kirodotdev

@kirodotdev source repo

70 skills
0 followers
8 hours ago last updated

▌
Kiro Support · kirodotdev bundle
File and track AWS Support cases for Kiro issues without leaving the IDE. Use when creating, tracking, replying to, or resolving AWS Support cases, or when checking Support API access.

0
installs
▌
Create Plugin · kirodotdev
Create a new Kiro Power using the Agent Plugins v1.0.0 specification. Use when building a new power from scratch with plugin.json, skills, and optional MCP server configuration.

0
installs
▌
Migrate Plugin · kirodotdev
Migrate an existing POWER.md-based Kiro Power to the Agent Plugins v1.0.0 specification. Use when converting a power that uses POWER.md frontmatter and steering files to the plugin.json and skills/ format.

0
installs
▌
Agent Plugins Reference · kirodotdev
Reference documentation for the Agent Plugins v1.0.0 specification. Use when you need to understand plugin structure, plugin.json schema, SKILL.md format, mcp.json configuration, or environment variable expansion.

0
installs
▌
Spec Workflow · kirodotdev
Drive the Kiro CLI v3 spec workflow (Requirements → Design → Tasks → Execution) for the Spec Builder app. Load when authoring a spec inside a spec-builder worker slot, or when the seed prompt references a spec directory and a spec type.

0
installs
▌
AI Discover · kirodotdev
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes and no verification happen here.

0
installs
▌
Sage Review · kirodotdev
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.

0
installs
▌
Kirocrew Worktree Dev · kirodotdev
HARD RULE for developing the Kiro Crew source repo ITSELF (not users' projects): develop, build and verify in a git worktree, never against the live gateway. Covers environment setup, build/dist ordering, feature flags, isolated previews, cleanup and publication authorization; prepare-pr owns the PR workflow.

0
installs
▌
Release Notes · kirodotdev
Draft a release note section from a commit range, grouped by what the reader gets.

0
installs
▌
Metric Design · kirodotdev
Phase 1 of the auto-improvement loop — analyze the target repository, then design and calibrate the ruler (the trustworthy metric) BEFORE any optimization. Produces a low-variance primary metric, frozen anchors, a calibrated noise band, guardrails, reward-hack guards, and a mandatory canary that must clear the band or the ruler is rejected.

0
installs
▌
Design Critique · kirodotdev bundle
Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what the evidence cannot reveal. Triggers: 'critique this design', 'evaluate this UI', 'usability review', 'design review', 'heuristic evaluation', 'roast my design', 'is this a good design', 'review this mockup/screen/figma'.

0
installs
▌
Learn From Sage · kirodotdev
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.

0
installs
▌
Feature Demo Recording · kirodotdev bundle
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen recording of a feature, dashboard, or web UI flow.

0
installs
▌
Personal Shopper · kirodotdev
Personal advisor for a problem that might be solved by buying something — diagnoses the real need through conversation, then recommends products from the user's configured stores only when a purchase is the right answer. Recalls the user's sizes, budget, brands and restrictions across sessions, and records new ones as they surface. Never purchases; always hands back a link. Load when the user asks for product help, shopping advice, gift ideas, or "help me find / what should I get".

0
installs
▌
Auto Flaky Triage · kirodotdev bundle
Classify a red test as a real regression, a flake, or an environment problem before patching.

0
installs
▌
Grill · kirodotdev
Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks memory for already-answered questions, saves every answer as a lesson. Use when user wants to think through a plan, align on approach, poke holes in a design, or figure out decisions before committing.

0
installs
▌
Goal Loop · kirodotdev bundle
Bootstrap a goal-driven self-improving AutoNudge loop from a goal plus an anchor directory, then run the board autonomously until the Definition of Done is met.

0
installs
▌
Rubber Duck · kirodotdev
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that has NOT seen the reasoning and interrogates it adversarially, hunting inconsistencies, gaps, unsupported magnitudes, and claims stated as fact but actually inferred. Goal — artifacts that are complete, gaps that are honest, findings that are truthful. Triggers include "rubber duck this", "rubber duck review", "explain this to a skeptic", "reconcile my findings", "is my doc honest".

0
installs
▌
Self Update · kirodotdev
Check for and apply KiroCrew updates. Use when user says "update yourself", "check for updates", "are you up to date", "keep yourself updated", or "auto-update".

0
installs
▌
Gateway Restart · kirodotdev bundle
Gracefully restart the KiroCrew gateway from within a running agent session, preserving conversation continuity via scheduled resume jobs. Use when user says "restart yourself", "restart gateway", "reload config", or after config changes that require a restart.

