my-agent-stuff

Use when the user asks to copy drafted content to the clipboard, copy it again, prepare something for LinkedIn, paste rich text into a social composer, or stage plain text for X. This skill tells Pi when to use the rich clipboard extension and which format/target to choose.

This skill should be used when the user asks to "dump this conversation", "save this conversation to markdown", "output this conversation to a markdown file", "export this chat", "log this session to a file", "save this chat log", or similar. Produces a structured, readable capture of the current Pi conversation - user requests verbatim, assistant responses in full, commands plus key output inline, decisions preserved - not a brief summary. Distinct from mischief-managed, which writes a compact Obsidian session note.

Safely back up local folders to private Hugging Face Buckets using the installed hf CLI and the hf-buckets Pi extension. Use when the user asks to upload/archive/back up local data, training data, agent traces, model artifacts, checkpoints, corpora, or folders to Hugging Face storage, especially when privacy, buckets, quarantine, resume, monitoring, or deleting local copies is involved.

This skill should be used when the user asks to "jot this down", "add this to my daily note", "save this to today's note", "log this to obsidian", "note this down", "put this in my daily", or invokes /jot. Quickly appends any content - insights, thoughts, todos, links, ideas - to today's daily note in the configured Obsidian vault.

Use when managing Linear issues, projects, cycles, or team workflows. Triggers on creating, updating, triaging, or querying Linear tickets.

Perform a high-signal security code review of pending git/PR branch changes, focusing only on newly introduced HIGH/MEDIUM exploitable vulnerabilities and filtering false positives. Use when asked to security-review a branch, PR, diff, or pending changes.

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review".

Author pre/post-iteration hooks for an autoresearch session. Use when the user asks to add research fetching, Slack/webhook notifications, persistent learnings, auto-tagging, anti-thrash intervention, idea rotation, or any side effect around iterations.

Delegate work to builtin or custom subagents with single-agent, chain, parallel, async, forked-context, and intercom-coordinated workflows. Use for advisory review, implementation handoffs, and multi-step tasks where a single agent should stay in control while other agents contribute context, planning, or execution.

Strip sensitive EXIF metadata from images before publishing to the web. Activates when working with images for blog posts, websites, or public content, or when EXIF, metadata, GPS data, or image privacy is mentioned.

Scan Terraform, Kubernetes, CloudFormation, ARM templates, and Dockerfiles for security misconfigurations using 790 Terrascan-derived policies with NIST 800-53 control mappings. Use when users need to review IaC for security issues, audit cloud configurations, check compliance posture, harden infrastructure code, or identify misconfigurations across AWS, Azure, GCP, and Kubernetes before deployment.

Generate and edit images using Gemini image models. Use this skill when the user asks you to generate images, create visuals, edit photos, create logos, generate product mockups, or perform image generation or image editing tasks.

Apply the SUCCESs framework from "Made to Stick" to make app concepts, features, and written content more memorable and actionable. Use when evaluating ideas, reviewing UX, improving copy, or crafting sticky pitches.

Analyze Istio, Consul, and Linkerd service mesh configurations for security vulnerabilities with NIST 800-53 control mappings. Use when users need to audit mesh security, identify misconfigurations, check mTLS settings, review ACL policies, or prepare for FedRAMP assessments. Triggers on keywords like "mesh config", "istio security", "consul ACL", "linkerd policy", "service mesh audit", or "NIST compliance".

Use when finishing a Pi, Codex, or other coding-agent session and wanting to save a lean Markdown session note into an Obsidian vault with decisions, code changes, validation, caveats, and follow-ups.