Context & AI engineering
25,745 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
richfrem/agent-plugins-skills/plugins/exploration-cycle-plugin/skills/vibe-to-speckit-superpowers Skill
5★ repoEnd-to-end pipeline that transforms an undocumented vibe-coded prototype into a Spec Kit-compatible specification package and a Superpowers-ready implementation handoff, including characterization tests, domain extraction, architecture decisions, task breakdown, TDD strategy, worktree guidance, and certification reports.
richfrem/agent-plugins-skills/plugins/obsidian-wiki-engine/skills/obsidian-query-agent Skill
5★ repoProgressive-disclosure query against the Obsidian LLM wiki. Returns RLM summary first, expands to bullets, then full wiki node on demand. Use when looking up concepts, searching the wiki, or getting instant context from the knowledge graph.
richfrem/agent-plugins-skills/plugins/obsidian-wiki-engine/skills/obsidian-rlm-distiller Skill
5★ repoDistills wiki source files into the RLM summary layer (summary.md, bullets.md, deep.md) using the cheapest available LLM CLI. Routes to Copilot gpt-5-mini first, then Claude Haiku, then Gemini Flash. Never uses Ollama. Use when wiki nodes need RLM summaries generated or refreshed.
richfrem/agent-plugins-skills/plugins/plugin-manager/skills/plugin-installer Skill
5★ repoInstalls plugin components (skills, commands/workflows, rules, hooks, MCP) into the .agents/ central store and symlinks them to agent environments that require it (.claude/). DEFAULT method: run plugin_add.py for an interactive require it (.claude/). DEFAULT method: run plugin_add.py (the primary TUI and headless orchestrator) which internally delegates to plugin_installer.py (the execution engine) for the actual OS-level installation. Trigger when a user says "install plugin", "deploy plugin", "add plugin", "install from GitHub", or "sync plugin to agents".
AnmarHani/SwarmVault/skills/swarm-design-ui Skill
5★ repoUI/UX design phase — propose an intentional design system (pattern, brand, color, typography, spacing, atomic components) with the user, offering distinct directions and per-page layout options, for any interface type: Web, Mobile, Desktop, TUI, or CLI. Use when the SRS declares a user interface, when defining a design system or visual identity, choosing layouts, or reviewing UI work against UX laws.
AnmarHani/SwarmVault/skills/swarm-design Skill
5★ repoSystem design phase — architecture, tech-stack options, module boundaries, data model, and ADRs from a validated SRS. Use after requirements are validated, when choosing a tech stack, designing system structure/APIs/data models, or recording an architecture decision.
AnmarHani/SwarmVault/skills/swarm-eject Skill
5★ repoDisconnect a project from SwarmVault and choose what happens to its knowledge — keep it, export it into the repo, or delete it. Use when the user wants to stop using SwarmVault here, remove the vault wiring, uninstall the framework from a project, offboard or archive a project, or delete a project's vault data.
AnmarHani/SwarmVault/skills/swarm-flow Skill
5★ repoThe SDLC router — figures out where a project stands and runs the right phase. Use at the START of any work in a SwarmVault project: continuing/resuming a project, starting a new one, "what's next", or before writing any feature code, spec, design, or ticket. Also use when unsure which phase (requirements, design, implementation, review) comes next. Resume-from-anywhere on any platform.
AnmarHani/SwarmVault/skills/swarm-implement Skill
5★ repoImplementation phase — turn a validated design into dependency-ordered tickets, then work them as one of N parallel agents with atomic claims, model tiering, and tests-in-ticket definition of done. Use to plan tickets from a design, pick up/continue implementation work, coordinate parallel agents, or check what to build next.
AnmarHani/SwarmVault/skills/swarm-init Skill
5★ repoStart a new project connected to the SwarmVault — register it, wire platform adapters, offer git init, set vault-as-default. Use when starting a new project, connecting a project to the vault, or when the user asks to set up SwarmVault in a directory.
AnmarHani/SwarmVault/skills/swarm-migrate Skill
5★ repoBring existing projects into the SwarmVault — register, mirror docs, optionally mine the repo into SDLC artifacts and resume the flow mid-phase (brownfield adoption). Use when the user wants existing projects migrated/connected to the vault, or an existing codebase placed into the SDLC flow.
