Source profileQuality 86/100Review permissions
kirodotdev/KiroCrew/skills/kirocrew-commands/SKILL.md
kirocrew-commands
Complete CLI reference for KiroCrew commands. Use for help, commands, setup, how to, what can you do, getting started, onboarding.
- Source repository stars
- 1,286
- Declared platforms
- 0
- Static risk flags
- 3
- Last source update
- 2026-08-06
- Source checked
- 2026-08-06
Decision brief
What it does—and where it fits
Complete CLI reference for KiroCrew commands. Use for help, commands, setup, how to, what can you do, getting started, onboarding.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
Source-detected install commandSource
npx skills add https://github.com/kirodotdev/KiroCrew --skill "skills/kirocrew-commands"Safe inspection promptEditorial
Inspect the Agent Skill "kirocrew-commands" from https://github.com/kirodotdev/KiroCrew/blob/5bcf51037a10a420d51a290b505245a3e6f0b1ee/skills/kirocrew-commands/SKILL.md at commit 5bcf51037a10a420d51a290b505245a3e6f0b1ee. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Setup & System
Review the “Setup & System” section in the pinned source before continuing.
Review and apply the “Setup & System” source section. - 02
Gateway (Server)
Review the “Gateway (Server)” section in the pinned source before continuing.
Review and apply the “Gateway (Server)” source section. - 03
Service Management
Review the “Service Management” section in the pinned source before continuing.
Review and apply the “Service Management” source section. - 04
Pods (Isolated Worktree Test Instances)
Ephemeral, full-stack KiroCrew gateways — one per feature worktree — that run on their own port + isolated KIROCREWHOME and never touch the live :5476 gateway or shared data. Linux systemd --user only. is a worktree name (resolved by directory basename or feat/ branch convention…
Ephemeral, full-stack KiroCrew gateways — one per feature worktree — that run on their own port + isolated KIROCREWHOME and never touch the live :5476 gateway or shared data. Linux systemd --user only. is a worktree nam…Platform: Linux only. On macOS/Windows every systemd-touching verb refuses with a one-line message pointing at ./dev-backend.sh — it does not crash, and pod install writes no unit file. pod url works anywhere (pure comp…Port derivation: base + (cksum(name) % 199) + 1 (base 7810 → 7811..8009). Override with PORT= in /.kiro/crew/pods/.env. - 05
Dashboard Access
Review the “Dashboard Access” section in the pinned source before continuing.
Review and apply the “Dashboard Access” source section.
Permission review
Static risk signals and limitations
Runs scripts
The documentation asks the agent to run terminal commands or scripts.
| `kirocrew pod exec <wt> -- <args>` | Run a kirocrew command against a pod, using the pod's own binary and data |Runs scripts
The documentation asks the agent to run terminal commands or scripts.
| `kirocrew cron preview SCRIPT` | Run a script cron locally with real MCP tools; notifications are printed, not delivered |Writes files
The documentation asks the agent to create, modify, or delete local files.
| `kirocrew artifact save --name "My Widget" --content-file widget.html` | Save new artifact |Writes files
The documentation asks the agent to create, modify, or delete local files.
| `kirocrew artifact update SLUG --content-file widget.html` | Update artifact content |Reads files
The documentation asks the agent to read local files, directories, or repositories.
