THE REGISTRY  ·  54 SKILLS  ·  INTAKE → ANALYZE → OUTPUT

AI Agent Skills
Registry & Showcase

A platform-agnostic directory of modular rules and terminal CLI tools built on the progressive disclosure paradigm.

GitHub repository ↗

CORE PHILOSOPHY

01 / AGNOSTIC

Platform-Agnosticism

Unlike vendor-locked extensions in specific IDEs, our skills are plain Markdown instructions with optional CLI scripts. They run seamlessly in Cursor, Claude Code, OpenCode, or any custom terminal agent.

02 / DETERMINISTIC

Process & Result Certainty

Instead of relying on fuzzy prompts, our skill configurations define strict execution steps, error-handling heuristics, and checklists to guarantee highly predictable agent outcomes.

03 / FILES

Files-as-Interfaces

All inputs and outputs are recorded as plain text files in your local workspace. This eliminates complex server infrastructure, keeping agent changes stateful and reviewable via Git.

Read Blog: Write the Skill Before You Execute Read Blog: Context Infrastructure & AI Cognition

FREQUENTLY ASKED QUESTIONS

Copy the GitHub URL of the skill and tell your agent in the terminal: "Read this repo's rules, clone it under adhoc_jobs/, map a symlink in rules/skills/, and register it in the index." The agent will fetch the code and link it automatically.

ONE-LINE INSTALL

No IDE-specific slash commands. No invoking a skill just to install a skill. Hit copy on any entry and paste into your agent — the prompt already carries the full install procedure for that skill's type.

REPO clone & symlink into rules/skills/
DOC place into your skill-discovery chain

Organized along the agent's working flow — intake → analyze → output — plus the infrastructure that runs it and the practices that guide it. A few skills serve more than one stage; those carry an ↺ also… marker.

INTAKE · CONTEXT IN 12
01
AI Session ExportREPO

Export OpenCode, Claude Code, Codex, Antigravity, and Second Mind sessions into one incremental Markdown archive for browsing and search.

02
AI Session Search & ArchiveDOC

Search multi-source session archives with source routing, lexical-first retrieval, fresh semantic file lists, and privacy-safe result links.

03
intake-skillREPO

Ingest voice recording notes, run local transcription, and maintain organized audio logs.

04
outlook_skillREPO↺ also output

Download, archive, and send Outlook.com emails, parse calendar invites, and format Markdown.

05
online-media-skillREPO

Download and transcribe online media, identify sources, and produce agent-reviewed bilingual SRT with deterministic coverage, rendering, and validation.

06
PDF to MarkdownDOC

Employs Docling parser for high-accuracy tabular and layout extraction from PDFs.

07
Semantic Search SkillREPO

Local-text embedding + cosine similarity search CLI with atomic cache. Supports any OpenAI-compatible endpoint.

08
tavily-skillREPO

Tavily search/extract CLI with stable JSON output optimized for AI agents.

09
google-maps-routing-skillREPO

Google Maps Routes + Geocoding CLI for address resolution, real-time drive time, and leave-by planning.

10
kit-skillREPO↺ also output

Kit Broadcast CLI for Markdown newsletters with dry-run, draft-only, web-only, and tag/segment targeting.

11
docx-skillREPO↺ also output

AI-first DOCX inspection and editing scaffold for Word documents and legacy forms; safe copy, fill, and verify workflow.

12
bright-horizons-photo-syncREPO↺ also output

Back up all My Bright Day events and media visible to an authorized family account, resume downloads, verify integrity, and import without duplicates into a macOS Photos album.

ANALYZE & RESEARCH · DATA INTO INSIGHT 09
13
stripe-skillREPO

Read-only Stripe integrations to extract sales metrics, subscription trends, and logs.

14
ai_usage_dashboardREPO

Track cross-platform API token consumption, estimate costs, and export stats.

15
health-quantificationREPO

Ingest Apple Health metrics, track caffeine/sleep logs, and run regressions in local SQLite.

16
roest-analysisREPO

Scrape Roest coffee roaster API, detect crack clusters, and chart roasting telemetry.

17
Deep Research & SurveyDOC

Gathers info using multiple parallel agents with overlapping topics to cross-validate.

18
Cognitive Profile ExtractionDOC

Iteratively extracts predictable cognitive axioms and traits from conversation logs.

19
Innovation AssistantREPO

Encodes SIT and Think Bigger as executable pipelines with hard validators, turning an agent into a structured innovation engine that produces buildable candidates with derivation chains.

20
firewalla-local-skillREPO

Firewalla local export analysis, device/flow reports, and redacted artifact workflow; home network details stay in local overlays.

21
dataforseo-skillREPO

DataForSEO keyword, SERP, and ranked keyword API CLI for AI agents; keyword suggestions, related keywords, and keywords-for-site queries.

