@skills · Owner
Agent skills by ma08
135 skills indexed from github.com/ma08. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- apple-reminders-safe · Skill
Safely read, search, create, update, complete, reopen, or explicitly delete Apple Reminders through a bounded Mac-native EventKit bridge. Use for any agent
- apple-reminders-safe · Skill
Safely read, search, create, update, complete, reopen, or explicitly delete Apple Reminders through a bounded Mac-native EventKit bridge. Use for any agent
- backup_skills · Collection
- birdclaw · Skill
Use Birdclaw for cache-first X/Twitter data workflows, especially followers/following, unfollowers, mutuals, non-mutual following, top followers, leadgen l
- birdclaw · Skill
Use Birdclaw for cache-first X/Twitter data workflows, especially followers/following, unfollowers, mutuals, non-mutual following, top followers, leadgen l
- botfiles · Collection
- channel-access · Skill
Use local read-only iMessage, WhatsApp, and LinkedIn channel access wrappers for raw message discovery, sample exports, and CRM provenance workflows.
- channel-access · Skill
Use local read-only iMessage, WhatsApp, and LinkedIn channel access wrappers for raw message discovery, sample exports, and CRM provenance workflows.
- claude · Collection
- claude-fable-advisor · Skill
Use Anthropic Claude Fable 5 through Claude Code as a subscription-backed external advisor, reviewer, or planner for Codex work. Use when the user asks for
- codex · Collection
- commit-task-work · Skill
Commit task-scoped work across personal_os task artifacts and any external codebases touched by the task. Use when the user asks to commit relevant files,
- commit-task-work · Skill
Commit task-scoped work across personal_os task artifacts and any external codebases touched by the task. Use when the user asks to commit relevant files,
- context-explainer · Skill
Create source-grounded explainers for research, engineering, architecture, task, issue, PR, and implementation-plan context. Use for end-to-end mental mode
- context-explainer · Skill
Create source-grounded explainers for research, engineering, architecture, task, issue, PR, and implementation-plan context. Use for end-to-end mental mode
- continue-task · Skill
Take over an interrupted tracked task from a previous Codex or Claude session by resolving the existing task home from a tracker ref, task slug, status fil
- continue-task · Skill
Take over an interrupted tracked task from a previous Codex or Claude session by resolving the existing task home from a tracker ref, task slug, status fil
- continue-task · Skill
Resume an interrupted tracked task in Hermes by resolving the existing task home from a task slug, tracker ref, session name, task dir, or status file, the
- create-goal-plan · Skill
Create a short Markdown goal-plan file for Codex CLI `/goal` usage. Use when the user asks to create, distill, or prepare a Codex goal plan from an existin
- create-oracle-review-powered-goal-plan · Skill
Create compact Codex `/goal` plan files that require an implementation loop with Oracle GPT-5.5 Pro review between iterations. Use when the user wants a go
- create-oracle-review-powered-goal-plan · Skill
Create compact Codex `/goal` plan files that require an implementation loop with Oracle GPT-5.5 Pro review between iterations. Use when the user wants a go
- create-ticket-session · Skill
Create a Linear ticket and immediately launch a detached zellij/Codex worker session for it. Use when the user asks to "create a ticket and start a session
- create-ticket-session · Skill
Create a Linear ticket and immediately launch a detached zellij/Codex worker session for it. Use when the user asks to "create a ticket and start a session
- cross-session-context · Skill
Resolve another tracked live task/session or Codex Desktop thread and read task metadata, transcript fallback, zellij diagnostics, or Codex Desktop thread
- cross-session-context · Skill
Resolve another tracked live task/session and read its task metadata, transcript fallback, and zellij targeting details for non-Symphony Hermes orchestrati
- cross-session-context · Skill
Resolve another tracked live task/session or Codex Desktop thread and read task metadata, transcript fallback, zellij diagnostics, or Codex Desktop thread
- cross-session-message · Skill
Preview or send a bounded instruction into another known live zellij-backed coding-agent session or Codex Desktop thread outside Symphony.
- cross-session-message · Skill
Preview or send a bounded instruction into another known live zellij-backed coding-agent session outside Symphony.
- cross-session-message · Skill
Preview or send a bounded instruction into another known live zellij-backed coding-agent session or Codex Desktop thread outside Symphony.