AnmarHani/SwarmVault/skills/swarm-orchestrate Skill
5★ repoOptional autonomy control plane — set up (which platforms you have + a pace: budget/balanced/fast), launch, monitor, recover, or stop local CLI-agent workers (Claude Code and Codex verified; Gemini, OpenCode, Droid, Cursor, Copilot best-effort; any other agent via a launch-command template) through SwarmVault's durable supervisor, with budget- and model-fit-aware task assignment, a cross-platform observability board (usage/limits, tokens, per-agent progress), safe-state context compaction, and usage-limit continuation so long projects survive quota resets. Use when the user asks to orchestrate agents, enable/disable a supervisor, dispatch work across platforms, assign work by usage limits or model strength, view or monitor a live board of all agents, add a launch adapter, compact/continue past a usage limit, or recover idle work.
AnmarHani/SwarmVault/skills/swarm-review Skill
5★ repoMilestone review sweep — a strong model audits everything since the last sweep against the spec: requirement fulfillment, standards, simplification, risk. Use when a milestone's tickets are done, before opening the next milestone, or when asked to review/audit/validate completed work.
AnmarHani/SwarmVault/skills/swarm-skill-forge Skill
5★ repoAuthor new high-quality skills that trigger reliably and stay lean. Use when creating or editing a skill, packaging a workflow as a skill, or deciding whether something should be a skill at all.
AnmarHani/SwarmVault/skills/swarm-spec Skill
5★ repoRequirements phase — a clarifying, options-first stakeholder interview that removes confusion and assumptions (not a relentless grilling) and produces a validated SRS + per-feature specs with EARS acceptance criteria and ISO 25010 NFRs. Use to start a new project's requirements, gather/analyze/specify/validate requirements, stress-test a plan, or mine requirements from an existing codebase (brownfield). Also handles requirement changes after validation.
AnmarHani/SwarmVault/skills/swarm-vault Skill
5★ repoThe vault contract — how any agent reads, writes, and queries the SwarmVault. Use at the start of work in any vault-connected project, before exploring the repo, when deciding where to record memory/plans/decisions/sessions, when handing off between sessions or agents, or whenever unsure how the vault works.
AnmarHani/SwarmVault/skills/swarm-write Skill
5★ repoWriting for humans — any end-user-facing text, in any language. READMEs, landing pages, blog posts, social posts, marketing copy, release notes, docs, and UI microcopy (tooltips, buttons, empty states, error messages). Use when asked to write, rewrite, polish, or humanize copy, when text sounds robotic or AI-generated, when defining a voice or tone, and — unprompted — whenever you are about to produce any string a real user will read.
SkillMedev/skills/skills/agent-orchestration Skill
5★ repoDesigns reliable multi-agent LLM systems - choosing a topology, writing handoff contracts between agents, deciding what runs in parallel vs series, and setting context, retry, and cost budgets that stop runaway loops. Use when someone asks "should I split this into multiple agents", "my agents keep looping", "how do I pass context between agents", "orchestrator vs pipeline vs router", or is architecting an agent workflow. Do NOT use for tuning a single prompt - use prompt-engineer instead; do NOT use for measuring agent output quality - use llm-evaluation instead; for making a product agent-operable end to end, use build-on-agent-native.
The same file is in 1 other repository
SkillMedev/skills/skills/build-on-agent-native Skill
5★ repoBuild an application on Builder.io's open-source Agent-Native framework (@agent-native/core) - the model where the agent acts inside the app as a first-class peer to the UI, sharing one set of actions and one database with the interface. Covers the core primitives (actions as the single source of truth, SQL-backed shared state, real-time sync, context-awareness, agent-to-agent, automations, the skills convention), the CLI and cloneable-template workflow, and where to read version-matched docs. Use when someone says "build an agent-native app", "use the agent-native framework", "defineAction", "@agent-native/core", "clone an agent-native template", "make the agent a peer to my UI", or "an app where the agent and the UI call the same actions". Do NOT use for authoring generic Claude Agent Skills / SKILL.md files - that is skill-creator; do NOT use for building a standalone MCP server unrelated to this framework - that is the MCP-builder path; do NOT use for plain Next.js / React scaffolding with no agent runtime.
SkillMedev/skills/skills/design-handoff-doc Skill
5★ repoWrites a complete design handoff document covering components, design tokens, interaction states, and edge cases for engineering implementation. Use when handing off a feature or screen to developers.
