kirodotdev
@kirodotdev Organization
Public Skills
mochi-watch
by kirodotdev
"Check one or more watch items, compare with last known status, suggest actions, and update the watchlist."
self-rca
by kirodotdev
When you make a mistake or the user corrects you, stop and run a blameless root-cause analysis of your OWN failure — concrete failure statement, Five Whys covering cause AND why you didn't self-catch it AND why no guardrail stopped it, and a durable lesson — instead of just apologizing and retrying.
image-authoring
by 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.
spec-workflow
by 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."
five-whys
by kirodotdev
Guided dive-deep research mode. 5 Whys is the default engine — one focused question at a time along What-it-is -> Example -> Why-not-alternatives -> Benefits -> Costs, user-steered branching, every step appended to an event log the tree and report fold from. Use for deep research asks.
rubber-duck
by 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".
crystallize
by 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.
mochi-slack
by kirodotdev
"Slack awareness — unread mentions, channel digests, topic radar, thread summaries. Load when user asks about Slack."
visual-edit
by 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.
self-update
by kirodotdev
Check for and apply Kiro Crew updates. Use when user says "update yourself", "check for updates", "are you up to date", "keep yourself updated", or "auto-update".
mochi-tips
by kirodotdev
"Feature tips catalog for new users. Plan skill loads this to pick a tip during the first week."
debug-gateway
by kirodotdev
Load this before concluding a change did not land, and to read what the kirocrew-debug tools actually answered - which question to ask first, the fields that mean the opposite of how they look, and what a 400 / 403 / 404 / 501 from these tools means.
mochi-plan
by kirodotdev
"INTERNAL pet queue — generates the pet's upcoming-window behavior schedule (moves, moods, notifications). NOT for user task or calendar planning."
design-critique
by kirodotdev
"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'."
session-summaries
by 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.
mochi-remind
by kirodotdev
"Handle due reminders — notify the user with natural language and mark them done."
personal-shopper
by kirodotdev
Personal advisor for a problem that might be solved by buying something — diagnoses the real need through conversation, then recommends products from stores the user names only when a purchase is the right answer. Uses preferences stated in the conversation or supplied by Kiro Crew memory, but cannot read or write the app's Preferences tab. 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".
metric-design
by kirodotdev
Phase 1 of the auto-improvement loop — how the app designs and calibrates the ruler (the trustworthy metric) BEFORE any optimization; calibration itself is backend code, read its result with get_ruler. Covers 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.
goal-loop
by kirodotdev
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.
Greeting Skill
by kirodotdev
Greeting patterns and onboarding tips
grill
by kirodotdev
Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks memory for already-answered questions, and saves only durable decisions the user wants remembered. Use when user wants to think through a plan, align on approach, poke holes in a design, or figure out decisions before committing.
goal-ledger-conductor
by kirodotdev
Deprecated alias of goal-conductor, removed next release. The work-ledger conducting procedure now lives in goal-conductor; read that skill instead.
release-notes
by kirodotdev
Draft a release note section from a commit range, grouped by what the reader gets.
auto/flaky-triage
by kirodotdev
Classify a red test as a real regression, a flake, or an environment problem before patching.