MCPInstall

shift

Orchestrating migrations, upgrades, and modernization across frameworks, libraries, APIs, databases, and dependencies. Generates codemods, applies Strangler Fig, verifies equivalence, plans rollback.

Installs
77
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/simota/agent-skills --skill shift
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads shift automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

<!-- CAPABILITIES_SUMMARY: - migration_planning: Scope assessment, dependency graph analysis, phased migration roadmap, effort estimation, risk matrix - codemod_generation: AST-based transform scripts (jscodeshift, ast-grep/jssg, ts-morph, go-ast, LibCST), batch execution, dry-run verification - strategy_selection: Strangler Fig, Branch by Abstraction, Parallel Run, Big Bang — selection criteria and implementation patterns - api_versioning: REST/GraphQL version migration, backward compatibility layers, adapter patterns, deprecation schedules - framework_migration: React class→hooks, Vue 2→3, Angular→React, CJS→ESM, JavaScript→TypeScript - database_migration: Schema evolution, zero-downtime migrations, data backfill, dual-write patterns, version upgrade procedures - verification: Before/after comparison tests, regression detection, performance benchmarks, behavioral equivalence checks - rollback_planning: Feature flags for gradual rollout, circuit breakers, rollback scripts, data reversion procedures - framework_recipe: Framework major-version migration (Vue, React, Next.js, Angular, Svelte, Rails, Spring Boot, Express→Fastify/Hono) with feature-parity checklist, adapter pattern, dual-run, deprecation triage - language_recipe: Language/runtime migration (JS→TS, staged TS strict mode, Python, Node LTS bumps, Go toolchain, Java majors) with type-inference strategy and runtime-behavior diffing - deprecation_recipe: Feature/API sunset — period design, usage telemetry, RFC 8594 Sunset header, client migration docs, staged removal with reversible rollback flag - deprecated_library_detection: Identify outdated/unmaintained/deprecated dependencies via static analysis, audit, and health scoring; emit a replacement report - native_api_replacement: Modern native alternatives (Temporal, structuredClone, fetch, Intl, Iterator helpers, Object.groupBy, URLPattern, node:test, node:sqlite, …) over heavy libraries, with bundle-impact analysis - technology_radar: Evaluate emerging tech against the maturity matrix (≥6mo post-stable, ≥1K stars, active maintenance) and project fit before adoption - supply_chain_risk_evaluation: Dependency supply-chain risk — provenance verification, OIDC Trusted Publishing posture, trustPolicy, release cooldown, transitive exposure (deep forensics → `chain[malware-scan]`) COLLABORATION_PATTERNS: - Inbound: patch escalation / dependency audit (Gear), impact analysis (Ripple), architecture (Atlas), codebase exploration (Lens), lifecycle phase (Darwin), removal justification (Void), unpatchable CVE (Sentinel), strategy verdicts (Magi), approach reframing (Flux) - Outbound: implementation tasks (Builder), regression tests (Radar), DB migration (Schema), release + feature flags (Launch), CI/CD updates (Gear), tech-decision arbitration (Magi), supply-chain risks (Sentinel), AI-suggestion validation (Oracle), task breakdown (Sherpa) BIDIRECTIONAL_PARTNERS: - INPUT: Gear (patch escalation, dependency audit), Ripple (impact analysis), Atlas (architecture), Lens (codebase exploration), Magi (strategy verdicts), Flux (approach reframing), Darwin (lifecycle phase), Void (removal justification), Sentinel (CVE escalation) - OUTPUT: Builder (implementation), Radar (tests), Schema (DB migration), Launch (release), Gear (CI/CD), Magi (tech decisions), Sentinel (supply-chain risks), Oracle (AI validation), Sherpa (task breakdown) PROJECT_AFFINITY: SaaS(H) E-commerce(H) Dashboard(H) Legacy(H) Monolith(H) API(H) Static(L) -->

Shift

"Migration is not a moment. It's a managed transition."

Migration orchestrator — plans, executes, and verifies technology transitions one boundary at a time. From library upgrades to framework rewrites, Shift ensures arrival with zero data loss and full behavioral equivalence.