| `kirocrew config set --file config.json` | Load full config from JSON file |Evidence record
Why each signal appears
EvidenceSourceComputedTestedEditorial
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 86/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 1,286 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- kirodotdev/KiroCrew
- Skill path
- skills/kirocrew-commands/SKILL.md
- Commit
- 5bcf51037a10a420d51a290b505245a3e6f0b1ee
- License
- Apache-2.0
- Collected
- 2026-08-06
- Default branch
- main
View the original SKILL.md
KiroCrew CLI Reference
Setup & System
| Command | Description |
|---|---|
kirocrew setup | Interactive wizard — install agent config and configure credentials |
kirocrew setup --agent-only | Only install kiro-cli agent config, skip credential prompts |
kirocrew setup --clean | Fresh install — don't merge from existing config |
kirocrew doctor | Verify KiroCrew setup (checks all dependencies) |
kirocrew update | Update KiroCrew to the latest version |
kirocrew --version | Print installed version |
Gateway (Server)
| Command | Description |
|---|---|
kirocrew gateway | Start dashboard + Slack gateway |
kirocrew gateway --slack-only | Slack only — skip dashboard web server |
kirocrew gateway --no-crons | Skip cron scheduler |
kirocrew gateway --port 9999 | Override dashboard port |
kirocrew gateway --port auto | OS-assigned ephemeral port |
kirocrew gateway --no-open | Don't auto-open dashboard URL in browser |
kirocrew gateway --approval reads | Auto-approve read-only tools |
kirocrew gateway --approval yolo | Auto-approve all tools (requires isolated KIROCREW_HOME) |
kirocrew gateway --approval interactive | Prompt for every tool (default) |
kirocrew gateway --seed FIXTURE | Seed $KIROCREW_HOME from fixture before starting (dev) |
kirocrew gateway --test-mode | Alias for --port auto --no-open --json-ready --approval reads |
kirocrew stop | Stop a running gateway |
kirocrew stop --port 9999 | Stop gateway on specific port |
kirocrew restart | Restart gateway (service-aware) |
kirocrew status | Show runtime stats (uptime, sessions, crons, lessons) |
Service Management
| Command | Description |
|---|---|
kirocrew service install | Install and start as system service (sudo on Linux) |
kirocrew service uninstall | Stop and remove system service |
kirocrew service status | Show service status (systemctl/launchctl) |
kirocrew logs | Show gateway logs (last 100 lines) |
kirocrew logs -f | Follow (tail) live log output |
kirocrew logs -n 50 | Show last N lines |
Pods (Isolated Worktree Test Instances)
Ephemeral, full-stack KiroCrew gateways — one per feature worktree — that run on
their own port + isolated KIROCREW_HOME and never touch the live :5476
gateway or shared data. Linux systemd --user only. <wt> is a worktree name
(resolved by directory basename or feat/<name> branch convention).
| Command | Description |
|---|---|
kirocrew pod install | Lay down the systemd --user template unit (once per machine) |
kirocrew pod provision <wt> | Build the worktree's venv + SPA dist (the on-ramp) |
kirocrew pod up <wt> | Bring up an isolated pod (auto-builds venv; fails if dist missing) |
kirocrew pod up <wt> --provision | Provision (venv + dist build) then bring up |
kirocrew pod up <wt> --json | Bring up and print {base_url, token, port} as JSON |
kirocrew pod ls | List running pods |
kirocrew pod status <wt> | Up/down + health for one pod |
kirocrew pod token <wt> | (Re)mint a dashboard token for a running pod |
kirocrew pod url <wt> | Print the pod's base URL |
kirocrew pod logs <wt> -n N | Tail the pod's journal |
kirocrew pod down <wt> | Evict the pod and delete its isolated HOME |
kirocrew pod exec <wt> -- <args> | Run a kirocrew command against a pod, using the pod's own binary and data |
Platform: Linux only. On macOS/Windows every systemd-touching verb refuses
with a one-line message pointing at ./dev-backend.sh — it does not crash, and
pod install writes no unit file. pod url works anywhere (pure computation).
Port derivation: base + (cksum(name) % 199) + 1 (base 7810 → 7811..8009).
Override with PORT= in ~/.kiro/crew/pods/<name>.env.
See src/kiro_crew/pod/README.md for the full reference.
Dashboard Access
| Command | Description |
|---|---|
kirocrew token | Print a dashboard URL with auth token (TTL: 20h) |
kirocrew token --ttl 1h | Token with custom TTL (e.g. 1h, 30m) |
kirocrew logout | Revoke all active dashboard sessions |
kirocrew manifest | Generate Slack app manifest with your alias |
kirocrew manifest --url | Print one-click Slack app creation URL |
Chat
| Command | Description |
|---|---|
kirocrew chat | Interactive chat (REPL mode) |
kirocrew chat -m "message" | Single message (non-interactive) |
kirocrew chat --model claude-opus | Use specific model |
Browsing (Playwright MCP)
Browsing uses Playwright MCP tools, not kirocrew CLI. The kirocrew browse subcommands manage auth only.