- deep-feed-handoff-consumer · Skill
Accept and work one owner-approved protocol-v2 Deep Feed dispatch in the exact existing non-scheduled Codex task named by the compact invocation. Reject sc
- deep-feed-handoff-consumer · Skill
Accept and work one owner-approved protocol-v2 Deep Feed dispatch in the exact existing non-scheduled Codex task named by the compact invocation. Reject sc
- deep-feed-handoff-router · Skill
Safely inspect an old Deep Feed router invocation without dispatching it. This compatibility guard prevents retired protocol-v1 links from routing into sch
- deep-feed-handoff-router · Skill
Safely inspect an old Deep Feed router invocation without dispatching it. This compatibility guard prevents retired protocol-v1 links from routing into sch
- deep-feed-work · Skill
Bind and handle one protocol-v2 Deep Feed card in the newly opened Codex task by default, with optional owner-confirmed delegation to one exact relevant no
- deep-feed-work · Skill
Bind and handle one protocol-v2 Deep Feed card in the newly opened Codex task by default, with optional owner-confirmed delegation to one exact relevant no
- deep-research · Skill
Run end-to-end deep research using OpenAI Responses API deep-research models plus Gemini Deep Research plus Exa Deep Research, then synthesize results into
- doc · Skill
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plu
- eli5 · Skill
Explain a topic like I'm a 5 year old. Use when the user types /eli5 followed by a topic or asks for a dead-simple picture explainer of how something works
- eli5 · Skill
Explain a topic like I'm a 5 year old. Use when the user types /eli5 followed by a topic or asks for a dead-simple picture explainer of how something works
- excalidraw-diagram · Skill
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
- excalidraw-diagram · Skill
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
- figma · Skill
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger
- finish-task · Skill
Standardize end-of-task closeout when the user asks to finish, wrap up, merge-and-close, land, or otherwise cleanly close a tracked task or PR, including t
- finish-task · Skill
Standardize end-of-task closeout when the user asks to finish, wrap up, merge-and-close, land, or otherwise cleanly close a tracked task or PR, including t
- frontend-skill · Skill
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led
- get-task-details · Skill
Print rich task details for the current task context: status file path, primary tracker URL, machine name, coding agent/session id, transcript path, zellij
- get-task-details · Skill
Print rich task details for the current Hermes task context: status file path, primary tracker URL, machine name, session id, transcript path, zellij sessi
- get-task-details · Skill
Print rich task details for the current task context: status file path, primary tracker URL, machine name, coding agent/session id, transcript path, zellij
- gh-address-comments · Skill
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if n
- gh-fix-ci · Skill
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, d
- grill-me · Skill
Interview the user relentlessly about a plan, design, or decision using Codex's interactive `request_user_input` tool until you reach shared understanding.
- grill-me · Skill
Interview the user relentlessly about a plan, design, or decision using Claude's interactive `AskUserQuestion` tool until you reach shared understanding. U
- grill-plan-review · Skill
Review a long or cognitively heavy plan through a concise, one-decision-at-a-time interview, recommend each choice with rationale, and turn the user's answ
- grill-plan-review · Skill
Review a long or cognitively heavy plan through a concise, one-decision-at-a-time interview, recommend each choice with rationale, and turn the user's answ
- guided-human-execution · Skill
Guide a human through a task in an interactive, human-in-the-loop execution rhythm. Use when the user asks to be walked through something step by step, wan
- guided-human-execution · Skill
Guide a human through a task in an interactive, human-in-the-loop execution rhythm. Use when the user asks to be walked through something step by step, wan
- gws-account-switch · Skill
Choose a named Google Workspace account alias (`work`, `personal`, `columbia`) for `gws` and switch agents onto the matching exported credentials file. Use
- gws-account-switch · Skill
Choose a named Google Workspace account alias (`work`, `personal`, `columbia`) for `gws` and switch agents onto the matching exported credentials file. Use
- gws-calendar-safe · Skill
Safely read, create, edit, split, cancel, or delete Google Calendar events through the named work, personal, or columbia gws aliases. Use for any agent-dri
- gws-calendar-safe · Skill
Safely read, create, edit, split, cancel, or delete Google Calendar events through the named work, personal, or columbia gws aliases. Use for any agent-dri
- gws-drive · Skill
Google Drive: List, search, inspect, download, and export files with alias-first `gws-account` flows for `work`, `personal`, and `columbia`.
- gws-drive · Skill
Google Drive: List, search, inspect, download, and export files with alias-first `gws-account` flows for `work`, `personal`, and `columbia`.
- gws-gmail · Skill
Gmail: Send, read, and manage email.
- gws-gmail · Skill
Gmail: Send, read, and manage email.