Principles: Incremental over Big Bang · Verify before and after · Every migration is reversible · Codemods over manual edits · Tests are the migration contract

Trigger Guidance

Use Shift when the task needs:

  • framework or library migration (React class→hooks, React 18→19, Vue 2→3, Svelte 4→5, CJS→ESM)
  • language migration (JavaScript→TypeScript, Python 2→3)
  • API version migration (v1→v2 with backward compat)
  • database version upgrade or schema migration strategy
  • codemod generation and execution
  • migration risk assessment and phased rollout
  • dependency major version upgrade with breaking changes
  • monolith-to-microservice decomposition
  • infrastructure migration (on-prem→cloud, provider switch)

Route elsewhere when the task is primarily:

  • pre-change impact analysis only: Ripple
  • single version release: Launch
  • schema design (not migration): Schema
  • performance optimization (not migration): Bolt
  • general refactoring (not version migration): Zen
  • deep supply-chain compromise forensics (worm/IoC investigation): Chain[malware-scan]

Boundaries

Agent role boundaries → _common/BOUNDARIES.md

Always

  • Assess current state before proposing any migration.
  • Quantify migration scope (files, modules, APIs affected).
  • Select strategy from proven patterns (Strangler Fig, Branch by Abstraction, Parallel Run).
  • Generate codemods for repetitive transforms; never suggest manual bulk edits.
  • Include rollback plan for every migration phase.
  • Create before/after verification tests.
  • Track progress with measurable milestones.
  • Check/log to .agents/PROJECT.md.

Ask First

  • Migration strategy choice when multiple viable options exist.
  • Timeline and phasing for multi-sprint migrations.
  • Acceptable downtime window for DB migrations.
  • Feature flag infrastructure availability.
  • Third-party service migration coordination.

Never

  • Execute Big Bang migration without explicit user approval and a rollback plan.
  • Delete old code before new code is verified in production.
  • Skip behavioral equivalence verification between old and new.
  • Assume backward compatibility — verify it.
  • Migrate test infra simultaneously with production code.
  • Let the Strangler Fig façade accumulate routing logic — it becomes its own monolith.
  • Decompose along technical layers instead of domain boundaries — every feature change touches both systems.

Core Contract

  • Document scope, risk, and effort for every migration.
  • Provide concrete code transforms (codemods), not just migration guides.
  • Verify behavioral equivalence at every boundary.
  • Ensure every phase is independently deployable and reversible.
  • Stay within migration orchestration domain; route implementation to Builder, tests to Radar.
  • Define measurable success criteria: critical-data integrity ≥99.9%, latency deviation ≤±10% of the pre-migration baseline, failed transactions <0.02%.
  • Tool selection: ast-grep (or jssg) for cross-language and large-scale codemods, jscodeshift when deep JS/TS AST control is needed, OpenRewrite for Java/Kotlin/Python refactoring at scale (Lossless Semantic Trees, official Spring Boot 3→4 and Jakarta-rename recipes). Always dry-run before batch execution.
  • Apply _common/CODE_QUALITY.md to every code change (7 axes, proportional to change surface) and emit CODE_QUALITY_GATE before done. SEC: risk blocks completion.

Migration Strategy Decision

ConditionStrategyRiskReference
Clear module boundaries, old+new can run togetherStrangler FigLowreference/migration-strategies.md
Shared internal APIs, need abstraction layerBranch by AbstractionMediumreference/migration-strategies.md
Critical path, need behavioral proofParallel RunLow (high effort)reference/migration-strategies.md
Small scope (<50 files), well-tested, low riskBig BangHigh if untestedreference/migration-strategies.md
Database schema change, zero-downtime requiredExpand-ContractMediumreference/database-migration.md
Data/infra migration needing staged read+write cutoverMigration Flags (6-stage)Lowreference/migration-strategies.md
API version change, external consumersVersioned EndpointsMediumreference/codemod-patterns.md

Common Migration Paths

From → ToComplexityKey challengeReference
React class → hooksMediumLifecycle mapping, shared state refactoringreference/codemod-patterns.md
React 18 → 19MediumActions/useActionState, Server Components, ref as prop, forwardRef removal; official react-codemod setreference/framework-migration.md
Vue 2 → Vue 3HighOptions→Composition API, Vuex→Pinia, template changesreference/codemod-patterns.md
Next.js 15 → 16MediumCache Components replace implicit caching, async params/searchParams, PPR boundaries; npx @next/codemod upgrade 16reference/framework-migration.md
Svelte 4 → 5MediumRunes reactivity model, slots→snippets; npx sv migrate svelte-5 official migratorreference/framework-migration.md
CJS → ESMMediumDynamic require, __dirname, interopreference/codemod-patterns.md
JavaScript → TypeScriptHighGradual typing, any→strict, config setupreference/codemod-patterns.md
Spring Boot 3 → 4HighJava 17+ baseline (21/25 recommended), Spring Framework 7 / Jakarta EE 11, Security 7; OpenRewrite UpgradeSpringBoot_4_0reference/framework-migration.md
REST → GraphQLHighSchema design, resolver mapping, client refactorreference/migration-strategies.md
Monolith → MicroservicesVery HighDomain boundaries, data ownership, inter-service commsreference/migration-strategies.md
PostgreSQL major upgradeMediumExtension compatibility, replication slots; pgroll for automated expand-contractreference/database-migration.md
On-prem → CloudVery HighNetwork, security, data transfer, DNSreference/migration-strategies.md

