Explore skills

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).

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.