Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TrueClicks/claude-plugins --skill skill-020-low-performing-keyword-pruninggit clone --depth 1 https://github.com/TrueClicks/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/trueclicks/claude-plugins/skill-020-low-performing-keyword-pruning)<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-020-low-performing-keyword-pruning"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-020-low-performing-keyword-pruning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-020-low-performing-keyword-pruning"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-020-low-performing-keyword-pruning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00778 |
| Opus 5 | $0.00016 | $0.00389 |
| Sonnet 5 | $0.00006 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
skill-020-low-performing-keyword-pruning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 020: Low-Performing Keyword Pruning
Purpose
Identify keywords that exceed cost thresholds without generating conversions, representing candidates for pausing or removal to improve account efficiency. Pruning non-performers reclaims budget for better keywords.
Data Requirements
Data Source: Standard
Standard Data:
data/performance/campaigns/*/*/keywords_metrics_30_days.md- Keyword performancedata/account/campaigns/*/*/keywords.md- Keyword settings (status, QS)data/account/campaigns/*/campaign.md- Campaign target CPA/ROAS and bidding strategy
Reference GAQL:
SELECT
campaign.name,
ad_group.name,
ad_group_criterion.keyword.text,
ad_group_criterion.keyword.match_type,
ad_group_criterion.quality_info.quality_score,
metrics.impressions,
metrics.clicks,
metrics.cost_micros,
metrics.conversions
FROM keyword_view
WHERE ad_group_criterion.status = 'ENABLED'
AND segments.date DURING LAST_30_DAYS
Use /google-ads:get-custom if you need different date ranges or longer lookback windows.
Analysis Steps
- Establish thresholds: Use campaign target CPA (prune at 2-3x with 0 conversions) or fixed $50 minimum
- Find zero-conversion keywords: Filter Conversions = 0, Cost >= threshold, sort by Cost descending
- Find high-CPA keywords: Filter Conversions >= 1, CPA > target CPA x 1.5
- Assess engagement signals: Check CTR < 1% (poor relevance), QS < 5 (landing page/ad issues)
- Consider context: New keywords in learning, conversion tracking issues, top-of-funnel awareness
Thresholds
| Condition | Severity |
|---|---|
| Cost >= 3x Target CPA AND Conv = 0 | Critical |
| Cost >= 2x Target CPA AND Conv = 0 | Warning |
| Cost >= $100 AND Conv = 0 AND CTR < 1% | Warning |
| CPA > 2x Target AND Conv >= 1 | Warning |
| Cost >= Target CPA AND Conv = 0 AND QS >= 7 | Info |
Output
Use Short format by default. Use Detailed if user requests comprehensive analysis.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 81 lines · 32 tokens per session scan A af2af3f10ad3
skill-020-low-performing-keyword-pruning is a skill published in the GitHub repository TrueClicks/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 778 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…