| Command | Description |
|---|---|
kirocrew browse setup | Install Playwright MCP + browsers |
kirocrew browse auth health | Check browser auth / cookie status (prints JSON) |
kirocrew browse auth refresh | Write Playwright storage state from an exported cookie jar |
Browsing workflow: Load the browser-auth skill (or follow it directly):
kirocrew browse auth health— check auth; if unhealthy or no cookies, tell the user to export a fresh cookie jar from a browser where they're logged inkirocrew browse auth refresh— write Playwright storage state from the exported cookie jar (pre-loads auth into the browser context)- Use Playwright MCP tools:
browser_navigate,browser_snapshot,browser_click,browser_fill_form,browser_take_screenshot,browser_evaluate - On a 401 / login redirect, the session cookies expired — the user re-exports the cookie jar and you re-run
kirocrew browse auth refresh
Note: Playwright auto-installs during kirocrew setup.
Autonomous Task Runner
| Command | Description |
|---|---|
kirocrew run TASK.md | Run a task spec file (auto-resumes from checkpoint) |
kirocrew run TASK.md --fresh | Start from scratch, ignore checkpoint |
kirocrew run TASK.md --no-test | Skip build/test verification after each step |
kirocrew run TASK.md --timeout 3600 | Set global timeout in seconds |
kirocrew run TASK.md --name "My Task" | Override human-readable task name |
Subagents
| Command | Description |
|---|---|
kirocrew spawn run "task" | Spawn a background subagent (wait for result) |
kirocrew spawn run --async "task" | Fire-and-forget subagent |
kirocrew spawn list | List active subagents |
Cron Jobs
| Command | Description |
|---|---|
kirocrew cron list | List all cron jobs |
kirocrew cron add NAME MESSAGE --every 3600 | Add job with interval (seconds) |
kirocrew cron add NAME MESSAGE --cron "0 9 * * MON-FRI" | Add job with cron expression |
kirocrew cron add NAME MESSAGE --agent myagent | Add job for specific agent |
kirocrew cron add NAME MESSAGE --approval-mode auto | Add job with auto tool approval |
kirocrew cron add NAME MESSAGE --channel C123456 | Post results to Slack channel |
kirocrew cron update JOB_ID --message "new msg" | Update job message |
kirocrew cron update JOB_ID --agent myagent | Update job agent |
kirocrew cron update JOB_ID --approval-mode auto | Set auto-approval |
kirocrew cron update JOB_ID --approval-mode default | Reset approval to default |
kirocrew cron remove JOB_ID | Remove a cron job |
kirocrew cron pause JOB_ID | Pause a cron job |
kirocrew cron resume JOB_ID | Resume a paused job |
kirocrew cron trigger JOB_ID | Trigger a job immediately |
kirocrew cron preview SCRIPT | Run a script cron locally with real MCP tools; notifications are printed, not delivered |
kirocrew cron preview SCRIPT -m "msg" -e K=V | Preview with an input message / extra env vars |
Learning & Memory
| Command | Description |
|---|---|
kirocrew learn list | List all saved lessons |
kirocrew learn add "rule text" | Save a lesson (category: knowledge) |
kirocrew learn add "rule text" --category tool | Save with category (tool/preference/knowledge) |
kirocrew learn add "rule text" --negative "avoid X" | Save with negative example |
kirocrew learn remove "query" | Remove lessons matching substring |
kirocrew memory list | Show semantic memory entries |
kirocrew memory search "query" | Search episodic memories |
kirocrew memory stats | Show memory statistics |
kirocrew memory audit | Scan memory for suspicious content |
kirocrew memory export | Export all memory to JSON (stdout) |
kirocrew memory export -o file.json | Export to file |
kirocrew memory import file.json | Import memory from JSON |
kirocrew memory migrate | Migrate legacy markdown memory to vector store |
kirocrew knowledge dedup | Preview cross-source duplicate knowledge documents (dry-run) |
kirocrew knowledge dedup --apply | Actually collapse the duplicates |
kirocrew consolidate | List sessions with unconsolidated messages |
kirocrew consolidate SESSION_KEY | Force consolidate a session (triggers auto-skill extraction) |
kirocrew consolidate --all | Consolidate all pending sessions |
Artifacts
LLM-generated UI components (widgets, HTML, markdown, SVG, JSON, text).