0
installs
▌
Self Nudge Loop · kirodotdev bundle
Build a reactive same-session autonomy loop using KiroCrew's AutoNudgeService. One long-lived dashboard session keeps working toward a goal — when its turn completes and no user input arrives within idle_secs, the service auto-injects a nudge message into the SAME session. Survives tab close, logout, and gateway restart. Use when user says "continuous improvement session", "keep going on its own", "same session loop", "self-nudge", "north star loop", or wants one persistent session that auto-resumes whenever idle. NOT for fresh-session crons, parallel work, or external-system callbacks.

0
installs
▌
Kirocrew App Dev · kirodotdev
Build, package, and publish KiroCrew external apps. Covers app.json manifest, UI components, crons, skills, self-healing install, git publishing, and common pitfalls.

0
installs
▌
Widgets · kirodotdev
Render rich HTML inline via `<mcwidget>` tags with theme-aware styling. Load when emitting an mcwidget so the iframe inherits the dashboard theme instead of clashing with light / dark / custom palettes.

0
installs
▌
Meetings · kirodotdev
Context for working with the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks, and calendar cache live, what the lifecycle states mean, and how the app's agents are driven. Load when the user asks about a meeting's notes or action items, or when writing/reading files under the meetings app data dir.

0
installs
▌
Artifacts · kirodotdev
Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown). Load when the user wants to save, find, update, or iterate on a previously-rendered widget — anything that should outlive the chat scrollback.

0
installs
▌
Five Whys · kirodotdev bundle
Enter a guided dive-deep research mode — 5 Whys is the default engine (one focused question at a time along a What-it-is -> Example -> Why-not-alternatives -> Benefits -> Costs chain, user-steered branching), every step appended to an event-sourced log the tree and report are folded from, and extensible with plug-in capabilities (web search, recap, ...) that share that log.

0
installs
▌
Deploy Web · kirodotdev
Publish a KiroCrew artifact (HTML / markdown / widget) to a public HTTPS URL on the user's own AWS account (private S3 + CloudFront + OAC). Use when the user says "publish this publicly", "deploy this artifact to the web", "make this a public URL", "deploy-web", or asks to set up / recall / destroy a deploy-web site. KiroCrew never stores credentials — only an AWS profile name.

0
installs
▌
PPTX Maker · kirodotdev
Generate or restyle a PowerPoint deck. Use when the user wants to create or edit a .pptx presentation, build slides from text or a URL, or design a reusable slide style.

0
installs
▌
Web Browse · kirodotdev
Open a REAL external web page so the user can see it in Kiro Crew's Browser panel. PRIMARY path is the `browser` MCP tool (drives the built-in native panel); playwright-cli is the fallback for remote/plain-browser sessions and for attached logged-in browsers. Use when the user wants to VIEW / verify / "show me" an actual website or public URL (not a local dev server, that is the web-preview skill).

0
installs
▌
Web Verify · kirodotdev bundle
Web Verify: look at your own front-end change

0
installs
▌
Crystallize · kirodotdev
Capture the current session as a reusable skill — staged as a candidate by default, or live only when the user explicitly asks for a live/active skill.

0
installs
▌
Explain For · kirodotdev
Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground truth before simplifying, then tunes vocabulary, analogy source, tone, depth and framing to that audience instead of producing one generic explanation.

0
installs
▌
LLM Council · kirodotdev
Use for hard, high-stakes, ambiguous, or subjective questions, group decisions, or reviews where a second (and third) opinion from different model families adds real signal. Convene a cross-vendor LLM council — the main session acts as Chairman and spawns several subagents, each pinned to a DIFFERENT model (Anthropic / OpenAI / DeepSeek / Zhipu / Qwen / etc. via kiro-cli). Three modes — synthesis (independent answers merged into one), vote (structured ballots + majority tally), and adversarial (red-team a target artifact into a SHIP/REVISE/REJECT verdict).

0
installs
▌
Web Preview · kirodotdev
Emit a hidden preview marker so Kiro Crew's right-panel "Browser" tab opens with a Load-preview card for the URL when you start a local web server for the user to preview. Use whenever you start a dev server or static server so the user can see a site/app you're working on (Vite, Next, `npm run dev`, `python -m http.server`, etc.).

0
installs
▌
Browser Auth · kirodotdev
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.

