← All skill packs

AI Agent Workflow Collection

Skill pack
26 skills0 selected
terrylicaSkills in this pack

Convert academic PDF papers to GitHub-renderable GFM markdown with math equations.

English

Add ADR references to code for traceability. TRIGGERS - ADR traceability, code reference, document decision in code.

English

Monitor background processes from Claude Code using sentinel files, heartbeat liveness, and subagent polling. Best practices and anti-patterns for autonomous loops that need to kick off work, detect completion/failure/hang/timeout, and resume the main context without wasting tokens. TRIGGERS - monitor background process, sentinel file, heartbeat monitoring, process supervision, agentic loop monitor, background task health, detect hung process, poll for completion, watchdog pattern, process liveness, monitor long-running task, agent poll loop, circuit breaker pattern.

English

Convert .cast recordings to .txt for analysis. TRIGGERS - convert cast, cast to txt, strip ANSI, batch convert.

English

Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.

English

Augment Kokoro TTS engine — upgrade dependencies and model. Renamed from 'upgrade' to avoid clashing with Claude Code's built-in.

English

Use when starting a new research campaign, entering a new Claude Code session on a research repo, or when unsure which methodology principle applies. Orients agents to the plugin's 4 specialized skills (foundations, investigation, meta-governance, resurrection) and the genetic-evolutionary framing that treats hypotheses as a population under selection. Covers reading order, when-to-invoke routing, and anti-patterns. TRIGGERS - new research campaign, where to start, which skill to use, how to approach, getting oriented, first time here, genetic evolutionary research, self-evolving methodology.

English

Use when validating whether a finding is real, designing a shuffled null, checking for label leakage, reviewing causal feature definitions, interpreting agent-reported z-scores, or setting up append-only record-keeping. Covers the 6 epistemic disciplines that prevent known methodological traps — invariant causality (bars[:i] only), bar-local label scaling (not window-relative), three null types (feature-shuffle vs mask-shuffle vs selection-shuffle), agent z-score overstatement corrections, audit-folder ledger discipline, and the post-mortem-before-abandon rule. TRIGGERS - shuffled null, permutation test, causal feature, label leakage, look-ahead bias, z-score significance, Bonferroni correction, bar-local scaling, epistemic discipline, record keeping, audit folder, supersedes ledger, is this real, signal validation, null hypothesis design.

English

List or validate Pushover notification sounds (built-in plus this account's custom uploaded sounds) via the /1/sounds.json API. Use when choosing a notification sound, checking whether a custom sound exists, or picking a safe fallback before sending. TRIGGERS - pushover sounds, list sounds, validate sound, custom sound, which sounds.

English

Send a Pushover EMERGENCY (priority 2) alert that repeats until acknowledged, then poll the receipt until the user acks or it expires. Use when something is urgent and must not be missed - production breakage, a blocked autonomous loop needing immediate input, an alarm-until-acknowledged notification. For routine notifications use send-notification. TRIGGERS - emergency alert, urgent pushover, alarm until acknowledged, priority 2, wake me up.

English

DST-aware exchange session detection using exchangecalendars. Holiday & lunch break handling.

English

Interactive helper for granting macOS Full Disk Access (FDA) to a launchd-spawned binary.

English

Machine-wide loop muster — enumerate every registered loop with health, ownership, and staleness. Renamed from 'status' to avoid.

English

Investigate why ODB bars are oversized, have zero duration, or show anomalous price ranges by forensically analyzing Parquet.

English

evaluating open deviation bar signal quality, computing Sharpe ratios with non-IID bars, running PSR/DSR/MinTRL statistical tests, or assessing.

English

Run a structured quality review before shipping code at any checkpoint such as PRs, releases, or milestones. Use whenever the user says.

English

Send Pushover notifications with UUID-linked verbatim JSONL audit trail.

English

Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU workstations. Use this skill proactively whenever writing or reviewing Python scripts that: run under systemd with MemoryMax, process data in loops (downloads, ETL, backfill), use ThreadPoolExecutor, or make repeated HTTP requests. Also use when diagnosing OOM kills, RSS creep, or fd exhaustion in Python services. TRIGGERS - memory optimization, OOM prevention, RSS reduction, malloctrim, systemd MemoryMax, memory leak, allocator purge, memory-safe script, RSS creep, fd exhaustion, SIGKILL status 9, MemoryHigh, glibc arena, mimalloc purge, requests memory leak, ThreadPoolExecutor cleanup.

