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

allemaar

45 listings · 0 installs

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

↗ github.com/allemaar
45 results
Self-run
SKILL

Diff Recap

>

0
0
Free
Self-run
SKILL

Map This

Plan and organize a bounded folder, project, or vault using map-rules; audit first, show simple proposals, and apply only selected changes. Trigger when the Handler says "organize this scope", "map this project", or "housekeep this vault".

0
0
Free
Self-run
SKILL

Human Output

>

0
0
Free
Self-run
SKILL

Orient Gaps

>

0
0
Free
Self-run
SKILL

Plan Cleanup

Post-execution cleanup — remove planning artifacts and tech debt left behind after a plan runs. Trigger when the user runs /plan-cleanup, says 'clean up artifacts', 'remove the plan file', or 'no tech debt'. Not /plan-evolve (plans the next version) — plan-cleanup only removes leftovers and adds no new work.

0
0
Free
Self-run
SKILL

Domain Check

>

0
0
Free
Self-run
SKILL

Improve Codebase Architecture

Explore a codebase to find opportunities for architectural improvement by deepening shallow modules (John Ousterhout, "A Philosophy of Software Design"). Use when the user says "improve architecture", "find refactoring opportunities", "make this more testable", "this codebase is hard to navigate", "consolidate these modules", "find coupling problems", "write an RFC for this refactor", or "help me…

0
0
Free
Self-run
SKILL

Insight Skill Gap

>

0
0
Free
Self-run
SKILL

Insight Critique

>

0
0
Free
Self-run
SKILL

Agent Mailbox

>

0
0
Free
Self-run
SKILL

Orient Roadmap

>

0
0
Free
Self-run
SKILL

Orchestrate Mode

>

0
0
Free
Self-run
SKILL

Ask Gate

>

0
0
Free
Self-run
SKILL

Map Maintain

Run one bounded MYK stewardship cycle: map-check, Handler-selected repairs through map-this semantics, then targeted recheck. Trigger on "maintain this map", "tend this graph", or "/map-maintain". Not for autonomous monitoring.

0
0
Free
Self-run
SKILL

Insight Cross Examine

>

0
0
Free
Self-run
SKILL

Plan Create

>

0
0
Free
Self-run
SKILL

Map Check

The honest inspector for Map Your Knowledge — read-only conformance checks of an organized scope via a small bundled script, always reporting what was checked AND what was not; it can never claim an unqualified "all clear". Trigger when the user says "check this map", "check the graph", "is this vault still healthy", "run map-check", or "/map-check". Read-only forever; repairs belong to map-this…

0
0
Free
Self-run
SKILL

Insight Adversarial

>

0
0
Free
Self-run
SKILL

New Skill Creator

Scaffold a new Agent Skill end-to-end into a skills repo you maintain (folder, SKILL.md, optional protocol.yon for dual-doc skills, tri-runtime links for Claude Code + Codex + the shared .agents/ dir, commit and push). The maintainer's authoring loop — it links your own clone into your runtimes because you write the changes those links carry. Trigger when the user runs /new-skill-creator or says…

0
0
Free
Self-run
SKILL

Investigate

Gather facts (files, deps, patterns) without making changes. Trigger when the user runs /investigate or asks to "look into this", "explore the codebase", "understand how this works", "what files are involved", "map the dependencies", or wants read-only fact-gathering before deciding what to do.

0
0
Free
Self-run
SKILL

Insight Retro

>

0
0
Free
Self-run
SKILL

Github Sync

Review the session's git changes, summarize them for approval, then commit and push to GitHub. Trigger when the user runs /github-sync or says "sync to github", "commit and push", "push this session", "wrap up and push", "save this session to git". For commit-only (no push) or partial staging, do not use this skill.

0
1
Free
Self-run
SKILL

Insight Explore

>

0
0
Free
Self-run
SKILL

Cold Review

>

0
0
Free
Self-run
SKILL

Map Rules

The shared Map Your Knowledge (MYK) rulebook for maps, frontmatter, filenames, titles, tags, rollups, archives, and semantic proposals — runtime-neutral rules any agent loads before touching organized vault Markdown. Trigger when the user says "follow the map rules", "structure this note", or "organize vault data". Not for sync or topology.

0
0
Free
Self-run
SKILL

Human Rewrite

>

0
0
Free
Self-run
SKILL

Handoff

Generate a structured cold-agent handoff brief (YAML frontmatter + Obsidian markdown + YON blocks) that any fresh LLM session can pick up and execute. Trigger when the user runs /handoff or says "create a handoff", "dispatch to a fresh agent", "hand this to a cold session", "switch to a new session", "I have N tasks for cold agents", "package this for another agent". Use /orchestrate-mode instead…

0
0
Free
Self-run
SKILL

Orient Status

>

0
0
Free
Self-run
SKILL

Double Check

Targeted re-verification of a specific claim, output, or decision. Re-read sources, challenge, cross-reference, and deliver a verdict. Trigger when the user runs /double-check or asks to "verify this", "re-check this", "are you sure about this", "go over this again", or "make sure this is right". Not /verify (formal phase gate needing intent+plan+execution artifacts) or /insight-critique (advisor…

0
0
Free
Self-run
SKILL

Map Init

Onboard Map Your Knowledge into a user's agent directives — check whether it is already installed, or offer to add the routing rules globally or per-project, for EVERY agent platform on the machine, with explicit consent and a per-platform manual fallback. Trigger when the user says "install map your knowledge", "set up myk", "make this my agents' default", or "/map-init". Idempotent and consent-…

0
0
Free
Self-run
SKILL

Multi Agent Mode

>

0
0
Free
Self-run
SKILL

Plan Deep Dive

>

0
0
Free
Self-run
SKILL

Handoff Execute

Execute a handoff brief with enforced source-read discipline — load the brief's @SOURCES.required tier fully before planning, cite sources per plan step, run @OUTCOME.verify after, emit the retro per @GROUND_TRUTH_REQUIRED. Trigger when the user runs /handoff-execute <brief-path>, or pastes the activation phrase emitted by /handoff. Not auto-triggered — the receiving session invokes explicitly. U…

0
0
Free
Self-run
SKILL

Next Skills

>

0
0
Free
Self-run
SKILL

Human Draw

>

0
0
Free
Self-run
SKILL

Orient Map

>

0
0
Free
Self-run
SKILL

Extract Signal

>

0
0
Free
Self-run
SKILL

Monorepo Deps

>

0
0
Free
Self-run
SKILL

Insight Assess

>

0
0
Free
Self-run
SKILL

Budget Check

>

0
0
Free
Self-run
SKILL

Design An Interface

Generate multiple radically different interface designs for a module, then compare and synthesize. Use when the user wants to design an API, explore interface options, compare module shapes, or says "design it twice" / "give me options" / "what should this interface look like". Also trigger proactively when a user is about to implement something non-trivial and hasn't locked in an interface yet.…

0
0
Free
Self-run
SKILL

Human Merge

>

0
0
Free
Self-run
SKILL

Insight Angles

>

0
0
Free
Self-run
SKILL

Caller Options

>

0
0
Free
Self-run
SKILL

Audit Coupled Constant

Audit every site of a constant whose value is duplicated across multiple call sites (retry budgets, timeouts, page sizes, magic numbers, feature flags). The author-maintained `SEE ALSO` trail is documentation, not enforcement — one missed site means the trail lies. Trigger on /audit-coupled-constant, "audit budget consistency", "find all sites of this value", "check coupled invariant", "before ra…

0
1
Free
You've reached the end · 45 loaded