Explorar skills

Recommend budget reallocation across Meta, Google, and LinkedIn based on per-platform CPA efficiency. Computes efficiency score (bestCPA/platformCPA) and weights budget proportionally. Read-only — recommendations must be applied manually. Triggers on prompts about where to shift budget or which platform to scale.

Build Meta custom audiences from CSV files (CRM leads, email/phone lists, WhatsApp contacts). Hashes PII client-side (SHA-256, normalized per Meta spec) before upload. Triggers on prompts about uploading leads/contacts/lists as custom audiences on Meta.

Trigger on "solution arc", "current state target state", "consult narrative", "storyline for proposal", "MVP pilot full as risk", "sequencing rationale". Builds one arc: as-is → target capability → why this order, with options tied to risk reduction. NOT the frame card (use consult-frame), NOT gate tables (use consult-gates), NOT diagrams (use arch-diagrams).

Trigger on "consult lint", "consistency pass", "diagram vs narrative", "broken promises across docs", "cross-artifact check", "scope drift lint". Read-only diff across frame, arc, gates, acceptance, commercial, architecture artifact. NOT rewriting copy (use consult-package), NOT drawing diagrams (use arch-diagrams).

Trigger on "what did I decide about X", "why did I pick X", "did I choose X over Y", "what was my call on X", "ADR for X", "is there a decision on X", "have I picked between X and Y". Use when the user wants to recall a settled past decision, not make a new one. NOT for fresh tradeoff analysis (route to Claude or timeln-find).

Trigger on "what bit me on X", "have I been burned by X", "gotchas with X", "what went wrong last time with X", "warn me about X", "any retros on X", "past incidents with X". Use when the user wants to sanity-check an approach against their own failure history. NOT for general pitfalls (ask Claude directly) or past decisions (use timeln-decided).

Optimize JavaScript library size.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest

Analyze Google Ads keywords — quality score, impression share, CPC, conversions. Flags low-QS (≤4) and low-IS (<50%) keywords. Triggers on prompts about keyword performance, quality score issues, or impression share gaps.

Google Ads period-over-period performance audit. Compares impressions, clicks, CTR, spend, CPC, conversions, CPA between current and previous window of same length. Generates HTML executive report. Triggers on prompts about performance audits, period comparisons, or "how is the account doing".

Trigger on "package for exec", "consult deliverable pack", "appendix vs main deck", "client-ready consulting doc", "strip placeholders proposal", "readout structure". Assembles exec layer vs detail, removes placeholders, runs consistency pass. Produces client-facing artifact + lint report (inline `consult-consistency-lint` or separate).

Trigger on "quickly: X", "quickly recall X", "what did I say about X", "what did they say about X", "find the quote on X", "remind me -- X", "did [name] mention X", "what was the number for X", "what date did I commit to X". Use when the user needs a one-breath answer mid-call or mid-pitch. NOT for exploration (use timeln-find) or planning (use timeln-plan).