0
installs
▌
Computer Use · kirodotdev
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full tool set on macOS and Windows; on Windows a keystroke takes the user's keyboard focus and a coordinate click moves their real cursor. Off unless the user enabled it in Settings.

0
installs
▌
Goal Conductor · kirodotdev bundle
Use when the user hands over a goal too large for one session ("clear the flaky-test backlog", "take this feature from design to PRs", "push these N PRs green") and wants the fleet's state to be readable rather than inferred. Own a long-horizon goal end to end while tracking it in the work ledger - decompose it into items, stand up one session per item, read each worker's reported status as structured data rather than as a transcript, verify claims with the acceptance evaluator, and decide each next round until the goal is met or a stop condition fires.

0
installs
▌
Artifact Deploy · kirodotdev bundle
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".

0
installs
▌
Feature Request · kirodotdev
Conversational workflow for gathering user feedback and filing GitHub Issues on the Kiro Crew repository. Load when the user clicks "Request a Feature", wants to report a bug, or suggest an improvement.

0
installs
▌
Image Authoring · kirodotdev
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.

0
installs
▌
Papyrus Writing · kirodotdev
Base skill for the Papyrus writing assistant — the conduct, paper-quality principles, and LaTeX house style that every Papyrus editing task builds on. Load this first when working on a .tex paper in Papyrus. For the mechanics of a specific task, also load papyrus-latex-comments, papyrus-latex-suggestions, papyrus-make-fluent, or papyrus-diagnose-compilation.

0
installs
▌
Blocked By Policy · kirodotdev
What to do when a Kiro Crew safety policy blocks a tool call — how to tell a policy block from a user refusal, and the sanctioned path for each class of block (AWS credentials, enterprise SSO, key files, the governance trust root, exfiltration-shaped requests, and the self-protection floor). Load when a tool result says a command was denied, when a credential or AWS access attempt is refused, or before concluding that this host lacks a capability.

0
installs
▌
Browser Recording · kirodotdev bundle
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI, or when a UI change involves motion or a sequence of steps.

0
installs
▌
Kirocrew Commands · kirodotdev
Complete CLI reference for Kiro Crew commands. Use for help, commands, setup, how to, what can you do, getting started, onboarding.

0
installs
▌
Session Summaries · kirodotdev
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.

0
installs
▌
Cron Cost Optimize · kirodotdev bundle
Audit the cron jobs a user already registered and recommend a cheaper execution mode for each one, either a zero-token script or command job, or an agent job with minimal context. Use when the user asks why their scheduled jobs cost so much, wants to cut cron or automation token spend, asks which crons could be scripts, or is porting existing scheduled jobs into Kiro Crew and wants cost-efficient defaults. Read-only by default, and it never edits a job on its own.

0
installs
▌
Pipeline Conductor · kirodotdev bundle
Use when a pipeline conductor session is being seeded, or when inspecting/debugging one. Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, preflight every candidate to one deterministic claim verdict, stand up one worker session per item in a dedicated folder, probe them each cycle with one script call, verify claimed greens independently, intervene when a worker loops or stalls, adjudicate blocked items under the override protocol, throttle admission on delivery capacity, enforce per-item credit budgets, track the conductor's own obligations in a status file, digest verified greens to the human, and clean up on merge.

0
installs
▌
Security Conductor · kirodotdev bundle
Use when a security conductor session is being seeded, or when inspecting/debugging one. Operating procedure for the kirocrew-security-conductor agent - run proactive vulnerability discovery on one target as a supervised fleet. Decompose the target into attack surfaces, dispatch one auditor per surface behind the rules of engagement, dispatch an independent verifier per finding whose job is rejecting false positives, adjudicate severity, hold the two human gates, run a retrospective that proposes lessons, and report upward.

0
installs
▌
Ops Mission Control · kirodotdev bundle
Investigate and triage operational signals — alarms, pages, monitors, and ops issues — using the Ops Mission Control incident board and knowledge ledger. Use when investigating an incident, triaging a firing alarm, checking what is broken, or recording a fix pattern.

0
installs
▌
Papyrus Make Fluent · kirodotdev
Polish the English of a LaTeX passage — fluency, grammar, and clarity — as tracked suggestions, without changing structure or meaning. Use when the author asks to make text fluent/readable, fix the English, proofread, or tighten wording. Includes a mandatory global-consistency (ripple) check.

0
installs
▌
Greeting · kirodotdev
Greeting patterns and onboarding tips

0
installs
▌
Babysit · kirodotdev bundle
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.