The same file is in 1 other repository
SkillMedev/skills/skills/kb-article-writer Skill
5★ repoTurns a resolved support ticket into a clear, searchable knowledge-base or help center article. Use when someone asks "write a KB article from this resolved ticket", "turn these resolved tickets into help center articles", or "write an internal knowledge base article for our support agents" - converting ticket resolutions into self-service documentation that deflects future tickets. Do NOT use for writing user-facing how-to guides from scratch - use help-documentation instead.
The same file is in 1 other repository
SkillMedev/skills/skills/llm-evaluation Skill
5★ repoBuilds evaluation harnesses for LLM products - golden datasets, deterministic checks, calibrated LLM-as-judge rubrics, and CI regression gates that turn "seems good" into a tracked number. Use when someone asks "how do I know this prompt change didn't break anything", "set up evals for my RAG pipeline", "is LLM-as-judge reliable", "why did quality drop after the model swap", or is shipping an LLM feature with no quality measurement. Do NOT use for classical ML model reporting (precision/recall, ROC curves, confusion matrices on trained classifiers) - use model-evaluation-report instead; do NOT use for analyzing online A/B experiments - use ab-test-analyzer instead.
The same file is in 1 other repository
SkillMedev/skills/skills/oncall-handoff Skill
5★ repoProduces a complete on-call shift handoff note - shift summary, open incidents, watch items with paging thresholds, silenced alerts, in-flight changes, and escalation contacts - checked against a completeness checklist. Use when someone asks "write my on-call handoff", "what should I tell the next on-call", "my shift ends in an hour, help me hand over", or "make a handoff template for our rotation". Do NOT use for writing the incident postmortem after resolution - use postmortem-writer instead. For live severity assessment during an incident, use sev-triage; for external customer-facing incident comms, use status-page-update.
The same file is in 1 other repository
SkillMedev/skills/skills/prompt-engineer Skill
5★ repoTurns a vague request into a structured, reliable prompt - role, context, task, format, failure handling, and few-shot examples - that produces consistent output across real inputs. Use when someone asks "why does my prompt give inconsistent results", "write a prompt for this task", "the model keeps breaking my JSON", "how do I stop prompt injection from user input", or is building any LLM feature whose prompt was written ad hoc. Do NOT use for converting a working prompt into a reusable agent skill - use prompt-to-skill instead; do NOT use for measuring whether a prompt change improved quality - use llm-evaluation instead.
The same file is in 1 other repository
SkillMedev/skills/skills/prompt-to-skill Skill
5★ repoConverts a prompt a user runs repeatedly into a reusable, paid-quality SKILL.md. Use when someone says "I keep pasting this prompt", "turn this prompt into a skill", "package this workflow", or has a recurring task pattern they want portable across projects and sessions. Do NOT use to author a skill from a capability idea with no existing prompt (use skill-creator) or to restructure an existing SKILL.md (use skill-author).
SkillMedev/skills/skills/remotion-setup Skill
5★ repoScaffolds a new Remotion video project wired for Claude Code Agent Skills - Node check, create-video scaffold, skills install, folder conventions, Google Fonts, and a smoke-test render. Use whenever someone wants to start making videos with Remotion and Claude, even just "make product videos with Claude."
The same file is in 1 other repository
SkillMedev/skills/skills/skill-creator Skill
5★ repoUse when authoring a brand-new skill from scratch - turning a capability idea or a "make me a skill that…" request into a complete SKILL.md with a trigger-precise description and the full paid-quality anatomy: procedure, elicitation, thresholds, worked artifact, deliverable, Do NOT, quality bar. Triggers on "write a new SKILL.md from scratch", "turn this capability idea into a complete skill". Do NOT use to review or grade an existing skill (use skill-auditor), to convert an existing prompt (use prompt-to-skill), or for writing unrelated to skills.
The same file is in 1 other repository
SkillMedev/skills/skills/social-hook-generator Skill
5★ repoGenerates 10 labeled opening lines for a written social post, one per hook archetype, so the writer can test instead of guess. Use when drafting or rewriting the first line of a LinkedIn post, X post or thread, Instagram caption, or newsletter intro. Do NOT use when the hook is the spoken or on-screen opener of a short-form video (TikTok, Reels, Shorts) - use video-hook-writer instead.
