Preserve discovered bugs as durable BUGS.md entries with reproduction steps, expected behavior, hypothesis, status, verification, and resolution.
EnglishImplement exactly one planned slice after scope is frozen, then run relevant verification, summarize changed files, and stop.
EnglishDetect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.
EnglishDebug failures systematically by freezing feature work, reproducing the issue, testing hypotheses, applying the smallest fix, and rerunning verification.
EnglishClarify ambiguous AI-engineering project ideas before specs or code by challenging vague terms, identifying assumptions, and updating durable context.
EnglishCompress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.
EnglishCreate a compact SPEC.md for fast solo AI-engineering projects when the goal is clear enough to define behavior, constraints, and verification without full PRD ceremony.
EnglishLimit an agent's blast radius before implementation by defining allowed files, read-only areas, forbidden operations, commands, and stop conditions.
EnglishRun a lightweight GO or NO-GO gate before using small dashboards, ML workflows, agent workflows, scheduled jobs, or decision-impacting outputs.
EnglishAdd focused deterministic tests, fixtures, golden examples, or smoke checks for workflows that can run while still being wrong.
EnglishConvert a mini-spec into 3-7 vertical implementation slices when a small project needs observable, independently verified progress.
EnglishRecord proof that a task works by capturing commands, pass/fail results, changed files, artifacts, risks, and the next safest task.
EnglishCheck consistency across CONTEXT.md, SPEC.md, PLAN.md, TODO.md, and scope-freeze notes.
Uncertain
AGENT SKILLS ATLASIncludes Bug Capture, Context Check, Diagnose Loop, 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
Bug Capture
Preserve discovered bugs as durable BUGS.md entries with reproduction steps, expected behavior, hypothesis, status, verification, and resolution.
Build One
Implement exactly one planned slice after scope is frozen, then run relevant verification, summarize changed files, and stop.
Context Check
Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.
Diagnose Loop
Debug failures systematically by freezing feature work, reproducing the issue, testing hypotheses, applying the smallest fix, and rerunning verification.
Grill with Docs Lite
Clarify ambiguous AI-engineering project ideas before specs or code by challenging vague terms, identifying assumptions, and updating durable context.
Lean Mode
Compress routine agent responses to reduce token usage while preserving commands, file paths, assumptions, risks, verification details, and next actions.
Mini Spec
Create a compact SPEC.md for fast solo AI-engineering projects when the goal is clear enough to define behavior, constraints, and verification without full PRD ceremony.
Scope Freeze
Limit an agent's blast radius before implementation by defining allowed files, read-only areas, forbidden operations, commands, and stop conditions.
Ship Mini
Run a lightweight GO or NO-GO gate before using small dashboards, ML workflows, agent workflows, scheduled jobs, or decision-impacting outputs.
Test Mini
Add focused deterministic tests, fixtures, golden examples, or smoke checks for workflows that can run while still being wrong.
Thin Plan
Convert a mini-spec into 3-7 vertical implementation slices when a small project needs observable, independently verified progress.
Verify Contract
Record proof that a task works by capturing commands, pass/fail results, changed files, artifacts, risks, and the next safest task.
Analyze Mini
Check consistency across CONTEXT.md, SPEC.md, PLAN.md, TODO.md, and scope-freeze notes.
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 Bug Capture 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.
- Reported license for the skills shown: MIT. The author’s terms apply.