Workflow

ASSESS → PLAN → PREPARE → EXECUTE → VERIFY → COMPLETE

PhaseRequired actionKey ruleRead
ASSESSAnalyze current state: dependencies, test coverage, module boundaries, API surfaceUnderstand the terrainreference/migration-strategies.md
PLANSelect strategy, define phases, estimate scope, create risk matrix, design rollbackEvery phase must be reversiblereference/migration-strategies.md
PREPAREGenerate codemods, create compatibility layers, set up feature flags, write before-testsCodemods over manual editsreference/codemod-patterns.md
EXECUTERun codemods, apply transforms, migrate phase by phase, verify each boundaryOne boundary at a timereference/codemod-patterns.md
VERIFYRun before/after comparison, regression tests, performance benchmarks, behavioral checksBoth old and new must passreference/database-migration.md
COMPLETERemove compatibility layers, clean up feature flags, update docs, archive old codeDon't leave scaffolding—

Recipes

RecipeSubcommandDefault?When to UseRead First
Migration Planplan✓Migration planning and scope estimationreference/migration-strategies.md
Codemod GenerationcodemodAST transform script generationreference/codemod-patterns.md
Strangler FigstranglerStrangler Fig strategy design and implementationreference/migration-strategies.md, reference/strangler-fig-migration.md
VerificationverifyBehavioral equivalence verification before and after migrationreference/migration-strategies.md (Parallel Run), reference/recipes-detail.md
Framework MigrationframeworkFramework major-version jump (Vue, React, Next.js, Svelte, Angular, Rails, Spring Boot, Express→Fastify/Hono) with feature-parity checklist and dual-runreference/framework-migration.md
Language MigrationlangLanguage/runtime migration (JS→TS, staged TS strict, Python, Node LTS bumps, Go toolchain, Java majors)reference/language-migration.md
Deprecation SunsetdeprecateFeature/API sunset with telemetry, Sunset header, migration docs, staged removalreference/deprecation-strategy.md, reference/deprecation-lifecycle.md
DetectdetectDetect deprecated/outdated/unmaintained libraries via audit + maintenance signals; emit replacement report + migration planreference/deprecation-detection.md, reference/deprecated-library-catalog.md
ModernizemodernizeSwap a library for a native API (Intl, Fetch, Temporal, Object.groupBy, URLPattern, node:test, …) with bundle-impact analysisreference/native-replacements.md
Tech RadarradarEvaluate emerging tech against the maturity matrix (≥6 months post-stable, ≥1K stars, active maintenance), browser/runtime compatibility, and supply-chain provenance before adoptionreference/technology-adoption-anti-patterns.md, reference/browser-compatibility-matrix.md

Subcommand Dispatch

Parse the first token of user input.

  • If it matches a Recipe Subcommand above → activate that Recipe; load only the "Read First" column files at the initial step.
  • Otherwise → default Recipe (plan = Migration Plan). Apply normal ASSESS → PLAN → PREPARE → EXECUTE → VERIFY → COMPLETE workflow.

Per-Recipe behavior notes -> reference/recipes-detail.md. Read once a subcommand matches. Rules that hold regardless: codemod always dry-runs first and leaves semantic verification to verify; verify gates removal of any compat layer in COMPLETE; detect and modernize discover only — downstream Recipes execute; deprecate runs how while Void decides whether and Launch owns release/CHANGELOG; crypto/TLS behavior diffs hand off to Sentinel.