The same file is in 1 other repository
SkillMedev/skills/skills/video-hook-writer Skill
5★ repoWrites the spoken line plus visual frame combination for the first 3 seconds of a short-form video, delivering labeled variants built from six proven hook formulas and matched to TikTok, Reels, or Shorts. Use when someone says "write a hook for this video", "my Shorts die in the first seconds", "give me openers for this TikTok", or "how should this Reel start". Do NOT use for the first line of a written post, thread, or caption - use social-hook-generator instead; do NOT use to build the full thread after the opener - use tweet-thread-builder instead; do NOT use for the 30-second intro of a long-form YouTube video - use youtube-script-writer instead; do NOT use to design the clickable image for a video - use thumbnail-concept instead.
The same file is in 1 other repository
Sudhakaran88/solopreneur-skills/skills/ai-seo Skill
5★ repoWhen the user wants to optimize content for AI search engines and LLM answer engines — ChatGPT, Perplexity, Claude, Google AI Overviews, Gemini. Covers GEO (Generative Engine Optimization), AEO (Answer Engine Optimization), LLMO, and AI visibility as one discipline. Also trigger on "AI SEO", "GEO", "AEO", "LLM optimization", "AI Overviews optimization", "optimize for ChatGPT", "optimize for Perplexity", "AI citations", "AI visibility", "zero-click search". For traditional Google SEO, see seo-audit. For structured data, see schema-markup.
zapgun-ai/clawback/.skills/watch-errors Skill
no license5★ repoQuiet operator watch for a detached clawback proxy — stream ONLY legitimate errors and never the benign flood. Wakes on [error]/[fatal] lines, crash signatures (uncaught/EADDRINUSE/ECONN*/Error:/self-loop), server-side 5xx that are NOT the transient 529, real (non-keep-alive) request failures, and a loud "PROXY DOWN" the instant the pid dies (then exits non-zero). Deliberately silences keep-alive ping failures (401 auth-stale / 404 retired-model / 429/529), real-request 429+529 (Claude Code auto-retries), and [info] no-route attach probes — all observed-benign and not actionable. Use when pointing an agent's Monitor tool at the live proxy and you want zero token burn on no-ops, only real errors. Prefer this over the broader `operate` skill when noise/cost matters.
MateoBogo/CLEAVE/skills/ctf-misc Skill
no license5★ repoMiscellaneous CTF: Python/bash jails, encoding puzzles, Z3/SMT, QR codes, RF/SDR, WASM games, esoteric languages, game theory, commitment schemes, AI/ML/LLM agent exploitation (prompt injection, tool-arg injection, federated poisoning, quantum/Qiskit).
HsuanYuLee/polaris/.claude/skills/codex-mcp-setup Skill
5★ repoUse when the user wants to set up or sync Codex MCP servers for Polaris workflows. Trigger: 'codex mcp', '同步 mcp', '設定 codex mcp', '讓 codex 接 mcp', 'codex mcp setup'.
HsuanYuLee/polaris/.claude/skills/memory-hygiene Skill
5★ repoManual memory tiering — classify Hot/Warm/Cold, review candidates, and migrate MEMORY.md index + memory files. Use when the session-start advisory fires, MEMORY.md Hot grows past 15 entries, or you want a periodic cleanup. Trigger "memory-hygiene", "整理記憶", "memory 降級", "/memory-hygiene", "decay scan", "tier memory".
leynos/visual-storytelling-skills/skills/video-generator Skill
5★ repoExecute production video generation from shot-specifier outputs through the Higgsfield Model Context Protocol (MCP). Use when prompts, storyboard frames, media roles, model routing, Higgsfield MCP uploads, generate_video calls, status polling, retakes, resume behaviour, or final assembly order are needed. Bridges structured [TAG] prompt files to model-native plain text prompts, validates model duration/aspect constraints, decomposes key-frame shots into supported start/end image clips, tracks uploaded media and job IDs, and writes generation logs.
rohingosling/claude-skills/plugins/g-render-ascii-memory-map/skills/ascii-memory-map Skill
5★ repoRender an ASCII box-drawing memory map (an address-space layout diagram) from a JSON description. Use whenever a response needs a memory map, memory layout, address map, or address-space diagram for ANY architecture (Commodore VIC-20/C64, x86 real-mode/segmented, ARM/MCU flash+SRAM, flat 32/64-bit, etc.). Separates the map's DATA from its RENDERING and offloads all box drawing, column alignment, address formatting, and size-proportional block heights to a deterministic Python renderer, so the model only authors compact JSON.
