Pause an AI-SDLC run and produce an Escalation Report when a hard-stop trigger fires, risk meets the tolerance threshold, or a decision exceeds the agent's authority. Trigger when a gate hits an escalation condition or the user asks to escalate, pause the loop, or request human approval.
EnglishProduce reversible multi-zoom summaries of a corpus of items (bugs, PRs, incidents, requirements, files, log clusters, ...) so an agent or human can survey many items at low detail, then expand only the interesting ones. Each item is summarized at multiple "zoom levels" — 2, 4, 8, 16, 32, 64, 128 words — with the full text preserved at the deepest level. Trigger when the user asks to pyramid-summarize, build collapsible summaries, do a multi-resolution survey, scan a large list of issues/PRs/incidents, prepare a triage view, or compress context without losing fidelity.
EnglishRun a multi-tool repository quality assessment — git object health, contributor analytics, commit hygiene, hook configuration, secret scanning, module dependency architecture, and changed-code quality — and consolidate findings into a single report. Trigger when the user asks for a repo health scan, git history audit, secret scan, dependency graph check, commit message quality review, bus factor analysis, or wants to know the overall structural health of the repository.
EnglishCompile all SDLC run artifacts from .sdlc/runs/ into a self-contained HTML/JS report and open it in the browser. Trigger when the user asks to generate a report, view run results, or produce an HTML summary of an SDLC run.
English
AGENT SKILLS ATLASIncludes Sdlc:escalate, Sdlc:pyramid, Sdlc:repo Health, 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
Sdlc:escalate
Pause an AI-SDLC run and produce an Escalation Report when a hard-stop trigger fires, risk meets the tolerance threshold, or a decision exceeds the agent's authority. Trigger when a gate hits an escalation condition or the user asks to escalate, pause the loop, or request human approval.
Sdlc:pyramid
Produce reversible multi-zoom summaries of a corpus of items (bugs, PRs, incidents, requirements, files, log clusters, ...) so an agent or human can survey many items at low detail, then expand only the interesting ones. Each item is summarized at multiple "zoom levels" — 2, 4, 8, 16, 32, 64, 128 words — with the full text preserved at the deepest level. Trigger when the user asks to pyramid-summarize, build collapsible summaries, do a multi-resolution survey, scan a large list of issues/PRs/incidents, prepare a triage view, or compress context without losing fidelity.
Sdlc:repo Health
Run a multi-tool repository quality assessment — git object health, contributor analytics, commit hygiene, hook configuration, secret scanning, module dependency architecture, and changed-code quality — and consolidate findings into a single report. Trigger when the user asks for a repo health scan, git history audit, secret scan, dependency graph check, commit message quality review, bus factor analysis, or wants to know the overall structural health of the repository.
Sdlc:report
Compile all SDLC run artifacts from .sdlc/runs/ into a self-contained HTML/JS report and open it in the browser. Trigger when the user asks to generate a report, view run results, or produce an HTML summary of an SDLC run.
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 Sdlc:escalate 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.