All authors
Claude Skills by fakoli
github.com/fakoli154 skills0 installs47 views
- Recipe Organize Drive FolderCreate a Google Drive folder structure and move files into the right locations.Votes: 0GitHub stars: 4
- Recipe Plan Weekly ScheduleReview your Google Calendar week, identify gaps, and add events to fill them.Votes: 0GitHub stars: 4
- Recipe Post Mortem SetupCreate a Google Docs post-mortem, schedule a Google Calendar review, and notify via Chat.Votes: 0GitHub stars: 4
- Recipe Reschedule MeetingMove a Google Calendar event to a new time and automatically notify all attendees.Votes: 0GitHub stars: 4
- Recipe Review Meet ParticipantsReview who attended a Google Meet conference and for how long.Votes: 0GitHub stars: 4
- Recipe Review Overdue TasksFind Google Tasks that are past due and need attention.Votes: 0GitHub stars: 4
- Recipe Save Email AttachmentsFind Gmail messages with attachments and save them to a Google Drive folder.Votes: 0GitHub stars: 4
- Recipe Save Email To DocSave a Gmail message body into a Google Doc for archival or reference.Votes: 0GitHub stars: 4
- Recipe Schedule Recurring EventCreate a recurring Google Calendar event with attendees.Votes: 0GitHub stars: 4
- Recipe Schema ExploreDiscover and introspect any Google Workspace API before using it — explore methods, parameters, and types.Votes: 0GitHub stars: 4
- Recipe Send Team AnnouncementSend a team announcement via both Gmail and a Google Chat space.Votes: 0GitHub stars: 4
- Recipe Setup SanitizationConfigure Google Cloud Model Armor globally for all gws commands to protect against prompt injection in API responses.Votes: 0GitHub stars: 4
- Recipe Share Doc And NotifyShare a Google Docs document with edit access and email collaborators the link.Votes: 0GitHub stars: 4
- Recipe Share Event MaterialsShare Google Drive files with all attendees of a Google Calendar event.Votes: 0GitHub stars: 4
- Recipe Share Folder With TeamShare a Google Drive folder and all its contents with a list of collaborators.Votes: 0GitHub stars: 4
- Recipe Stream InboxStream real-time Gmail notifications using gws gmail +watch for continuous inbox monitoring.Votes: 0GitHub stars: 4
- Recipe Sync Contacts To SheetExport Google Contacts directory to a Google Sheets spreadsheet.Votes: 0GitHub stars: 4
- Recipe Watch Drive ChangesSubscribe to change notifications on a Google Drive file or folder.Votes: 0GitHub stars: 4
- Marketplace ManagerManage the fakoli-plugins marketplace. Use when: (1) adding a new plugin to the marketplace, (2) removing a plugin, (3) validating plugins, (4) regenerating registry indices, (5) checking marketplace status, or (6) any plugin registry management task. Triggers on phrases like "add plugin", "validate plugins", "update registry", "marketplace status".Votes: 0GitHub stars: 4
- GenerateGenerate, edit, remix, and optimize images using Google Gemini 3 Pro Image Preview (Nano Banana Pro)Votes: 0GitHub stars: 4
- Notebooklm CoreComplete Google NotebookLM automation — create notebooks, add sources, generate podcasts/videos/quizzes/slides, chat with content, and download results. Activates on explicit /notebooklm-enhanced commands or intent like "create a podcast about X", "summarize these URLs", "generate a quiz"Votes: 0GitHub stars: 4
- Notebooklm ResearchMulti-notebook research synthesis — activates when user needs cross-notebook research, comparative analysis, or deep research workflows combining multiple NotebookLM notebooksVotes: 0GitHub stars: 4
- Safe FetchThis skill should be used when the user asks to "fetch a URL safely", "sanitize web content", "search the web securely", "check URL safety", "prevent prompt injection from web content", or discusses web fetching security. Also triggers when curl/wget is used to fetch web content.Votes: 0GitHub stars: 4
- ExampleAn example skill demonstrating the plugin structureVotes: 0GitHub stars: 4
- PulseStart, stop, or check the anvil-pulse dashboard — a live local web page showing active anvil claims (actor, phase, elapsed, lease countdown), the event feed, and stuck-state detection (healthy / quiet / possibly wedged / lease expired) for long autonomous runs. Use when the user asks to "watch this run", "open the anvil dashboard", "is the agent stuck?", "monitor the claims", "start/stop pulse", or wants a heartbeat view of an anvil project. Also installs an optional Claude Code statusline se...Votes: 0GitHub stars: 4
- Cli To PluginGenerate a portable Codex and Claude Code plugin from a CLI help tree. Use when wrapping a command-line tool as skills, converting captured help to a plugin, or regenerating command-group workflows while preserving local edits.Votes: 0GitHub stars: 4