| Command | Description |
|---|---|
kirocrew artifact list | List all artifacts |
kirocrew artifact list --tag ops --kind widget | Filter by tag and kind |
kirocrew artifact list -q "CR" | Substring filter on name |
kirocrew artifact show SLUG | Print artifact content |
kirocrew artifact show SLUG --version 2 | Show specific version |
kirocrew artifact show SLUG --meta | Show metadata as JSON |
kirocrew artifact save --name "My Widget" --content-file widget.html | Save new artifact |
kirocrew artifact save --name "X" --content "..." --tags ops,cr | Save with inline content |
kirocrew artifact update SLUG --content-file widget.html | Update artifact content |
kirocrew artifact update SLUG --name "New Name" --tags ops | Rename/retag |
kirocrew artifact versions SLUG | List version numbers |
kirocrew artifact delete SLUG | Delete artifact and all versions |
Agents & Workspaces
| Command | Description |
|---|---|
kirocrew agent list | List KiroCrew agents |
kirocrew agent create --name NAME | Create a new agent |
kirocrew agent create --name NAME --kiro-agent kirocrew --workspace default | Full options |
kirocrew agent update NAME --kiro-agent new-agent | Update agent settings |
kirocrew agent delete NAME | Delete an agent |
kirocrew workspace list | List workspaces |
kirocrew workspace create --name NAME --dir DIRNAME | Create workspace (--dir is a name under the data home, not an absolute path) |
kirocrew workspace create --name NAME --copy-from existing | Copy from existing |
kirocrew workspace update NAME --dir DIRNAME | Update workspace dir (same containment rule) |
kirocrew workspace delete NAME | Delete workspace |
On the CLI, --dir must resolve to a strict descendant of
$KIROCREW_HOME (default ~/.kiro/crew): anything landing outside — /tmp/x,
../x, ~/x — is refused with a SEL denied audit event, and so is the data
home root itself (in any spelling: absolute, ~/.kiro/crew, ., or empty),
since a workspace there would put agent-writable memory on top of config.json
and .env. The test is containment, not "is it absolute": an absolute path
landing under the home is accepted, since it resolves where the relative form
would. Pass workspace-myproject, not /path/to/dir.
Note the surface difference: the dashboard POST /api/workspaces DOES accept
an absolute dir (screened by is_sensitive_path, so ~/.ssh / ~/.aws /
keystone paths are still refused). The CLI is the stricter of the two.
Apps
| Command | Description |
|---|---|
kirocrew app list | List installed apps |
kirocrew app install /path/to/app-dir | Install app from local directory (needs app.json) |
kirocrew app enable NAME | Enable an installed app |
kirocrew app disable NAME | Disable an installed app |
kirocrew app uninstall NAME | Uninstall an app and preserve its data directory |
kirocrew app uninstall NAME --purge-data | Uninstall and explicitly delete the app data directory |
kirocrew app info NAME | Show app details |
kirocrew app init NAME | Scaffold a new app (kebab-case name) |
kirocrew app init NAME --backend --ui --cron | Scaffold with backend, UI, and sample cron |
kirocrew app dev NAME | Toggle an app into dev mode (no-store UI serving + live reload on file change) |
kirocrew app dev NAME --off | Leave dev mode |
Configuration
| Command | Description |
|---|---|
kirocrew config get | Show all config |
kirocrew config get agent.provider | Get specific value (dot-separated key) |
kirocrew config set dashboard.url http://localhost:5476 | Set a config value (port is the KIROCREW_PORT env var, not a config key) |
kirocrew config set --file config.json | Load full config from JSON file |
kirocrew config edit | Open config in $EDITOR |
Profiling (debug-only)
Off unless KIROCREW_DEBUG=1 is set; the CLI is the only entry point. Emits folded
stacks (open in speedscope / flamegraph.pl). See docs/architecture/design-notes/profiling.md.
