Use when designing a product, API, or workflow that agents must operate directly and recoverably. Do not use for ordinary automation, generic service observability, or product analytics without an agent-facing contract.

  • Agent planning system review

    SylphxAI/skills/skills/agent-planning-system-review Skill

    1★ repo

    Design or audit the planning and control mechanism of an autonomous agent or multi-step agent workflow, producing an Agent Planning and Control Contract. Use when choosing or evaluating BDI, HTN, partial-order or causal-link planning, Plan-and-Execute, ReAct, receding-horizon control, bounded search, replanning, execution monitoring, or stop conditions. Do not use merely to plan one ordinary task, schedule a current work queue, design agent memory, or review a finished code candidate.

  • Agent system improvement

    SylphxAI/skills/skills/agent-system-improvement Skill

    1★ repo

    Improve a recurring agent-system failure through a causal Learning Change Record, controlled intervention, replay or holdout evidence, promotion criteria, and recurrence monitoring. Use when prompts, Skills, context assembly, tools, evals, coordination, or agent workflows repeatedly produce the same error, cost, delay, or weak outcome. Do not use for a one-off product-code bug, live incident response, ordinary task planning, or evaluation of one already-defined Skill candidate alone.

  • Ai product risk review

    SylphxAI/skills/skills/ai-product-risk-review Skill

    1★ repo

    Design or audit one AI product behavior and launch contract covering the user job, AI necessity, model role, autonomy and action rights, data use, affected parties, failure and abuse, UX disclosure, fallback, cost and latency, support, evidence dependencies, and release boundaries. Use when an assistant, copilot, generator, classifier, recommender, or agent needs a product-risk dossier. Do not use for eval implementation, adversarial red teaming, security threat modeling, provider selection, a whole-product blueprint, or incident response.

  • Prompt architecture

    SylphxAI/skills/skills/prompt-architecture Skill

    1★ repo

    Design or audit durable agent instructions, runtime constitutions, Skill metadata, agent-to-agent and subagent briefs, bootstrap/install prompts, and instruction hierarchy without duplicating source policy. Use when creating, reviewing, projecting, or restructuring agent prompt architecture. Do not use for ordinary user-facing copy or one task's content brief alone.

  • Self feeding agent loop standard

    SylphxAI/skills/skills/self-feeding-agent-loop-standard Skill

    1★ repo

    Public agent skills from SylphxAI — standards, product procedures, and one-command sync for Codex, Claude Code, and Grok Build

  • Skill eval designer

    SylphxAI/skills/skills/skill-eval-designer Skill

    1★ repo

    Design or audit a falsifiable, exact-candidate runtime auto-injection and behavior evaluation for one Agent Skill or a complete catalog: positive, near-neighbour, abstention, compound injection, hidden tasks, controls, independent model families, deterministic artifact and safety checks, provenance, uncertainty, replay, and regressions. Use when proving incremental behavior, not when authoring a skill or building a router.

  • Gpt engineer

    SYMBaiEX/skills/skills/gpt-engineer Skill

    1★ repo

    Own a software-engineering outcome end to end with a provider-routed agent fleet: research the real codebase, turn findings into implementation waves, edit safely, test and inspect the result, and persist through gap-closing cycles until the authorized goal is complete. Use when the user asks for a GPT engineer, autonomous engineer, complete feature or repository build, broad remediation, research plus implementation, multi-agent coding, explicit subagents, different models, or a durable /goal-style engineering run. Prefer confirmed Codex Sol, Terra, and Luna profiles or Claude model-specific profiles; preflight routing and never silently present same-model children as a model-diverse fleet.

    The same file is in 1 other repository

  • Gpt orchestration auto

    SYMBaiEX/skills/skills/gpt-orchestration-auto Skill

    1★ repo

    Autonomously pursue a sustained engineering outcome through repeated research, planning, multi-agent implementation, integration, verification, and gap-closing cycles. Use when the user asks for a /goal-style run, says do not stop, finish the whole codebase, research and build autonomously, babysit an outcome, or wants the orchestrator to keep working across continuations until genuinely complete. Use native goal tracking when explicitly requested and available; otherwise maintain an equivalent goal ledger without inventing tool capabilities or broadening authority.

    The same file is in 1 other repository

  • Gpt orchestration build

    SYMBaiEX/skills/skills/gpt-orchestration-build Skill

    1★ repo

    Turn an existing audit, finding list, issue set, review, failing-test report, or implementation plan into completed, verified code through a coordinated agent fleet. Use when the user asks to build from findings, implement every audit item, finish a known backlog, remediate review results, or continue from research without repeating the whole investigation. Validate each finding, preserve repository state, assign non-overlapping writers, integrate in dependency order, and track every item to an explicit disposition.

    The same file is in 1 other repository

  • Gpt orchestration

    SYMBaiEX/skills/skills/gpt-orchestration Skill

    1★ repo

    Coordinate hierarchical coding-agent fleets for repository-wide audits, implementation sprints, migrations, and complex work that benefits from parallel specialists. Use when a user asks for subagents, a fleet, parallel delegation, GPT-5.6 Sol, Terra, or Luna routing, broad codebase completion, or independent implementation and verification passes. Enforce bounded ownership, concurrency-aware waves, dirty-worktree safety, runtime-honest model handling, and evidence-based integration.

    The same file is in 1 other repository

  • Handoff

    IvanGomezMartinez/MatStudyLab/.agents/skills/handoff Skill

    1★ repo

    Compact the current conversation into a handoff document for another agent to pick up.

    The same file is in 11 other repositories

  • Skill authoring workflow

    2702207741-dev/agent-skills-pipeline/skill-authoring-workflow Skill

    1★ repo

    Use when the user says "写个 skill""创建 SKILL.md""这个流程变成 skill" or any new skill creation request. Use when the user provides a design document and asks to implement it as a skill. Do NOT use for small edits to existing skills or questions about skill format — answer those directly.

  • Skill pipeline orchestrator

    2702207741-dev/agent-skills-pipeline/skill-pipeline-orchestrator Skill

    1★ repo

    Use when the user says "一键发布 skill", "走完整 pipeline", "发布这个 skill", or "skill 上线". Use when a new skill has passed review and is ready for release across one or more agent platforms.

  • Loop verify

    ksed8/cc-loopkit/.claude/skills/loop-verify Skill

    1★ repo

    Outer-loop verification step for run.sh — checks the repo against PROMPT.md and .claude/IMPLEMENTATION_PLAN.md, runs mechanical checks, invokes the verifier subagent, and records the verdict. Invoked externally as `/loop-verify` by run.sh, once per outer-loop iteration. Not for ad hoc use — during interactive work, invoke the `verifier` subagent directly instead.

  • Session handoff

    bglglzd/agent-workflows/plugins/agent-workflows/skills/session-handoff Skill

    1★ repo

    Capture a durable, privacy-safe handoff at the end of a coding or research session. Use when Codex must preserve repository state, decisions, validation results, blockers, and exact next steps so the next human or AI agent can resume without rediscovering context.

  • Prepare agent compatible repository

    lilabrooks/lila-agent-skills/skills/prepare-agent-compatible-repository Skill

    1★ repo

    Audit, create, and reconcile repository instructions and agent-facing configuration so a project works consistently with Codex and Claude Code. Use when asked to add or review AGENTS.md, AGENTS.override.md, CLAUDE.md, CLAUDE.local.md, .claude rules or settings, .codex project configuration, shared Agent Skills packages, nested instruction scope, setup and verification commands, or cross-agent repository readiness. Keep shared rules in one place, preserve intentional host differences, and distinguish behavioral guidance from enforced controls.