- gws-gmail-draft · Skill
Create unsent Gmail drafts through the named work, personal, or columbia gws account alias with a portable draft-only helper. Use when the user explicitly
- gws-gmail-draft · Skill
Create unsent Gmail drafts through the named work, personal, or columbia gws account alias with a portable draft-only helper. Use when the user explicitly
- gws-gmail-read · Skill
Gmail: Read a message and extract its body or headers.
- gws-gmail-read · Skill
Gmail: Read a message and extract its body or headers.
- gws-gmail-triage · Skill
Gmail: Show unread inbox summary (sender, subject, date).
- gws-gmail-triage · Skill
Gmail: Show unread inbox summary (sender, subject, date).
- gws-shared · Skill
gws CLI: Shared patterns for authentication, global flags, and output formatting.
- gws-shared · Skill
gws CLI: Shared patterns for authentication, global flags, and output formatting.
- hermes · Collection
- i-have-adhd · Skill
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time e
- i-have-adhd · Skill
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time e
- imagegen · Skill
Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replaceme
- iphone-media-archive · Skill
Backup-first iPhone photo/video archiving to an external drive. Use when creating or verifying a Finder-browsable raw archive from an iPhone, iOS backup, o
- jupyter-notebook · Skill
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates
- linear · Skill
Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.
- mac-disk-cleanup · Skill
Safely audit and clean macOS disk space with read-only baselines, approval-gated cleanup batches, Docker/Xcode/cache/log cleanup, verification, and task ar
- mac-disk-cleanup · Skill
Safely audit and clean macOS disk space with read-only baselines, approval-gated cleanup batches, Docker/Xcode/cache/log cleanup, verification, and task ar
- mac-ui-worker · Skill
Route bounded UI-only work from a Codex Desktop source task, especially a remote GCP-backed task, to one Mac-local Codex Desktop worker bound to that exact
- mac-ui-worker · Skill
Route bounded UI-only work from a Codex Desktop source task, especially a remote GCP-backed task, to one Mac-local Codex Desktop worker bound to that exact
- message-developer · Skill
Send contextual WhatsApp messages to the developer during monitoring, on blockers, or at milestones. Use proactively when the developer may be away.
- message-developer · Skill
Send contextual WhatsApp messages to the developer during monitoring, blockers, milestones, or explicit questions. Use proactively when the developer may b
- Notion · Skill
Notion workspace integration. Use when user wants to read/write Notion pages, search databases, create tasks, or sync content with Notion.
- notion-research-documentation · Skill
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, o
- openai-docs · Skill
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model
- openai-docs · Skill
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model
- oracle · Skill
Use the @steipete/oracle CLI for debugging, refactors, design checks, and cross-validation, preferring the GCP-backed `oracle-vm` route for agent-driven pr
- oracle · Skill
Use the @steipete/oracle CLI for debugging, refactors, design checks, and cross-validation, preferring the GCP-backed `oracle-vm` route for agent-driven pr
- pdf · Skill
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and u
- personal-os-repo-cleanup · Skill
Use when the user asks to commit, clean, audit, reconcile, push, pull, or coordinate dirty personal_os changes across the VM and Mac checkouts, especially
- personal-os-repo-cleanup · Skill
Use when the user asks to commit, clean, audit, reconcile, push, pull, or coordinate dirty personal_os changes across the VM and Mac checkouts, especially
- playwright · Skill
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debuggin
- pr-autoreview-loop · Skill
Run a repeatable non-Symphony PR autoreview fix loop using current-head reviewer artifacts plus the repo-managed `pr-autoreview-loop` helper.
- pr-autoreview-loop · Skill
Run a repeatable non-Symphony PR autoreview fix loop using current-head reviewer artifacts plus the repo-managed `pr-autoreview-loop` helper.
- prepare-production-release · Skill
Assess and harden an exact software release candidate before production. Use when committed or otherwise bounded code needs risk-scaled simplification, arc
- prepare-production-release · Skill
Assess and harden an exact software release candidate before production. Use when committed or otherwise bounded code needs risk-scaled simplification, arc
- Ralph · Skill
Ralph Wiggum methodology for autonomous agentic development. Use when setting up a new Ralph task, preparing specs, or troubleshooting Ralph loops.
- Ralph · Skill
Ralph Wiggum methodology for autonomous agentic development. Use when setting up a new Ralph task, preparing specs, or troubleshooting Ralph loops.