English

Terminate (quench) the running FloatingClock process. Renamed from 'quit' to avoid clashing with Claude Code's built-in /quit.

English

Scion (create or configure) a fork workflow with git-town. Renamed from 'fork' to avoid clashing with Claude Code's built-in.

English

Create new skills, modify existing skills, and understand skill architecture. Use when users want to create a skill from scratch, learn YAML frontmatter standards, validate skill structure, understand progressive disclosure patterns, or choose between structural patterns (workflow, task, reference, capabilities, suite). Also use for troubleshooting skills that don't trigger correctly, optimizing skill descriptions, or learning best practices for writing effective skill instructions.

English

Tether (install/uninstall) hooks for auto-backup on session end. Renamed from 'hooks' to avoid clashing with Claude Code's.

English

Diagnose and repair the documented autoloop bootstrap failure modes for a registered loop. Idempotent. Use when a loop is registered but doesn't fire, when ownersessionid is stuck at "pending-bind", or after a marketplace update that may have left stale plists. Renamed from "doctor" to avoid clashing with Claude Code's /doctor. TRIGGERS - autoloop doctor, autoloop repair, autoloop fix, fix loop, repair loop, pending-bind, loop won't fire, loop not firing.

English

ZigZag swing pattern classification for algorithmic trading. UP-DOWN and UP-DOWN-UP patterns.

English

Includes Academic PDF to Gfm, Adr Code Traceability, Agentic Process Monitor, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills26CategorygeneralStars0

What’s included

Academic PDF to Gfm

Convert academic PDF papers to GitHub-renderable GFM markdown with math equations. TRIGGERS - PDF, GitHub markdown, math

Adr Code Traceability

Add ADR references to code for traceability. TRIGGERS - ADR traceability, code reference, document decision in code.

Agentic Process Monitor

Monitor background processes from Claude Code using sentinel files, heartbeat liveness, and subagent polling. Best practices and anti-patterns for autonomous loops that need to kick off work, detect completion/failure/hang/timeout, and resume the main context without wasting tokens. TRIGGERS - monitor background process, sentinel file, heartbeat monitoring, process supervision, agentic loop monitor, background task health, detect hung process, poll for completion, watchdog pattern, process liveness, monitor long-running task, agent poll loop, circuit breaker pattern.

Asciinema Converter

Convert .cast recordings to .txt for analysis. TRIGGERS - convert cast, cast to txt, strip ANSI, batch convert.

Asciinema Recorder

Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.

Augment

Augment Kokoro TTS engine — upgrade dependencies and model. Renamed from 'upgrade' to avoid clashing with Claude Code's built-in.

Crucible Navigator

Use when starting a new research campaign, entering a new Claude Code session on a research repo, or when unsure which methodology principle applies. Orients agents to the plugin's 4 specialized skills (foundations, investigation, meta-governance, resurrection) and the genetic-evolutionary framing that treats hypotheses as a population under selection. Covers reading order, when-to-invoke routing, and anti-patterns. TRIGGERS - new research campaign, where to start, which skill to use, how to approach, getting oriented, first time here, genetic evolutionary research, self-evolving methodology.

Crucible Research Foundations

Use when validating whether a finding is real, designing a shuffled null, checking for label leakage, reviewing causal feature definitions, interpreting agent-reported z-scores, or setting up append-only record-keeping. Covers the 6 epistemic disciplines that prevent known methodological traps — invariant causality (bars[:i] only), bar-local label scaling (not window-relative), three null types (feature-shuffle vs mask-shuffle vs selection-shuffle), agent z-score overstatement corrections, audit-folder ledger discipline, and the post-mortem-before-abandon rule. TRIGGERS - shuffled null, permutation test, causal feature, label leakage, look-ahead bias, z-score significance, Bonferroni correction, bar-local scaling, epistemic discipline, record keeping, audit folder, supersedes ledger, is this real, signal validation, null hypothesis design.