OUTPUT & DELIVERY · ARTIFACTS FOR PEOPLE 15
22
gdocs-skillREPO↺ also intake

Search, publish, share, and manage Google Docs using Markdown and Tab interfaces.

23
pptx.skillREPO

Read, write, and render slide decks with strict design layouts.

24
presentation_skillREPO

Build previewable agent slide decks (Reveal.js): image-rendered slides by default, HTML modules on request—not PPTX.

25
image-generation-skillREPO

Generate text-to-image prompts, edit images, and upscale resolution via Gemini/GPT.

26
tiff-icc-profileREPO

Embed default P3-D65 or custom ICC color profiles into unmarked TIFF files.

27
Share Report to WebDOC

Converts Markdown to HTML pages and deploys to servers via SSH.

28
resend_email_skillREPO

Send custom domain emails, check attachments, and retrieve notifications.

29
imessage_skillREPO

Send macOS iMessages using CLI; maps contacts to local overlay names.

30
typefully-twitter-skillREPO

Schedule draft tweets, queue threads, and fetch X (Twitter) statistics.

31
circle-post-skillREPO

Circle community Markdown conversion, dry-run preflight, and publish/update/delete CLI; community defaults stay in local overlays.

32
iOS UI AutomationDOC

Xcode simulator builds, XCTest UI click-through testing, and visual screenshot verification flows without private data leakage.

33
genai_portrait_skillREPO

Edit portraits, headshots, and ID photos with identity preservation, photographic coherence, multi-image relighting, and alpha outputs.

34
smart_home_skillREPO

AI-facing local smart home control layer with OpenAPI-driven APIs and a lightweight dashboard; integrates Hue, Wemo, Rinnai, Meross, and Amcrest.

35
eink_diaryREPO

Color E-Ink visual diary: every two hours turns what you've been doing into a clay-style image, refreshed to a Raspberry Pi-driven Spectra 6 display.

36
design_skillREPO

Structured UI design judgment skill for AI coding agents; evaluation-first critique, design-system audit, and frontend aesthetic direction across iOS, Android, and Web.

INFRASTRUCTURE · RUN THE AGENTS 09
37
process-launcherREPO

Local HTTP process daemon to bridge GUI/TCC permissions, logs, and process cancellations.

38
opencode_skillREPO

Submit and monitor OpenCode tasks, run cron pipelines, and archive SQLite databases.

39
opencode-dockerREPO

Docker deployment configurations to quickly containerize OpenCode execution environments.

40
AI CLI Agent GuideDOC

Architectural rules for designing CLI interfaces and nesting agent-to-agent calls.

41
Antigravity CLIDOC

Run a headless Gemini agent on Antigravity subscription quota, with first-run setup, file-based prompt/result/log artifacts, sandbox boundaries, timeouts, and fresh conversations.

42
Parallel SubagentsDOC

Orchestrates concurrent background subagents for independent task branches.

43
Claude Code CLI GuideDOC

Runtime best practices (non-interactive calling, nested agent rules, session recovery, and timeout management).

44
chat-gpt-oauth-skillREPO

Use a user-owned ChatGPT Plus/Pro subscription for local browser PKCE, plaintext token lifecycle, refresh, and a minimal Codex request. Owner-only compatibility experiment; unstable and not recommended for production.

45
logto-management-skillREPO

CLI and Python library for managing Logto users and roles via the Management API; 1Password-native credential resolution, two-phase destructive guards, and AI-agent-friendly JSON output.

BEST PRACTICES · WORK WELL 09
46
AI Programming MindsetDOC

Strategy detailing the 70% accuracy boundary and script-writing priority.

47
Skill Writing GuideDOC

Meta-instructions explaining how to write reusable, outcome-focused Skill files.

48
Staged WorkflowDOC

Maintains a strict "isolate-process-validate" loop to execute dry-runs on code changes.

49
Temporal VerificationDOC

Guidelines to verify information lying past model knowledge cutoff dates.

50
Project Scaffold & ReorgDOC

Scaffolds loose workspaces into organized directories (docs/, src/, tests/).

51
Academic Paper IngestionDOC

arXiv ID query aggregation, HTML/PDF conversion to markdown via Docling/Tavily, and duplicate matching quality checks.

52
OpenRouter Data ScraperREPO

Periodically scrape OpenRouter model activity data (token usage, request counts, rankings, benchmarks) into local SQLite, breaking the 31-day trailing window limit.

53
Playwright E2E TestingREPO

CDP step-by-step debugging CLI for AI agents writing Playwright E2E tests; covers SSO flows, modal handling, and known pitfalls.

54
Skill Registry LifecycleDOC

Create, fork, extend, prune, privacy-review, and release a governed skill registry with explicit success criteria.