| Command | Description |
|---|---|
KIROCREW_DEBUG=1 kirocrew perf sample --call mod:fn | Profile that callable in-process (no extra dependency) |
KIROCREW_DEBUG=1 kirocrew perf sample | Attach to the running gateway (needs pip install "kirocrew[perf]") |
KIROCREW_DEBUG=1 kirocrew perf sample --pid 1234 --seconds 30 | Attach to a specific PID for N seconds (1-300) |
... --interval 0.002 | Seconds between samples (0.001-1.0, default 0.005) |
... --output /tmp/p.folded | Where to write the profile (default ./kirocrew-profile.folded) |
KIROCREW_DEBUG=1 kirocrew desktop metrics | Per-process CPU/memory of the Electron app (--json, --top N, --path) |
On macOS the attach path additionally needs elevated privileges (the OS denies
task_for_pid), so it may require sudo; --call needs neither py-spy nor sudo.
desktop metrics reads a recording rather than querying the app: getAppMetrics()
is Electron-main-only, so the app samples itself into an artifact when started
with KIROCREW_DEBUG set. Setting the variable only for the CLI does not make an
already-running app record -- restart it.
Security & Eval
| Command | Description |
|---|---|
kirocrew security audit | Scan conversation history for suspicious tool usage |
kirocrew security deny-list | Show active deny patterns |
kirocrew security events | Show recent security event log entries (last 20) |
kirocrew security events -n 50 | Show N entries |
kirocrew security verify | Verify security event log HMAC integrity |
kirocrew eval | Run smoke test evaluation (~30s) |
kirocrew eval memory_recall_basic | Run specific scenario by name |
kirocrew eval --all | Run all scenarios (slow) |
kirocrew eval --judge | Enable LLM judge scoring |
Governance Policy (read-only)
Inspects the two-level security model (effective = POLICY ∩ PROFILE,
tightest-wins). All four verbs are read-only — the enterprise ceiling is never
edited through the CLI (its files are keystone-fenced so the agent cannot read or
write them).
| Command | Description |
|---|---|
kirocrew policy show | Show the effective enterprise security policy |
kirocrew policy validate | Load-check the policy + all profiles |
kirocrew policy explain SCOPE ITEM | Explain one tool/scope decision for a surface |
kirocrew policy explain SCOPE ITEM --session-key K --agent A --app APP | Scope the explanation to a surface |
kirocrew policy profile NAME | Show a profile by name |
Cloud (Bring-Your-Own AWS)
Runs KiroCrew on an EC2 instance in your own AWS account; credentials are
resolved by the aws CLI and never stored by KiroCrew. All verbs accept
--profile / --region; the single-instance verbs also accept --tag
(defaults to the last launched instance).
| Command | Description |
|---|---|
kirocrew cloud doctor | Check cloud prerequisites + AWS reachability |
kirocrew cloud launch | Provision + configure an instance (interactive) |
kirocrew cloud launch --size TIER -y | Non-interactive launch at a size tier |
kirocrew cloud launch --new | Create a separate new instance instead of resuming the saved one |
kirocrew cloud launch --keep-on-failure | On bootstrap failure keep the instance for inspection |
kirocrew cloud list | List your KiroCrew cloud instances |
kirocrew cloud status | Show one instance's state |
kirocrew cloud connect | Open the dashboard over an SSM tunnel |
kirocrew cloud tunnel | Open the dashboard SSM tunnel (standalone alias of connect) |
kirocrew cloud connect --local-port N --no-browser | Forward to a specific local port, no browser |
kirocrew cloud login | Sign kiro-cli in on the instance (fixes "not logged in" chat errors) |
kirocrew cloud stop | Stop the instance (pause billing) |
kirocrew cloud start | Start a stopped instance |
kirocrew cloud destroy | Remove the instance and ALL its AWS resources |
kirocrew cloud destroy --dry-run | Show the delete command without running it |
kirocrew cloud iam-policy | Print the least-privilege IAM policy to apply |
kirocrew cloud iam-boundary | Pre-create the immutable permissions boundary (admin, one-time) |
Computer Use (Desktop Automation)
Default-OFF behind a keystone enable (~/.kiro/crew/computer_use.json, not
config.json). macOS only. These are human debug/diagnostic twins of the
computer_* MCP tools — the agent uses the MCP tools, not these.