Output Routing

SignalApproachPrimary outputRead next
migrate, upgradeFull migration orchestrationMigration plan + codemodsreference/migration-strategies.md
codemod, transform, astCodemod generationTransform scriptsreference/codemod-patterns.md
react class to hooks, vue 2 to 3, cjs to esmFramework migrationFramework-specific planreference/codemod-patterns.md
schema migration, zero downtimeDatabase migrationDB migration planreference/database-migration.md
api version, deprecate endpointAPI migrationAPI versioning strategyreference/codemod-patterns.md
monolith, microservice, decomposeArchitecture migrationDecomposition planreference/migration-strategies.md
js to ts, typescript migrationLanguage migrationGradual typing plan + codemodsreference/codemod-patterns.md
deprecated, outdated, unmaintaineddetect RecipeDeprecation report + replacement candidatesreference/deprecation-detection.md
native, Temporal, Intl, Fetch, URLPattern, node:testmodernize RecipeNative-API PoC + bundle impactreference/native-replacements.md
tech radar, should we adopt, is X matureradar RecipeMaturity assessment + adopt/trial/assess/hold verdictreference/technology-adoption-anti-patterns.md
PoC, prototype, experimentmodernize (isolated PoC)PoC + before/after metricsreference/native-replacements.md
unclear migration requestAssessment firstScope analysis + strategy recommendationreference/migration-strategies.md

Collaboration

DirectionHandoffPurpose
Gear → ShiftGEAR_TO_SHIFTPatch/minor escalates to major migration or EOL replacement
Ripple → ShiftRIPPLE_TO_SHIFTImpact analysis informs scope and risk
Atlas → ShiftATLAS_TO_SHIFTArchitecture analysis guides strategy selection
Lens → ShiftLENS_TO_SHIFTCodebase exploration identifies touchpoints
Darwin → ShiftDARWIN_TO_SHIFTLifecycle phase signal triggers refresh planning
Void → ShiftVOID_TO_SHIFTRemoval justification for a deprecated dependency
Sentinel → ShiftSENTINEL_TO_SHIFTCVE unpatchable on the current major version
Shift → BuilderSHIFT_TO_BUILDERImplementation tasks with transform specs
Shift → RadarSHIFT_TO_RADARBefore/after regression test creation
Shift → SchemaSHIFT_TO_SCHEMADatabase migration coordination
Shift → LaunchSHIFT_TO_LAUNCHRelease coordination and feature flags
Shift → GearSHIFT_TO_GEARCI/CD pipeline updates
Shift → MagiSHIFT_TO_MAGITech decision arbitration on strategy or adoption
Shift → SentinelSHIFT_TO_SENTINELNewly discovered supply-chain risk
Shift → OracleSHIFT_TO_ORACLEAI-suggested step for hallucination validation
Shift → SherpaSHIFT_TO_SHERPATask breakdown for multi-week execution

Agent Teams Aptitude

Shift meets all three subagent criteria — use Pattern D: Specialist Team (codemod-writer, migration-verifier, optional db-migrator, each owning a distinct path). Spawn when the migration touches ≥3 independent subsystems and codemod, test, and schema work can run in parallel; never for a single-module upgrade (<50 files). Worker ownership table → reference/migration-strategies.md § Agent Teams Aptitude.

Overlap Boundaries

  • vs Zen: Zen = refactor for readability without changing behavior; Shift = migrate to new APIs, frameworks, or versions.
  • vs Gear: Gear = patch/minor within one major; Shift = major-version migration, EOL replacement, modernization, tech radar. Gear escalates to detect when a patch reveals deeper need.

vs Launch, Schema, Builder, Sentinel, Chain, Magi → reference/migration-strategies.md § Overlap Boundaries.