Gravisun/lynqu-ai-toolkit/skills/lynqu-lead-capture Skill
no license5★ repoCapture new leads into Lynqu — from scanned badges, business cards, event lists, or a paste of names — then dedupe against existing contacts, tag them, and route them into the right pipeline. Use for lead capture, importing contacts, "add these people as leads", post-event data entry, or turning a list into a working pipeline. Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).
Gravisun/lynqu-ai-toolkit/skills/lynqu-lead-management Skill
no license5★ repoKeep the Lynqu sales pipeline clean and moving — advance leads through stages, assign owners, score and tag, run bulk hygiene, and surface stalled deals. Use for pipeline management, lead routing, "tidy up my pipeline", reassigning leads, moving deals between stages, or weekly pipeline grooming. Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).
Gravisun/lynqu-ai-toolkit/skills/lynqu-lead-research Skill
no license5★ repoFind and qualify target accounts and decision-makers before an event or outbound campaign, then create them as leads in Lynqu. Use for AI lead research, lead generation, prospecting, building a target account list, or "who should we talk to" — especially before a conference, trade show, or campaign. Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).
Gravisun/lynqu-ai-toolkit/skills/lynqu-pipeline-report Skill
no license5★ repoGenerate a pipeline and performance report from Lynqu — what moved, what's stalling, campaign and event ROI, card engagement, and who needs attention. Use for weekly pipeline review, sales reporting, "how's the pipeline looking", campaign performance, lead/card analytics, or a stand-up summary. Read-only. Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).
Gravisun/lynqu-ai-toolkit/skills/lynqu-sales-followup Skill
no license5★ repoDraft and send on-brand sales follow-up emails to Lynqu leads using your follow-up templates, and log them to the lead timeline. Use for sales follow-up, post-event outreach, "follow up with these leads", nurture sequences, or "what should I say to this prospect". Requires the Lynqu MCP server connected (https://api.lynqu.com/mcp/v2).
ramboz/jig/hosts/claude/skills/memory-sync Skill
5★ repoPersist new context, terms, learnings, and settled lightweight decisions. Use when the user says remember this, save this for later, add to glossary, note this down, or at session end to consolidate what was learned — that goes to the memory layer (CLAUDE.md hot cache, docs/memory/, docs/inbox.md). Also use to record a decision or remember this decision when the call is a lightweight one shipped outside a spec slice: UI strings, visual and CSS choices, copy, or translation fixes. Those go to docs/decisions/lightweight-decisions.md via decisions.py. Also use when revising, updating, or re-pricing an already-recorded decision: judge whether it now warrants an ADR and promote it if so, rather than editing it in place. Also auto-fires at session end. Do not use for updating specs or code comments. For a NEW load-bearing decision, one with rejected alternatives, or any the user wants written up as an ADR, use `/jig:adr-workflow`; an already-recorded entry that outgrew this home is promoted from here.
ramboz/jig/hosts/codex/plugins/jig/skills/memory-sync Skill
5★ repoPersist new context, terms, learnings, and settled lightweight decisions. Use when the user says remember this, save this for later, add to glossary, note this down, or at the end of a session to consolidate what was learned — that goes to the memory layer (AGENTS.md hot cache, docs/memory/, docs/inbox.md). Also use to record a decision, remember this decision, or write this decision down when the call is a lightweight one shipped outside a spec slice: UI strings, visual and CSS choices, sizes, copy, or translation fixes. Those go to docs/decisions/lightweight-decisions.md via decisions.py. Also auto-fires at session end to surface capture-worthy items. Do not use for updating specs or code comments — those have their own workflows. For a load-bearing or architectural decision, one with rejected alternatives worth recording, or any decision the user wants written up as an ADR, use `/jig:adr-workflow` instead.
ramboz/jig/skills/memory-sync Skill
5★ repoPersist new context, terms, learnings, and settled lightweight decisions. Use when the user says remember this, save this for later, add to glossary, note this down, or at session end to consolidate what was learned — that goes to the memory layer (CLAUDE.md hot cache, docs/memory/, docs/inbox.md). Also use to record a decision or remember this decision when the call is a lightweight one shipped outside a spec slice: UI strings, visual and CSS choices, copy, or translation fixes. Those go to docs/decisions/lightweight-decisions.md via decisions.py. Also use when revising, updating, or re-pricing an already-recorded decision: judge whether it now warrants an ADR and promote it if so, rather than editing it in place. Also auto-fires at session end. Do not use for updating specs or code comments. For a NEW load-bearing decision, one with rejected alternatives, or any the user wants written up as an ADR, use `/jig:adr-workflow`; an already-recorded entry that outgrew this home is promoted from here.