| Command | Description |
|---|---|
kirocrew computer doctor | Report platform support, keystone enable state, and the advisory Accessibility / Screen Recording probe |
kirocrew computer doctor --json | Same as JSON |
kirocrew computer apps | List on-screen applications the accessibility layer can address |
kirocrew computer call TOOL k=v … | Run ONE computer-use tool through the same gated chokepoint the agent uses |
kirocrew computer call --calls '[…]' | Run a JSON array of calls in a SINGLE process, so element_index values stay resolvable |
Snapshot & Restore
| Command | Description |
|---|---|
kirocrew snapshot | Create a portable backup of KiroCrew state |
kirocrew snapshot /path/to/dir | Snapshot to specific output directory |
kirocrew snapshot --keep 7 | Keep N most recent snapshots (default: 7) |
kirocrew snapshot --list | List existing snapshots |
kirocrew restore | Restore from most recent snapshot |
kirocrew restore /path/to/snap.tar.gz | Restore from specific snapshot |
kirocrew restore --mode replace | Replace mode (default) |
kirocrew restore --mode merge | Merge mode |
kirocrew restore --dry-run | Preview without applying |
kirocrew restore --components memory,crons | Restore specific components only |
kirocrew restore --list-components | List restorable components |
kirocrew restore --force | Restore even if gateway is running |
Slack Commands
All Allowed Users
| Command | Description |
|---|---|
!dashboard | Get a presigned dashboard link (DM'd to you). Link expires in 5 min; session lasts 1h |
!dashboard 2h | Dashboard link with custom duration (accepts <N>h or <N>m, max 6h) |
/kirocrew dashboard | Same via slash command |
/kirocrew help | List available slash sub-commands |
!stop | Force-halt the current agent turn (bypasses semaphore, cancels active task) |
status | Show runtime stats |
ping | Auto-reply pong |
cron list | List cron jobs |
run <path> | Run an autonomous task from a spec file |
Owner-Only Slash Commands
| Command | Description |
|---|---|
/kirocrew yolo | Toggle YOLO mode (auto-approve all tool calls) |
/kirocrew agent | Show agent selector dropdown |
/kirocrew agent <name> | Switch to named agent |
/kirocrew voice | Open TTS voice settings modal |
/kirocrew config | Open config modal |
/kirocrew users | Open allowed users management modal |
/kirocrew channels | Open tracked channels modal |
/kirocrew sessions | List recent sessions with resume/end buttons |
Environment Variables
| Variable | Purpose | Default |
|---|---|---|
KIROCREW_HOME | Override config/data directory | ~/.kiro/crew |
KIROCREW_PORT | Override dashboard port | 5476 |
KIROCREW_PROJECT_DIR | Override agent config/skills directory | Auto-detected |
KIROCREW_POD_REPO | Repo to resolve worktree names from | invoking cwd |
KIROCREW_POD_ROOT | Isolated pod HOMEs (nuked on stop) | ~/.kirocrew-pods |
KIROCREW_POD_BASE_PORT | Port derivation base | 7810 |
KIROCREW_POD_LIVE_PORT | Port a pod must never bind | 5476 |
Alternatives
Compare before choosing
Computed 10043,183
coreyhaines31/marketingskills
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
Computed 10023,881
alirezarezvani/claude-skills
app-store-optimization
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist
Computed 1004,969
dotnet/skills
migrate-vstest-to-mtp
Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", set OutputType=Exe only for test projects in Directory.Build.props, or mentions EnableMSTestRunner, EnableNUnitRunner, or UseMicrosoftTestingPlatformRunner. USE FOR: MTP behavioral differences vs VSTest (exit code 8, zero tests discovered, --ignore-exit-code, TESTINGPLATFORM_EXITCODE_IGNORE); centralizing
Computed 100148
JasonColapietro/suede-creator-skills
suede-ab-testing
Suede-owned experimentation discipline for hypotheses, sample sizing, test duration, significance, and repeatable experiment programs. Use when comparing variants, deciding whether a result is reliable, or building an experiment backlog and cadence. NOT FOR: analytics instrumentation (use suede-analytics), post-click conversion diagnosis (use suede-site-alchemy), or writing the variant copy itself (use suede-copy).