Save compact project-local lessons, prompt improvements, source blacklists/whitelists, and recurring failure modes after a task. Use when wrapping up a research task, "save what we learned", "log this lesson", or when a useful pattern emerges.
EnglishScore candidate tools, plugins, agents, products, or repos, keep the high-signal subset, and cut overlap, abandonment, or low-value options.
EnglishUse the standard quick, normal, deep-dive, and adversarial report formats for worker briefs and final synthesis.
EnglishRank sources by credibility, freshness, firsthand evidence, maintenance health, and shill risk. Use when the user says "are these sources good", "rank these", "which sources should I trust", or when separating signal from SEO sludge.
EnglishConvert messy comparisons or findings into a clean spreadsheet plan, scoring model, and review checklist. Use when the user says "make a comparison table", "turn this into a spreadsheet", "score these options", or has raw findings that need structure.
EnglishBuild compact, high-quality task packets for subagents with objective, scope, ranking criteria, stop rules, red flags, and expected report style.
English
AGENT SKILLS ATLASIncludes Lessons Ledger, Rank and Prune, Research Report Contract, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Lessons Ledger
Save compact project-local lessons, prompt improvements, source blacklists/whitelists, and recurring failure modes after a task. Use when wrapping up a research task, "save what we learned", "log this lesson", or when a useful pattern emerges.
Rank and Prune
Score candidate tools, plugins, agents, products, or repos, keep the high-signal subset, and cut overlap, abandonment, or low-value options.
Research Report Contract
Use the standard quick, normal, deep-dive, and adversarial report formats for worker briefs and final synthesis.
Source Triage
Rank sources by credibility, freshness, firsthand evidence, maintenance health, and shill risk. Use when the user says "are these sources good", "rank these", "which sources should I trust", or when separating signal from SEO sludge.
Spreadsheet Polish
Convert messy comparisons or findings into a clean spreadsheet plan, scoring model, and review checklist. Use when the user says "make a comparison table", "turn this into a spreadsheet", "score these options", or has raw findings that need structure.
Task Packet Builder
Build compact, high-quality task packets for subagents with objective, scope, ranking criteria, stop rules, red flags, and expected report style.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Lessons Ledger skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.