Receber por email
← Voltar para o catálogo

Autor no catálogo

mikeprasad

101 skills 1.616 estrelas no total GitHub ↗

Skills publicadas

Mostrando 12 de 101

context

16

Load relevant knowledge by topic. Queries the tag index and presents matching promoted files for selective loading into context. Use when user says "/aria-cowork:context stripe", "/aria-cowork:context api pagination", "/aria-cowork:context architecture", "load knowledge about...", "what do we know about...". (Cowork variant — namespaced-only.)

Desenvolvimento #ai #api por mikeprasad

distill

16

Shape messy task input into an implementation-ready task spec with scope, criteria, risks, dependencies, and execution plan. Trigger on /distill or turn this into a task spec.

Desenvolvimento #ai por mikeprasad

aria-setup

16

Configure aria-cowork on first run or after updates. Verifies your knowledge folder is reachable from this Cowork session, guides you through adding it to claude_desktop_config.json for persistent multi-session access if needed, scaffolds the folder structure, and writes the canonical aria-config.md. Safe to re-run anytime — only touches what.

Desenvolvimento #ai por mikeprasad

index

16

Rebuild the knowledge tag index. Scans promoted files, normalizes tags, flags untagged files, suggests freeform-to-known promotions, detects stale files, and regenerates index.md. Use when user says "/aria-cowork:index", "rebuild index", "update index", "reindex knowledge". (Cowork variant — namespaced-only.)

Desenvolvimento #ai por mikeprasad

handoff

16

Generate a handoff package for the next session or a coworker: status, continuity notes, optional commit, and extraction. Trigger on /handoff, hand it off, context is full, or pass off.

Desenvolvimento #ai por mikeprasad

aria-knowledge

16

Run a structured retrospective on a shipped commit range, release, deployment, PR, commit, or session. Per-fix validation enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, re-diagnosis, action verdicts, and a growing failure-mode pattern library. Triggers: '/retrospect' (auto-range), '/retr

DevOps e Infra #ai #deploy por mikeprasad

help

16

Show available aria-cowork commands. Use when user says "/aria-cowork:help", "aria help", "what commands are available", "list commands", "what can aria-cowork do". (Cowork variant — namespaced-only.)

Desenvolvimento #ai por mikeprasad

aria-knowledge

16

Generate or update a feature-organized CODEMAP.md for any codebase. Scans repos, detects frameworks, identifies features, traces full-stack flows (frontend routes → hooks → state → backend views → models → integrations), and produces a navigable reference with a directory table for selective loading. Supports modes: create (full generation), inventory (quick index only), update (incremental refres

Design e Frontend #ai por mikeprasad

index

16

Rebuild the ARIA knowledge tag index, including tag normalization, project mappings, stale file signals, skill connections, and shared-knowledge entries. Trigger on /index or reindex knowledge.

Desenvolvimento #ai por mikeprasad

aria-knowledge

16

NOTE: this skill requires connected ~~chat / ~~email / ~~project-tracker / ~~docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker / docs. Use when user says '/digest', 'weekly digest', 'cross-tool rollup', 'wh

Desenvolvimento #ai #mcp por mikeprasad

aria-knowledge

16

Save the current Antigravity transcript to the knowledge intake on demand. Use when user says '/snapshot', 'snapshot the session', 'save this conversation', 'capture the transcript', or 'archive this session'. Same archival output as the canonical pre-compact hook, but explicit because Antigravity has no PreCompact event. Distinct from /extract and /intake.

Desenvolvimento #ai por mikeprasad

aria-knowledge

16

Run a structured pre-mortem on a plan or approach BEFORE execution. Per-step risk enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, plan-formation diagnosis, action verdicts (PROCEED/SHRINK/SPLIT/DEFER/KILL), and a growing failure-mode pattern library. Triggers: '/prospect' (defaults to pla

Desenvolvimento #ai por mikeprasad