zeikar/hyperclaude/skills/hyper-auto Skill
5★ repoUse when plan-harden → implement-harden should chain in one gesture — hyper-plan-loop produces a clean plan, then hyper-implement-loop executes and hardens it. Also when the user invokes /hyperclaude:hyper-auto. For manual control between phases use /hyperclaude:hyper-plan-loop, inspect the plan, then /hyperclaude:hyper-implement-loop. Inherits both loops' agent-teams requirement (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`).
zeikar/hyperclaude/skills/hyper-memory Skill
5★ repoUse on-demand to extract evidence-anchored repo-local knowledge candidates from accumulated .hyperclaude/ artifacts (plans/done, plan-reviews, research) and curate them. Also when the user invokes /hyperclaude:hyper-memory. Orchestration-only — no Codex spawn.
zeikar/hyperclaude/skills/hyper-recap Skill
5★ repoUse at cycle completion to write a human-readable recap of what was built and why — "recap this cycle", "summarize what we built", "cycle recap", "write up what changed this cycle". Also when the user invokes /hyperclaude:hyper-recap. Claude-only — no Codex, no agent dispatch — runs after a plan is implemented and reviewed, and writes a recap to .hyperclaude/recaps/. Recaps ONE completed detailed plan / milestone archived under .hyperclaude/plans/done/. Distinct from /hyperclaude:hyper-memory (durable knowledge extraction, not a one-cycle narrative).
air-gapped/skills/.claude/skills/confluence-best-practices Skill
5★ repoAdvise on USING Confluence well, not operating it: make the structural call — is this a space, a page, or a child page? — diagnose why a wiki is a dread (can't find anything, content rots, duplicates, hidden by permissions, unreadable), and recommend the lean fix. Built FIRST for an agent that ACTS on Confluence (creates/organises/governs content via REST/CQL or an MCP server) and SECOND for helping humans author readable pages. Self-hosted Server/Data Center first (storage format NOT ADF; no native page archive; REST v1), but works for Cloud too. Adapt to the org's own space conventions and working language; never auto-translate content. Covers ALL content types — knowledge base, docs, intranet, meeting notes, runbooks, decision records.
air-gapped/skills/.claude/skills/jira-best-practices Skill
5★ repoAdvise on USING Jira well, not operating it: make the structural call — is this an epic, a story, a task, or a sub-task? — and diagnose why a Jira is a dread, then recommend the lean fix. Adapt to the organisation's OWN hierarchy names, conventions, and working language instead of imposing a methodology. Self-hosted-first: Jira Data Center 10.3/11.x (no Cloud AI; dual Epic Link + Parent Link). Built for an agent that ACTS on Jira through the jira-cli tool or the mcp-atlassian MCP server while advising the user; Jira web-UI and admin-schema guidance is secondary. Covers ALL project types — software AND non-software (operations, engineering, services, business).
air-gapped/skills/.claude/skills/jira-confluence-mcp Skill
5★ repoInstall, configure, secure, and troubleshoot the mcp-atlassian MCP server (sooperset/mcp-atlassian) that connects an agent to Jira/Confluence — including AIR-GAPPED setup (mirror the prebuilt image by digest; no PyPI/git mirror) and internal-CA / TLS handling (mount the CA vs JIRA_SSL_VERIFY=false). Self-hosted Data Center first: the #1 gotcha is DC uses JIRA_PERSONAL_TOKEN (a PAT), NOT the Cloud username+API-token pattern. Covers `claude mcp add`, the env-var catalog, hardening (READ_ONLY_MODE, TOOLSETS/ENABLED_TOOLS, project filters, the v0.22 default-toolset change), Cloud-vs-DC tool/format divergence, and 401/403/field/rate-limit/SSL fixes. NOT a catalogue of the 72 tools — those self-document at runtime; this is the setup/ops knowledge invisible at call time.
air-gapped/skills/.claude/skills/open-webui-embeddings Skill
5★ repoClaude Code plugin marketplace — 58 installable reference skills across vLLM/SGLang inference, Kubernetes & Harvester, GPU host bring-up, observability, security, and agent workflows.
