Explorar skills

Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.

Mine negative keyword candidates from Google Ads search terms (terms with impressions + clicks + cost but zero conversions + low CTR). Can optionally bulk-apply negatives to an ad group with explicit confirmation. Triggers on prompts about wasted spend, negative keyword lists, or search term cleanup.

Parent skill for LinkedIn Ads operations — campaigns, creatives, analytics, DMP segments (custom audiences). Delegates to sub-skills for ABM audience builds, bid optimization, bulk campaign edits, and creative format analysis.

Analyze LinkedIn campaign CTR, conversions, and actual CPC vs bid, then suggest ±% bid adjustments. Can apply adjustments with explicit confirmation. Triggers on prompts about bid tuning, CPC/CTR optimization, or reallocating spend to winning campaigns.

Analyze LinkedIn creative format performance (single image, carousel, video, document, lead gen) and suggest next formats to test. Aggregates by format across all creatives in a campaign. Triggers on prompts about which format to double down on, lead gen performance, or creative testing strategy.

Parent skill for Meta (Facebook/Instagram) Ads operations — campaigns, ad sets, ads, creatives, audiences, insights. Delegates to specialized sub-skills for bulk creative uploads, custom audience builds, fatigue detection, and spend tracking.

Extract Google Ads search terms report and classify by intent (commercial, informational, navigational, unknown) using PT/EN keyword hints. Triggers on prompts about search terms, intent analysis, or finding keyword opportunities.

Track Meta Ads daily spend against a monthly budget. Projects end-of-month spend based on current pace, flags when burn rate exceeds expected pace, and generates a daily spend chart. Triggers on prompts about budget pacing, monthly projections, burn rate, or spend anomalies.

Trigger on "frame the engagement", "consult frame", "problem frame", "scope card", "definition of good", "what decision does this support", "in scope out of scope", "client brief → frame", "one-pager frame". Turns a brief or transcript into a structured engagement frame. NOT the solution arc (use consult-arc), NOT phasing gates (use consult-gates), NOT memory recall (use timeln-find / timeln-decid

Trigger on "lock phasing", "stage gates", "consult gates", "phase outcomes", "primary question per phase", "entry exit criteria", "gate table". Defines staged outcomes with one primary question per phase plus entry/exit. NOT acceptance metrics (use consult-acceptance), NOT personal save cascade (timeln-plan is parallel -- use its output as optional input only).

Use when writing, reviewing, or modifying any test files, or when asked to add test coverage.

Guide for implementing a new language parser in Codanna. Use when adding language support, implementing parsers, or extending language capabilities. Covers the six-file architecture (mod.rs, definition.rs, parser.rs, behavior.rs, resolution.rs, audit.rs), trait implementation patterns, resolution scope design, and integration workflow. Triggers on requests to add language support, implement new pa