- Templates<!-- Template: structural reference for the cli-to-plugin generator. Claude reads this to understand expected shape. NOT a Jinja template — no placeholder substitution. -->Votes: 0GitHub stars: 4
- Plugin ReviewReview plugin manifests, skills, hooks, MCP configuration, and specialist agent definitions for concrete defects. Use when auditing a Codex or Claude Code plugin, checking marketplace readiness, or investigating why a bundled capability is unavailable.Votes: 0GitHub stars: 4
- SpeakSpeak requested text through fakoli-speak, inspect TTS providers/voices/playback and estimated cost, or manage its opt-in autospeak setting.Votes: 0GitHub stars: 4
- ExecuteExecute a claimed Fakoli State work packet, verify its acceptance criteria and submit concrete evidence for review.Votes: 0GitHub stars: 4
- FinishReview a Fakoli State evidence bundle and record the authorized accept or reject decision for a submitted task.Votes: 0GitHub stars: 4
- PlanTurn a reviewed Fakoli State PRD into scored, reviewable tasks and a ready queue before implementation.Votes: 0GitHub stars: 4
- Style OpsMaintain, validate or report on the Fakoli principles ledger, checking evidence pointers and keeping its Markdown projection synchronized.Votes: 0GitHub stars: 4
- Fleet ExecRun structured remote commands over SSH, read or write a remote file, or inspect host facts when the user requests work on another machine.Votes: 0GitHub stars: 4
- Gate CheckRoute changed file paths to the verify commands this repo requires before shipping — docs changed means docs strict build, shell changed means bash -n, CLI changed means the encoding smoke test. Use before committing/opening a PR, when the user asks "what checks do I need to run", "run the gates", "gate check", or after substantive edits in a repo with a .claude/gate-router.local.md rules file. Deterministic local gates instead of session memory; also helps AUTHOR the rules file for a new repo.Votes: 0GitHub stars: 4
- HandoffSave or update this project's cross-session handoff note — the resume point for the next session, shared across checkouts of the same git remote and across linked worktrees. Use when the user types /handoff (optionally with a one-line summary), says "save a handoff", "note where we are for next time", "write a handoff before I clear context", or is wrapping up a session.Votes: 0GitHub stars: 4
- RecallShow this project's saved cross-session handoff note (the resume point shared across checkouts of the same git remote and across linked worktrees). Use when the user types /recall, asks "where did we leave off?", "what's the handoff?", "what was I working on?", or "catch me up".Votes: 0GitHub stars: 4
- Find NotesRead back, search, browse, or get stats on the user's existing personal notes. Use when the user wants to retrieve or explore notes — e.g. "what notes do I have", "show my notes", "show me my recent notes", "find my notes about X", "read back my notes", "search my notes for…", "show notes from today", "notes tagged #work", "notes since last week", "how many notes do I have", "give me a summary of my notes", "export my notes", "save my notes to markdown". This skill is for RETRIEVING and SUMMA...Votes: 0GitHub stars: 4
- Take NoteSave a quick personal note to the user's notes log. Use whenever the user dictates or types something they want recorded as a note — e.g. "save a note…", "jot down…", "note that…", "take a note…", "remember this…", "add to my notes…", "log this thought…". Captures the spoken/typed content verbatim and appends it to the log. Use for capturing a thought, NOT for the user asking to read, search, or summarize existing notes (use find-notes for that).Votes: 0GitHub stars: 4
- Recall Mode VerifierReview a change for concrete failure modes in malformed inputs, required preconditions, resource use, and concurrent state. Use for an independent breakage review or when asked what could break. Reports findings and evidence; fixes follow the user’s requested scope.Votes: 0GitHub stars: 4
- Session EvalsMine past coding-agent sessions (Claude Code, Codex, OpenClaw, Cursor CLI) into local-model eval suites executable via anvil-serving. Retro-first — consumes session-retro output dirs and cross-session findings themes, curates candidates into deterministic check-based evals sized for local models, emits anvil-serving-compatible eval-data suites, and runs them against any OpenAI-compatible endpoint. Use when the user asks to "create evals from my sessions", "build local-model evals", "turn this...Votes: 0GitHub stars: 4