air-gapped/skills/.claude/skills/skill-improver Skill
5★ repoAutoresearch loop for Claude Code skills — greedy keep/discard hill climbing on a 10-dimension quality rubric, with blind subagent validation for self-scoring bias, plus a `freshen` mode that probes external references (release notes, docs, deprecation signals) and applies verified updates, plus a `trigger` mode that measures and tunes the skill's frontmatter description until it reliably fires when it should and stays silent when it shouldn't (60/40 train/test split, 7 runs/query, blinded test scores).
mr-kelly/skills/skills/kelly-agent-builder Skill
5★ repoBusabase-backed App-in-Skill low-code agent configuration and governance console for a platform team. Use when the user invokes $kelly-agent-builder or /kelly-agent-builder, wants to review or edit a catalog of mock LLM agent configs, check quota usage, find configs that need attention, move a draft to live, pause a live agent, or archive an agent. Mock config/governance console only — it never provisions or calls any real agent.
mr-kelly/skills/skills/kelly-agent-eval Skill
5★ repoReview board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.
mr-kelly/skills/skills/kelly-agent-observability Skill
5★ repoBusabase App-in-Skill dashboard visualizing a generated MOCK fleet of LLM agents running behind a shared AI gateway for a generic organization. Use when the user invokes $kelly-agent-observability or /kelly-agent-observability, wants to review agent health, call volume, latency, error rates, cost, or trace-level chain breaks across an agent fleet. This is a demo/reference dashboard over a generated mock fleet snapshot seeded into Busabase by a trusted script — never a live monitoring integration, never a real gateway or real agents.
mr-kelly/skills/skills/kelly-llm-gateway Skill
5★ repoGeneric, brand-free App-in-Skill dashboard for a shared LLM gateway's cost and model governance — daily spend trend, cost breakdown by service/model, a canary-rollout status board, and a deterministic cost/error anomaly list. Use when the user invokes $kelly-llm-gateway or /kelly-llm-gateway, or wants to review LLM gateway spend, model routing, canary rollouts, rollback readiness, or cost/error anomalies for services routed through one shared gateway to multiple LLM providers/models. Human actions (promote/rollback/hold a rollout, acknowledge an anomaly) write only local handoff files — this skill never changes a real routing config.
mr-kelly/skills/skills/kelly-seo Skill
5★ repoPersonal App-in-Skill desk covering SEO + GEO (AI-search) + brand entity — wired to Google Search Console for a local dashboard over search analytics and an agent-prepared SEO opportunities review queue, plus an AI-visibility tracker (are we cited in ChatGPT / Perplexity / Gemini / Claude / Copilot answers), a GEO content-optimization queue gated by geo-qa, and an entity / knowledge-panel readiness checklist. Use when the user invokes $kelly-seo or /kelly-seo, mentions SEO, Google Search Console, GSC, search analytics, search performance, queries, keywords, rankings, positions, impressions, clicks, CTR, striking-distance queries, title/meta rewrites, content briefs, internal links, SEO opportunities review, GEO, generative engine optimization, AI search, AI visibility, being cited by AI answer engines, ChatGPT/Perplexity/Gemini/Claude/Copilot citations, brand entity, knowledge panel, Wikidata, schema.org, or entity readiness.
mr-kelly/skills/skills/publish-skills Skill
5★ repoPublish agent skills AND MCP servers to every marketplace, plugin directory, and registry — security-scan for private data, validate with `gh skill`, cut a release, wire the Claude /plugin and Codex marketplaces, publish an MCP server to the official MCP Registry (mcp-publisher + server.json), and prep the curated / monetized stores (Buda Marketplace, Agensi, OpenClaw ClawHub) and review-gated directories (ChatGPT App Directory, Anthropic Connectors + Desktop Extensions/.mcpb). Use when the user wants to publish, release, list, 上架, or distribute agent skills, plugins, or MCP servers to skills.sh / SkillsMP / Claude Code / Codex / the MCP Registry.
fabioc-aloha/Alex_Skill_Mall/plugins/academic-research/deep-dive Skill
5★ repoClaude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.
The same file is in 1 other repository
fabioc-aloha/Alex_Skill_Mall/plugins/academic-research/research-summarizer Skill
5★ repoStructured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.
The same file is in 2 other repositories