Agent skill

ads-resonance

Analyze ad performance and feed the learnings back into your Octave library — the resonance loop.

activeReaches the webActs undeclared380 words

From octavehq/lfgtm · 27 skill entries · 11 · pushed 2026-09-21

What it does when it runs

Analyze ad performance and feed the learnings back into your Octave library — the resonance loop. Pulls performance data from Google Ads MCP, BigQuery Data Transfer, direct API, or manual paste; maps winners back to the source cards behind each ad variant; generates library update recommendations and a sales intelligence brief; writes falsifiable prediction cards and accumulates a calibration track record over time. Use when user says "analyze ad performance", "resonance loop", "score predictions", "evaluate my ads", or asks to turn ad performance into GTM intelligence. Do NOT use to build a new ad campaign — use /octave:ads instead.

Automated analysis of the skill and the 7 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply: None found.
Hosts it reaches: fonts.googleapis.com
Tool permissions it declares: No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files: writes files

Our read

Computed from the artifact. Nothing here has been run, so none of it is a claim about how well the skill works — only about what it is and what it needs.

Maintenanceactive

Pushed within the last 30 days, with commits in the last 90.

CouplingReaches the web

Reaches a third-party host at runtime, but needs no key of its own.

Blast radiusActs undeclared

It acts, and declares no `allowed-tools`, so it inherits whatever your session already permits.

What it does to your systemsUnreviewed

The reading was not confident enough, or not yet confirmed, to publish.

Sends messages: No step found in the source
Writes records: No step found in the source
Spends credits: Unreviewed
Needs credentials: No key or connector found by pattern match

Read from source, not tested by running. Machine-read from SKILL.md at commit 6facb2c with jev-1.13.0; labels that write, send or spend were also checked against the cited line by a second reviewer. How this is read

Substancebrief

Under 600 words, no bundled reference files.

LicenceMIT

Permits redistribution with attribution, per the repository.

Ask about ads-resonance

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?Claude ChatGPT

Adapt it to my stackClaude ChatGPT

What else do I need for it to workClaude ChatGPT

Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗

git clone --depth 1 --filter=blob:none --sparse https://github.com/octavehq/lfgtm.git /tmp/lfgtm
git -C /tmp/lfgtm sparse-checkout set "skills/ads-resonance"
mkdir -p ~/.claude/skills/ads-resonance
cp -R "/tmp/lfgtm/skills/ads-resonance/." ~/.claude/skills/ads-resonance/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

Or take the whole library

This repo ships a .claude-plugin manifest, so Claude Code can install all 27 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.

/plugin marketplace add octavehq/lfgtm
/plugin

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

The skill

Source on GitHub ↗

Reproduced in full from octavehq/lfgtm/blob/6facb2c00d93c48e29a370d3d93d52e4380f3b45/skills/ads-resonance/SKILL.md, which is licensed MIT (repository). 380 words, 6 headings.

Octave Ads Resonance Loop — Performance → Library Intelligence

Run the task

Read the task method before selecting context, claims, or output. It is the execution method for this skill. Supporting templates supply structure and styling; populate them from the task method and current evidence, not their illustrative figures or assertions.

Support connected API, CSV and BigQuery inputs. Scope every record to verified workspace/platform/customer IDs. Use exact creative membership or a unique complete fingerprint; never join on a headline alone. Use the deterministic prediction reducer. No automatic strategic writes, confidence promotion, CPC-based pausing, or budget transfers.

Use GTM context for strategic tasks and evidence and inputs for material claims and missing facts. A narrow list/get or a render-only handoff does not require unrelated research. Read host runtime for available tools, portable resource paths, routing, and review fallback.

Resolve current tool schemas before execution; use returned IDs and pagination. Inventory rows locate records; hydrate selected entities/resources before relying on their contents. Reuse supplied or inherited context and authorization. Ask grouped questions only for material unresolved inputs, continue independent work, incorporate replies, and recheck affected output.

Usage

Use /octave:ads-resonance with the requested task, target, and output.

References by task

Read only the reference for the selected mode, then the format/layout references when rendering. Do not repeat intake or change approved claims when routing to a renderer.

Delivery and changes

Apply output readiness to text and artifacts. HTML also uses the review protocol and the matching format checks. A working preview can be shared with its status; unrun checks are NOT RUN. Reviewers return findings on an immutable version; one author applies edits and rechecks the final version.

For visual output, inherit the selected sender/workspace brand through brand kit usage; honor an explicit override and avoid repeated brand extraction. Public hosting requires the approved audience and publish manifest, followed by URL/access/link verification.

For comparisons, trends or rates, use the analytics contract. Only requested persistence loads workspace mutations; report changes as applied only after scoped readback.

Runtime resources

Resolve these paths from the installed skill directory. Inline template JS/CSS into self-contained artifacts; do not add runtime dependencies on the plugin installation.

predictions.py

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

google-ads-youtube-ads-strategist by Ad-Superpowers · 5
ads by coreyhaines31 · 51,063
facebook-ads by OpenClaudia · 697
google-ads by OpenClaudia · 697
google-ads-report by OpenClaudia · 697
linkedin-ads by OpenClaudia · 697
meta-ads-expert by Varnan-Tech · 660
competitor-ads-analyst by thatrebeccarae · 147

Need help setting it up?

This page tells you what ads-resonance does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.