AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
Arasz avatar

Arasz

34 listings · 0 installs

Open-source publisher. Listings imported from github.com/Arasz — credited to the original author with their license.

↗ github.com/Arasz
34 results
Self-run
SKILL

Mcp Index

>-

0
20
Free
Self-run
SKILL

Worktree Agent Isolation

Use when running multiple agents in parallel, or when the user says 'worktrees only', 'agent isolation', 'parallel workstreams', or 'don't touch main': give each agent its own git worktree branched from origin/main (fetch first), integrate via GitHub PRs, keep the main checkout read-only, and avoid shared obj/ races and file-modification conflicts.

0
15
Free
Self-run
SKILL

Task

>-

0
18
Free
Self-run
SKILL

Migrate Documentation

>-

0
19
Free
Self-run
SKILL

Code Review Evidence

Use when reviewing code that wraps external libs/extensions/SDKs/CLIs, or QA-reviewing a test harness: verify wrapped-library semantics from the upstream source (not comments/spec), query the real store read-only for data claims, and hunt tautological tests that assert values the code constructed itself. Catches spec-vs-coverage gaps, fake honesty, hygiene.

0
16
Free
Self-run
SKILL

Design Gate Audit

Use when auditing a design doc's acceptance gates BEFORE implementation: check every gate would fail if the feature were broken (HONEST) and the named test file/framework/seam exists (FEASIBLE). Attacks vacuous negatives, timing-window vacuity, port races, env poisoning, unprovable real-time halves. Pairs with dotnet-hosted-service-testing for FakeTimeProvider mechanics.

0
13
Free
Self-run
SKILL

Documentation Drift Audit

Use when auditing docs for drift vs code ('audit and fix documentation drift'): inventory claims with path:line, verify each against real files (scaffolders, manifests, hooks), classify verifiably-false vs design-position vs ambiguous vs historical, fix only the false, and report A/B/C. Also for post-merge doc-gap audits and user-facing doc compaction rewrites.

0
12
Free
Self-run
SKILL

Owner Gate Review

>-

0
11
Free
Self-run
SKILL

Complete Project Scope Code Review

>-

0
20
Free
Self-run
SKILL

Refactor Safely

>-

0
16
Free
Self-run
SKILL

Maintain Agent Instructions

>-

0
15
Free
Self-run
SKILL

Differential Feature Refactor

>-

0
17
Free
Self-run
SKILL

Call Behaviorist

>-

0
17
Free
Self-run
SKILL

Ai Raccoon Memory

>-

0
16
Free
Self-run
SKILL

Evidence First Research

>-

0
16
Free
Self-run
SKILL

Code Review Checklist

>-

0
15
Free
Self-run
SKILL

Update Documentation

>-

0
19
Free
Self-run
SKILL

Den Refresh

>-

0
17
Free
Self-run
SKILL

Scaffold Documentation

>-

0
18
Free
Self-run
SKILL

Welcome Ai Badger

>-

0
15
Free
Self-run
SKILL

Feed Badger

>-

0
15
Free
Self-run
SKILL

Semantica Knowledge Graph

>-

0
16
Free
Self-run
SKILL

Commit Reminder

>-

0
14
Free
Self-run
SKILL

Explore Codebase

>-

0
19
Free
Self-run
SKILL

Artifact Verification

Use when verifying changed artifacts that lack a canonical test gate — specs, docs, manifests, generated files, published packages: use the workflow-defined checker first (spec_holes.py), review manual fresh-install protocols against the false-pass checklist, and verify 'installed build contains merged PR X' by tree comparison, never squash-ancestry.

0
10
Free
Self-run
SKILL

Debug Issue

>-

0
16
Free
Self-run
SKILL

Hermes Plugin Development

Use when writing or debugging Hermes Agent Python plugins — including the memory-provider specialized plugin type: directory-plugin packaging (plugin.yaml + __init__.py with register(ctx) — flat .py files are INVISIBLE), VALID_HOOKS list, per-hook payload keys (no cwd; tool_name vs function_name), plugins.enabled opt-in, pre_llm_call context injection, stash/pop for post_tool_call, HERMES_PLUGINS…

0
13
Free
Self-run
SKILL

Ai Raccoon Manual Checklist

>-

0
16
Free
Self-run
SKILL

Prompt Markers

>-

0
14
Free
Self-run
SKILL

Humanizer

>-

0
19
Free
Self-run
SKILL

Auto Wm

Use when the user wants Claude to auto-approve tool calls — "enable autonomic/autonomous work mode", "/auto-wm", "partner mode", "work by yourself for N hours", "no one will be around to approve/answer" — or to check status, switch modes, or turn it off ("awm status", "auto-wm away 4h", "auto-wm off").

0
17
Free
Self-run
SKILL

Review Changes

>-

0
13
Free
Self-run
SKILL

Cron Watchdog Authoring

Use when scheduling a Hermes cron job or writing a watchdog script: recurring schedules need 'every 30m' (bare '30m' is ONE-SHOT — check repeat), no_agent+script shape, silent-unless-action stdout discipline, version-gated rollout watchdogs (marker files, surgical port-kill), idempotent ticks, and verifying CLI verb paths before the rollout branch can run.

0
17
Free
Self-run
SKILL

Create Task Spec

>-

0
16
Free
You've reached the end · 34 loaded