Custom Sounds

List or validate Pushover notification sounds (built-in plus this account's custom uploaded sounds) via the /1/sounds.json API. Use when choosing a notification sound, checking whether a custom sound exists, or picking a safe fallback before sending. TRIGGERS - pushover sounds, list sounds, validate sound, custom sound, which sounds.

Emergency Priority2 Receipt

Send a Pushover EMERGENCY (priority 2) alert that repeats until acknowledged, then poll the receipt until the user acks or it expires. Use when something is urgent and must not be missed - production breakage, a blocked autonomous loop needing immediate input, an alarm-until-acknowledged notification. For routine notifications use send-notification. TRIGGERS - emergency alert, urgent pushover, alarm until acknowledged, priority 2, wake me up.

Exchange Session Detector

DST-aware exchange session detection using exchangecalendars. Holiday & lunch break handling. TRIGGERS - exchange session, trading hours

Macos Fda Grant Helper

Interactive helper for granting macOS Full Disk Access (FDA) to a launchd-spawned binary. TRIGGERS - full disk access, fda grant, TCC permission, "Maccy DB unreadable", "operation not permitted" on sandbox-protected paths, launchd binary needs file access

Muster

Machine-wide loop muster — enumerate every registered loop with health, ownership, and staleness. Renamed from 'status' to avoid.

Odb Microstructure Forensics

Investigate why ODB bars are oversized, have zero duration, or show anomalous price ranges by forensically analyzing Parquet.

Opendeviation Eval Metrics

evaluating open deviation bar signal quality, computing Sharpe ratios with non-IID bars, running PSR/DSR/MinTRL statistical tests, or assessing.

Pre Ship Review

Run a structured quality review before shipping code at any checkpoint such as PRs, releases, or milestones. Use whenever the user says.

Pushover Verbatim Notify

Send Pushover notifications with UUID-linked verbatim JSONL audit trail. TRIGGERS - pushover notify, send pushover, observability alert, verbatim notification, fleet alert, pushover-lookup, audit log notification, push notification with UUID

Python Memory Safe Scripts

Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU workstations. Use this skill proactively whenever writing or reviewing Python scripts that: run under systemd with MemoryMax, process data in loops (downloads, ETL, backfill), use ThreadPoolExecutor, or make repeated HTTP requests. Also use when diagnosing OOM kills, RSS creep, or fd exhaustion in Python services. TRIGGERS - memory optimization, OOM prevention, RSS reduction, malloctrim, systemd MemoryMax, memory leak, allocator purge, memory-safe script, RSS creep, fd exhaustion, SIGKILL status 9, MemoryHigh, glibc arena, mimalloc purge, requests memory leak, ThreadPoolExecutor cleanup.

Quench

Terminate (quench) the running FloatingClock process. Renamed from 'quit' to avoid clashing with Claude Code's built-in /quit.

Scion

Scion (create or configure) a fork workflow with git-town. Renamed from 'fork' to avoid clashing with Claude Code's built-in.

Skill Architecture

Create new skills, modify existing skills, and understand skill architecture. Use when users want to create a skill from scratch, learn YAML frontmatter standards, validate skill structure, understand progressive disclosure patterns, or choose between structural patterns (workflow, task, reference, capabilities, suite). Also use for troubleshooting skills that don't trigger correctly, optimizing skill descriptions, or learning best practices for writing effective skill instructions.

Tether

Tether (install/uninstall) hooks for auto-backup on session end. Renamed from 'hooks' to avoid clashing with Claude Code's.

Tinker

Diagnose and repair the documented autoloop bootstrap failure modes for a registered loop. Idempotent. Use when a loop is registered but doesn't fire, when ownersessionid is stuck at "pending-bind", or after a marketplace update that may have left stale plists. Renamed from "doctor" to avoid clashing with Claude Code's /doctor. TRIGGERS - autoloop doctor, autoloop repair, autoloop fix, fix loop, repair loop, pending-bind, loop won't fire, loop not firing.

Zigzag Pattern Classifier

ZigZag swing pattern classification for algorithmic trading. UP-DOWN and UP-DOWN-UP patterns. TRIGGERS - zigzag, swing classification

Showing 24 of 26 skills. Use the list’s page controls above to explore the rest.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Academic PDF to Gfm skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • Reported license for the skills shown: MIT. The author’s terms apply.
AI Agent Workflow Collection | Agent Skills Atlas