- Session RetroAnalyze a Claude Code or Codex session (or a multi-session arc) from local JSONL logs and produce a markdown retro — token economy (main-loop vs delegated workflows), workflow taxonomy, tool distribution, interaction shape, and concrete recommendations. Use when the user asks to "do a session retro", "analyze this session", "pull stats on this session", "how many tokens did this session use", "session statistics / report", "post-session findings", "evaluate how we worked", or wants to review ...Votes: 0GitHub stars: 4
- Dispatch PacketGenerate a dispatch packet — a self-contained subagent packet / implementer prompt that lets a weaker executor equal a stronger one on bounded work. Use when asked to generate a subagent packet, dispatch an implementer, turn issue N into an agent prompt, or write a delegation prompt for a sonnet/opus executor from an issue or task description. Never auto-dispatches — a human/orchestrator reviews the generated packet before any agent runs it.Votes: 0GitHub stars: 4
- Ship LoopRun the full ship loop for a feature or fix — sync and isolate in a worktree, scope with ground-truth sweeps, implement with reality-faithful tests, gate on a multi-angle adversarial review, merge, and close the follow-up loop (promotions ledger, out-of-diff issues). Use when the user says "ship this the usual way", "run the loop", "ship-loop", asks to take a change from idea to merged PR with the standard review gate. The adversarial review is the merge gate — never merge substantive work wi...Votes: 0GitHub stars: 4
- Ship TaskThis skill should be used AFTER code review and verification pass, when the user wants to "ship this", "ship the task", "open and merge the PR", "push, PR, wait for CI, and merge", or otherwise run the mechanical tail of a one-PR-per-task loop. It pushes the current branch, opens a PR, waits for CI to reach a terminal state, merges (squash + delete branch), syncs the base branch, and optionally runs a post-merge command (e.g. `anvil apply`). It makes NO review decisions — the human or agent g...Votes: 0GitHub stars: 4
- Skill Spec LintValidate Agent Skills YAML, field types, naming, lengths, and discovery layout. Use when authoring, reviewing, or checking SKILL.md files. Requires PyYAML; uv runs it in an isolated environment.Votes: 0GitHub stars: 4
- Architecture Risk ReviewTargeted review of failure modes, hidden dependencies, limits, and operational burden in a specific architecture or design. Use this when you need a focused risk assessment without running a full complexity mapping — to identify single points of failure, blast radius concerns, hidden coupling, and operational survivability gaps. Produces a Hidden Risk Summary with dependency risk matrix, compound failure scenarios, and prioritized remediation actions. Ask for an "architecture risk review", "f...Votes: 0GitHub stars: 4
- Complexity MapperSurface hidden complexity, risks, dependencies, and likely project blow-up points in a proposed design or architecture. Use this when you have architecture docs, design proposals, or technical specs and need to identify where operational, cost, networking, or implementation complexity is hiding before committing resources. Produces a Complexity Heat Map and Hidden Risk Summary with source-anchored evidence and severity ratings. Ask for a "complexity map", "hidden risk analysis", "blow-up poin...Votes: 0GitHub stars: 4
- Context ShardingSplit large or varied source material across parallel subagents for extraction before synthesis. Use this when documentation exceeds what can be processed in a single pass — typically more than 5 dense documents or 50+ pages — or when material spans multiple distinct domains. Produces structured Context Packets that can feed into complexity-mapper, decision-brief, or architecture-risk-review. Ask to "shard documents", "split for parallel extraction", or "break this into digestible chunks" to ...Votes: 0GitHub stars: 4
- Decision BriefPackage extracted findings into a compact, decision-ready format for engineers, managers, or review bodies. Use this after running complexity-mapper, architecture-risk-review, or context-sharding to synthesize findings into a structured brief with options, evidence, risks, and recommended next steps. Produces a Decision Brief with evidence summary, top risks, unresolved questions, and actionable recommendations. Ask for a "decision brief", "decision package", or "summarize findings for a deci...Votes: 0GitHub stars: 4