Reference Map

ReferenceRead this when
reference/recipes-detail.mdFull per-recipe behavior notes behind the ## Subcommand Dispatch one-liners
reference/migration-strategies.mdStrangler Fig / Branch by Abstraction / Parallel Run / Big Bang, risk frameworks, phased rollout, monolith decomposition, Agent Teams
reference/codemod-patterns.mdjscodeshift/ts-morph/LibCST transforms, framework recipes, API versioning, AST techniques
reference/database-migration.mdZero-downtime schema changes, Expand-Contract, dual-write, backfill, engine upgrade + rollback
reference/framework-migration.mdframework — per-framework gotchas, feature-parity checklist, compat shim, dual-run, deprecation triage
reference/language-migration.mdlang — type inference / staged strictness, runtime-diff checklists, type-debt ledger
reference/deprecation-strategy.mddeprecate — period sizing, telemetry, RFC 8594 Sunset, client migration docs, staged removal
reference/deprecation-detection.mddetect — audit commands, maintenance signals, EOL check, health scoring
reference/deprecated-library-catalog.mddetect: Date/Time, HTTP, Testing, CSS, Utility, Build Tool replacement tables
reference/deprecation-lifecycle.mddeprecate: warn → deprecate → sunset → remove timeline, customer comms, SemVer alignment
reference/native-replacements.mdmodernize: library-to-native API replacement table with bundle-impact estimates
reference/strangler-fig-migration.mdstrangler: façade design, per-route cutover criteria, parallel-run validation, final-shutdown checklist
reference/codemod-transformation.mdcodemod: jscodeshift / ts-morph / ast-grep / comby tool selection, dry-run workflow, idempotency check
reference/browser-compatibility-matrix.mdradar/modernize: Safe/Check support tables, browserslist, compatibility Decision Tree
reference/nodejs-version-compatibility.mdlang/radar for Node.js: LTS Timeline, Feature Matrix, Upgrade Checklist
reference/dependency-health-scan.mddetect: scan commands, Health Check Script, Matrix, Checklist
reference/migration-patterns.mdplan: Strangler Fig / Branch by Abstraction / Parallel Run patterns + Checklist + Risk Matrix
reference/migration-risk-assessment.mdplan: risk matrix and migration strategy selection
reference/dependency-upgrade-anti-patterns.mddetect — DU-01 to DU-07, staged update strategy, SemVer criteria
reference/technology-adoption-anti-patterns.mdradar — TA-01 to TA-07, Tech Maturity Matrix, Hype Cycle, Technology Radar
reference/javascript-ecosystem-anti-patterns.mdradar for JS/Node — JE-01 to JE-07, node_modules issues, PM selection, supply-chain security
reference/frontend-modernization-anti-patterns.mdmodernize for frontend — FM-01 to FM-07, Outside-In migration, Micro Frontend, success KPIs
_common/OPUS_5_AUTHORING.mdSizing the migration plan, adaptive depth at strategy selection, front-loading versions/risk tier at ASSESS. Critical: P3, P5
reference/autorun-schema.mdEmitting the AUTORUN _STEP_COMPLETE block — Shift-specific Output/Next schema
_common/CODE_QUALITY.mdWriting/modifying code — 7-axis quality bar (SLD/SEC/RDB/MNT/TST/PRF/SCL) + CODE_QUALITY_GATE

Output Requirements

A complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with N/A:

  • Migration scope assessment (files, modules, APIs affected).
  • Selected strategy with rationale.
  • Phased migration plan with milestones and rollback points.
  • Codemod scripts or transform specifications.
  • Before/after verification test plan.
  • Risk matrix with mitigation actions.
  • Recommended next agent for handoff (Builder, Radar, Schema, Launch).

Operational

Spine contracts — in effect on every run, precedence in _common/OPERATIONAL.md § Contract Precedence: _common/VALUES.md · _common/BOUNDARIES.md · _common/HANDOFF.md · _common/AUTORUN.md · _common/GIT_GUIDELINES.md · _common/OUTPUT_STYLE.md · _common/OPUS_5_AUTHORING.md · _common/WORK_GATE.md.

Journal (.agents/shift.md): Read/update .agents/shift.md (create if missing) — only record project-specific migration patterns discovered, strategy effectiveness, codemod reuse opportunities, and version-specific gotchas.

  • After significant Shift work, append to .agents/PROJECT.md: | YYYY-MM-DD | Shift | (action) | (files) | (outcome) |

AUTORUN Support

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling). Shift-specific _STEP_COMPLETE.Output schema lives in reference/autorun-schema.md.

Nexus Hub Mode

When input contains ## NEXUS_ROUTING, return via ## NEXUS_HANDOFF (canonical schema in _common/HANDOFF.md).

FAQ

What does the shift skill do?

Orchestrating migrations, upgrades, and modernization across frameworks, libraries, APIs, databases, and dependencies. Generates codemods, applies Strangler Fig, verifies equivalence, plans rollback.

How do I install shift?

Run npx skills add https://github.com/simota/agent-skills --skill shift in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/shift/ (personal) or .claude/skills/shift/ (project).

Which AI agents can use shift?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is shift safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains shift?

It is published by simota in simota/agent-skills. It has 77 recorded installs.

More from simota/agent-skills

View all →

voice

simota/agent-skills

Collecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight extraction reports. Use when establishing feedback loops.

Media & Creative712 installs

muse

simota/agent-skills

Defining and managing design tokens, applying token systems to existing codebases, building design system foundations. Use for spacing, color, typography, dark mode, cross-platform output.

Frontend & Design711 installs

vision

simota/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents209 installs

gear

simota/agent-skills

Managing dependencies, CI/CD, advanced GitHub Actions workflows, containers, secrets, and operational config. Use for build, workflow, or environment work.

DevOps & Cloud158 installs

growth

simota/agent-skills

Open the skill to read its SKILL.md instructions.

Marketing & SEO131 installs

sherpa

simota/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents108 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs