agent-guards

In the author's own words, from each skill's SKILL.md — showing the first 29 of 73 files.

• architect

  Design features, subsystems, and substantial refactors through component boundaries, caller usage, data models, and interfaces before implementation. Use when asked to architect a change, choose a design, or decide where code and responsibilities should live.

  skills/architect/SKILL.md on GitHub (opens in a new tab)

• concisely

  Present concise plans, progress updates, findings, and final reports that keep the human oriented, informed, and able to learn how the project works. Use for complex agent coding work and focus on the most important points and decisions.

  skills/concisely/SKILL.md on GitHub (opens in a new tab)

• explain-report

  Create a self-contained HTML explanation when the user requests one or when important, durable project knowledge is materially easier to understand visually than in concise chat. Use for significant architecture, research, decisions, incidents, audits, or changes that the user may revisit. Do not use for routine status, simple answers, or unverified findings.

  skills/explain-report/SKILL.md on GitHub (opens in a new tab)

• find-bugs

  Find important, high-confidence correctness bugs and edge cases in an existing codebase. Use when the user asks to inspect a repository, subsystem, or implementation for bugs, failure modes, incorrect behavior, or overlooked edge cases.

  skills/find-bugs/SKILL.md on GitHub (opens in a new tab)

• find-quick-wins

  Find low-risk, high-confidence improvements in a codebase that an agent can fix and prove on its own, and optionally fix them as small PRs. Use when the user asks for quick wins, low-hanging fruit, easy fixes, or continuous small improvements to a repo or subsystem. For a deep hunt for severe bugs regardless of fix size, use find-bugs.

  skills/find-quick-wins/SKILL.md on GitHub (opens in a new tab)

• learn-from-mistake

  Find why an agent produced a bad result, strengthen the code, repository, verification, tooling, or workflow that enabled it, then retry the original task. Use when the user asks to learn from a mistake, prevent recurrence, or postmortem an agent failure.

  skills/learn-from-mistake/SKILL.md on GitHub (opens in a new tab)

• new-task

  Clarify a new task by stating the goal the agent believes the user wants, showing its current understanding, and asking only product-related or high-priority questions that could materially change the outcome. Use before planning or implementation when the task needs alignment.

  skills/new-task/SKILL.md on GitHub (opens in a new tab)

• ori-pr

  Take an OpenRouterIncubator/ori PR from ready to merged. Matthew runs /ori-pr once he has decided the PR is ready and understands the change. Asks perry for review once CI is green, handles perry's comments, and enqueues the merge once perry approves the head and CI is green, within quiet hours.

  skills/ori-pr/SKILL.md on GitHub (opens in a new tab)

• record-screen

  Record a small MP4 while demonstrating or verifying a UI change, then attach the video as proof. Linux cloud sessions record the private virtual display; macOS records only the app window under test. Use for any repo whenever a UI change is verified or demoed.

  skills/record-screen/SKILL.md on GitHub (opens in a new tab)

• repo-setup

  Set up or refactor a repository so agents naturally follow its intended architecture and important mistakes fail mechanically. Use when the user invokes $repo-setup, asks to make a repo agent-friendly, or wants important repository rules enforced through structure, types, tooling, tests, or CI.

  skills/repo-setup/SKILL.md on GitHub (opens in a new tab)

• skills-audit

  Audit agent skills for triggering quality, correctness, context efficiency, redundancy, structure, failure guidance, and coverage gaps. Use when the user asks to review, improve, compare, simplify, or evaluate skills in global, repo-local, Claude, Codex, or custom skill paths.

  skills/skills-audit/SKILL.md on GitHub (opens in a new tab)

• teach

  Help the user build a working mental model of code, system designs, and proposed changes, including code outside the current repo. Use when asked to teach, explain how a system works, walk through an architecture, compare a design with ours, or understand a change.

  skills/teach/SKILL.md on GitHub (opens in a new tab)

• arena

  Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

  plugins/pstack/skills/arena/SKILL.md on GitHub (opens in a new tab)

• automate-me

  Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.

  plugins/pstack/skills/automate-me/SKILL.md on GitHub (opens in a new tab)

• benchmark-checklist

  Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.

  plugins/pstack/skills/benchmark-checklist/SKILL.md on GitHub (opens in a new tab)

• blast-radius

  Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.

  plugins/pstack/skills/blast-radius/SKILL.md on GitHub (opens in a new tab)

• bro

  Restate the last message in plain human language, with no jargon.

  plugins/pstack/skills/bro/SKILL.md on GitHub (opens in a new tab)

• correct

  Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.

  plugins/pstack/skills/correct/SKILL.md on GitHub (opens in a new tab)

• create-formal-verification-skill

  Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.

  plugins/pstack/skills/create-formal-verification-skill/SKILL.md on GitHub (opens in a new tab)

• create-verification-skill

  Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

  plugins/pstack/skills/create-verification-skill/SKILL.md on GitHub (opens in a new tab)

• figure-it-out

  Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.

  plugins/pstack/skills/figure-it-out/SKILL.md on GitHub (opens in a new tab)

• how

  Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

  plugins/pstack/skills/how/SKILL.md on GitHub (opens in a new tab)

• in-your-own-words

  Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.

  plugins/pstack/skills/in-your-own-words/SKILL.md on GitHub (opens in a new tab)

• interrogate

  Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Adversaries try to break a change or design, and only findings proven by a run survive.

  plugins/pstack/skills/interrogate/SKILL.md on GitHub (opens in a new tab)

• ketchup-video

  Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.

  plugins/pstack/skills/ketchup-video/SKILL.md on GitHub (opens in a new tab)

• ketchup

  Catch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /ketchup.

  plugins/pstack/skills/ketchup/SKILL.md on GitHub (opens in a new tab)

• maintain-formal-verification-skill

  Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, "is the model still true to the code", or after merges an…

  plugins/pstack/skills/maintain-formal-verification-skill/SKILL.md on GitHub (opens in a new tab)

• maintain-verification-skill

  Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

  plugins/pstack/skills/maintain-verification-skill/SKILL.md on GitHub (opens in a new tab)

• make-bot-ui

  Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

  plugins/pstack/skills/make-bot-ui/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 434k stars · 5 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 315k stars · 30 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 313k stars · 15 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 298k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 230k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 188k stars · 19 skills