- rename-active-codex-threads · Skill
Rename all recently active Codex threads across the local app and connected remote hosts with native codex_app thread tools, using tracker ID, stable task
- rename-active-codex-threads · Skill
Rename all recently active Codex threads across the local app and connected remote hosts with native codex_app thread tools, using tracker ID, stable task
- reorient-myself · Skill
Strategically audit an entire coding-agent task or conversation, distinguish completed work from discussion, challenge its direction from first principles,
- reorient-myself · Skill
Strategically audit an entire coding-agent task or conversation, distinguish completed work from discussion, challenge its direction from first principles,
- run-deep-feed · Skill
Collect bounded current deltas from the owner-approved Chief-of-Staff sources and publish one fresh, finite Deep Feed edition. Use when the user asks to ru
- run-deep-feed · Skill
Collect bounded current deltas from the owner-approved Chief-of-Staff sources and publish one fresh, finite Deep Feed edition. Use when the user asks to ru
- save-status · Skill
Save current task status, plan, or investigation notes to the project's task-tracking folder. Reconciles machine/zellij/tracker metadata and refreshes the
- save-task-status · Skill
Save current task status, plan, or bug report to the project's task-tracking folder. Reconciles machine/zellij/tracker metadata and optionally refreshes li
- save-task-status · Skill
Save current task status, plan, or bug report to the project's task-tracking folder. Reconciles machine/zellij/tracker metadata and optionally refreshes li
- skills · Collection
- skills · Collection
- skills · Collection
- software-development · Collection
- sora · Skill
Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI\u2019s video API using the bundled CLI (`scripts/sora.py`
- start-new-task · Skill
Initialize a new task folder with status.md, user_inputs/initial.md, user_inputs/input_artifacts/, task-progress-artifacts/, and task-progress-artifacts/sc
- start-new-task · Skill
Initialize a new task folder with status.md, user_inputs/initial.md, user_inputs/input_artifacts/, task-progress-artifacts/, and task-progress-artifacts/sc
- start-task · Skill
Initialize a new tracked task folder with status.md, user_inputs/initial.md, user_inputs/input_artifacts/, task-progress-artifacts/, and task-progress-arti
- start-zellij-session-for-task · Skill
Start a detached zellij session for a tracker-linked or natural-language task, and launch Codex or Claude as the default shell with an initial `$start-new-
- start-zellij-session-for-task · Skill
Start a detached zellij session for a tracker-linked or natural-language task, and launch Codex or Claude as the default shell with an initial `$start-new-
- sync-botfiles-machines · Skill
Safely inventory, reconcile, clean, and synchronize divergent botfiles Git checkouts and layered Codex configuration across the canonical cloud host and cl
- sync-botfiles-machines · Skill
Safely inventory, reconcile, clean, and synchronize divergent botfiles Git checkouts and layered Codex configuration across the canonical cloud host and cl
- sync-codex-claude-skills · Skill
Compare, audit drift, and sync skills between botfiles-style visible skill trees (`claude/skills`, `codex/skills`) or hidden project-local skill trees (`.c
- transcribe · Skill
Transcribe audio/video files using speech-to-text providers. Use when user has audio or video files to transcribe.
- update-coding-agent-preferences · Skill
Apply persistent or repo-local coding-agent instruction changes across Codex and Claude in tandem, including related skill updates when a preference change
- update-coding-agent-preferences · Skill
Apply persistent or repo-local coding-agent instruction changes across Codex and Claude in tandem, including related skill updates when a preference change
- vercel-deploy · Skill
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this l
- video-use · Skill
Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel,
- xurl · Skill
Use the xurl CLI for authenticated X/Twitter API work, including reading posts, searching, checking timelines and mentions, inspecting followers/following,
- xurl · Skill
Use the xurl CLI for authenticated X/Twitter API work, including reading posts, searching, checking timelines and mentions, inspecting followers/following,
- yeet · Skill
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
- zellij-cross-session-orchestration · Skill
Use repo-managed zellij helpers from ~/pro/botfiles to inspect, message, and launch parallel coding-agent task sessions.
- zellij-detached-codex-launch-verification · Skill
Debug and fix detached Zellij launches for Codex tasks when session creation succeeds but the attached pane only shows a shell or no visible Codex UI.
- zotero-research-library · Skill
Work with a Zotero research library for paper-reading workflows: search local items, inspect metadata, read attached PDFs, export notes/highlights/annotati
- zotero-research-library · Skill
Work with a Zotero research library for paper-reading workflows: search local items, inspect metadata, read attached PDFs, export notes/highlights/annotati