0
installs
▌
Theme Pack Authoring · kirodotdev
Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.

0
installs
▌
Goal Ledger Conductor · kirodotdev bundle
Deprecated alias of the goal-conductor skill, removed next release. The work-ledger conducting procedure - decompose a goal into items, bind each to a session, read reported status as data, verify claims with the acceptance evaluator - now lives in goal-conductor. Read that skill instead of this one.

0
installs
▌
IOS Simulator Preview · kirodotdev bundle
Show a live iOS Simulator in the dashboard's Browser side panel while building or testing an iOS app. Use when the user asks to preview an iOS/SwiftUI app, run an app in the simulator, "show me the app", test in the iOS simulator, or watch you drive an iOS app. macOS + Xcode only.

0
installs
▌
Papyrus Latex Comments · kirodotdev
Set up and use a non-destructive COMMENT layer in a LaTeX document — insert margin/inline notes (tagged by type) next to the author's text instead of rewriting it. Use when asked to comment on, review, or annotate a .tex file. For proposing actual replacement text the author can accept/reject, use papyrus-latex-suggestions.

0
installs
▌
Oncall Runbook · kirodotdev
On-call runbook and escalation procedures

0
installs
▌
Pod E2e · kirodotdev bundle
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Boots a Kiro Crew feature worktree's full stack as an ISOLATED throwaway pod and proves it boots, authenticates and renders (headless Playwright), without touching the live gateway. It does NOT run the worktree's test suite -- run the tests your change touches yourself and let CI own the full suite. Use when asked to e2e-test / smoke-test / verify a Kiro Crew worktree's feature hands-off, drive browser checks on a pod, or prove a new backend route + UI work together. NOT for testing the live instance, and NOT a general-purpose e2e or smoke-test skill.

0
installs
▌
Prepare Pr · kirodotdev bundle
Prepare PR

0
installs
▌
Frontend Design Workflow · kirodotdev
Workflow for frontend features, visual changes, and product design changes. Present mockup options before writing code, build against the project's design system, capture the right evidence type (screenshots vs video), and run a new-user usability review before finalizing. Use when building or changing UI, styling, layouts, animations, or any user-facing visual surface.

0
installs
▌
Papyrus Latex Suggestions · kirodotdev
Propose actual inline replacement text (old → new) as accept/reject suggestions — LaTeX "suggesting mode" / track changes — that render directly in the PDF. Use when the author wants concrete edit proposals they can see and accept or reject. For remarks ABOUT the text (notes, not replacements), use papyrus-latex-comments.

0
installs
▌
Writing Tests · kirodotdev
How to write a Kiro Crew backend test that has NO side effects and does not flake. Use when adding, editing, reviewing, or debugging a pytest test in the Kiro Crew source repo: which conftest is under your file, what leaks (temp dirs, the real data home, ~/.kiro, cron, threads, child processes), how to tell which of the six flake classes you have and where each one's fix is written, and the cross-platform traps on macOS/Linux/Windows and arm64. Also covers diagnosing a residue failure and keeping the parallel suite fast.

0
installs
▌
Papyrus Diagnose Compilation · kirodotdev
Diagnose and fix LaTeX compilation failures. Use when the document does not compile, pdflatex/bibtex/biber/tectonic errors out, the PDF is stale, or the author reports a build/compile error in the Papyrus editor.

0
installs
▌
Mochi Plan · kirodotdev
INTERNAL pet queue — generates the pet's 30-minute behavior schedule (moves, moods, notifications). NOT for user task or calendar planning.

0
installs
▌
Mochi Tips · kirodotdev
Feature tips catalog for new users. Plan skill loads this to pick a tip during the first week.

0
installs
▌
Visual Edit · kirodotdev
Interpret and act on batched visual edit requests produced by the Design Tweak app. Use when the user references a visual selection, a "design tweak" request, an edit request number, or asks you to apply pending visual edits.

0
installs
▌
Mochi Slack · kirodotdev
Slack awareness — unread mentions, channel digests, topic radar, thread summaries. Load when user asks about Slack.

0
installs
▌
Mochi Watch · kirodotdev
Check one or more watch items, compare with last known status, suggest actions, and update the watchlist.

0
installs
▌
Mochi Remind · kirodotdev
Handle due reminders — notify the user with natural language and mark them done.

0
installs
▌
Mochi Replan · kirodotdev
INTERNAL pet queue — partial adjustment of the pet's behavior schedule. NOT for user task or calendar planning.

0
installs

70 published skills