will-pagane/chief-of-staff-template
Agent Claude Code
Renders the final HTML report from a structured analysis payload. Use after the main agent has finished diagnosing — never for analysis itself.
not rated 5 2mo ago A 32 tokens
will-pagane/chief-of-staff-template
Skill Claude Code
Full performance analysis of a single Product Ads campaign with HTML report and feedback sidecar.
not rated 5 2mo ago A 23 tokens
will-pagane/chief-of-staff-template
Skill Claude Code
Account-wide performance overview across all active Product Ads campaigns.
not rated 5 2mo ago A 16 tokens
will-pagane/chief-of-staff-template
Skill Claude Code
Scan all feedback sidecars, identify patterns in done vs not-done recommendations, and propose updates to knowledge files. Owner approval required before applying.
not rated 5 2mo ago A 35 tokens
ml-ads-auth
05will-pagane/chief-of-staff-template
Skill Claude Code
Start or complete OAuth authorization with Mercado Livre. No args opens the authorization URL in the browser; with a callback URL argument completes the flow.
not rated 5 2mo ago A 33 tokens
will-pagane/chief-of-staff-template
Skill Claude Code
Conversational shortcut to mark a recommendation as done or not-done with reason, updating its feedback sidecar.
not rated 5 2mo ago A 26 tokens
ml-ads
07will-pagane/chief-of-staff-template
MCP server Claude CodeCodexCursor +2
MCP server "ml-ads" as configured in will-pagane/chief-of-staff-template. Launched with uv --directory mcp run ml-ads-mcp.
not rated 5 2mo ago A
tokens not measured
will-pagane/claude-superdev-harness
Skill Claude CodeCodex
Use when the user asks for an extensive, maximum-quality, whole-codebase review or audit and wants a consolidated findings report (read-only, default). Add --autopilot to run a fully autonomous performance pipeline: read Supabase signals, deep-dive via dynamic workflows, refine fixes with a headless Codex pass, apply…
not rated 4 2d ago A 0 tokens
original MIT
codex-review
09will-pagane/claude-superdev-harness
Skill Claude CodeCodex
A standalone adversarial PLAN-review loop where Claude Code (builder) and OpenAI Codex (read-only critic) tag-team an implementation plan before any code is written. Use this when you ALREADY have a plan or a clear idea and just want the cross-model stress-test — no requirements interview first. Claude drafts/loads…
not rated 4 2d ago B 271 tokens
original MIT
will-pagane/claude-superdev-harness
Skill Claude CodeCodex
Use when the user wants an idea taken from conversation to implemented, pushed branches in one pass — "/session-build ", "builda isso", "brainstorma e implementa", "aprimore ao máximo", "faça as melhorias", "vamos mapear e escrever estas specs", "pega essa ideia e leva até a branch pronta". ALSO invoke…
not rated 4
changed 2d ago A 0 tokens
original MIT
session-end
11will-pagane/claude-superdev-harness
Skill Claude CodeCodex
Use when branch work is finished and the user asks to close the session out — "/session-end", "encerra a sessão", "fecha essa branch", "vamos encerrar aqui", "abre o PR e faz o merge", "leva até o merge e limpa a branch", "finaliza e limpa o worktree". Also OFFER it (do not auto-run it) when the user signals closure…
not rated 4
changed 1mo ago A 0 tokens
original MIT
will-pagane/claude-superdev-harness
Skill Claude CodeCodex
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
not rated 4 2d ago A 91 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: