portable-agent-layer

Rewrites text to remove AI slop and make it sound human: eliminates em-dashes and en-dashes, LLM tell-words (delve, leverage, robust, seamless), 'not just X, it's Y' constructions, rule-of-three padding, boilerplate openers/closers, hedging, and decorative emoji, while preserving meaning and voice. Use when asked to humanize text, de-slop, remove AI dashes or em-dashes, strip AI tells, make writing sound human, or clean AI-generated prose.

Author a NEW skill that ships WITH the PAL repo (committed to assets/skills/ and installed for every downstream user). Use only when working inside the portable-agent-layer repo and adding a shared, general-purpose skill. For a user's own private skill, use create-skill instead.

Create a user-scoped subagent for every installed agent (Claude Code, opencode, Cursor, Copilot) from one merged definition, then install and run the doctor on it. Use when the user asks to create a subagent, add a custom agent, delegate a role to a specialized agent, or "make a subagent that…".

Create a new personal skill for this user, scaffolded into their own ~/.pal/skills/ and linked into every installed agent. Use when the user asks to create a skill, add a capability, build a custom command, or "make a skill that…".

Convert markdown files into a styled PDF. Use when creating a PDF from existing markdown files, combining markdown into a report, or converting .md to .pdf.

Project context management. PROACTIVE — use when the user references a project (by name or as "this repo", "current work"), asks to add/update/complete a project, says "store under a named project", "track this", "what am I working on", "my projects", "my priorities". Also triggered by ISC/ISA terminology — ISC stands for Ideal State Criteria, a project's verifiable done-conditions stored as `ISC-N:` lines in the Criteria section of its ISA.md spec. Phrases like "ISC", "open/opening the ISC", "open ISCs" (unfinished criteria), "create/creating a ticket for a project", "new ticket", or "project ticket" all map here: use `list-isc` to read them, `add-isc` to create one, `complete-isc`/`reopen-isc` to change status.

Download and analyze PDF files from URLs or local paths — extract text, answer questions, summarize content. Use when analyzing, reading, or extracting information from a PDF.

Analyze YouTube videos using Gemini's native video understanding — summarize, extract insights, answer questions. Use when analyzing, summarizing, or extracting information from a YouTube video.

Build a beautifully-typeset consulting-report PDF from a typed data file and a React layout. Use when generating an assessment, strategic review, operational readiness check, or any McKinsey-style consulting deliverable as a PDF.

Multi-perspective parallel debate on a decision — 3-5 independent perspectives argue in parallel, then synthesize into a verdict. Use when debating, weighing options, or needing multiple viewpoints on a question.

Maintain the personal knowledge graph of people and companies. Detect named entities in any content (article, video, paste, conversation), upsert them to ~/.pal/memory/knowledge/, and surface what's already known. Use proactively whenever named entities appear — don't wait to be asked.

Extract structured insights from content (articles, videos, podcasts). Use when extracting wisdom, key takeaways, or structured insights from any content.

Break down a problem to its fundamental constraints and build up a solution. Use when decomposing complexity, challenging assumptions, or finding root causes.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Query Fyzz Chat conversations and projects via the REST API. Use when looking up conversations, searching chat history, or listing projects in Fyzz Chat.

Run learning analysis — surface rating trends, recurring failure patterns, and graduation candidates. Use when learning analysis is due, or when the user asks about performance patterns, low ratings, or what to improve.

Run relationship reflect — promote recurring behavioral observations into tracked opinions. Use when relationship reflect is due, or when the user asks to review what patterns have been observed.

Capture a screenshot of a URL or local page and load it into context for a visual check. Use when asked to check visually, use playwright, screenshot a page, see or look at the design yourself, or verify a layout on desktop and mobile widths.

Build branded HTML presentations from markdown using Reveal.js. Multi-template registry per user (each template = brand color, logo, fonts, footer, aspect). Per-deck workflow: scaffold → edit one markdown file per slide in slides/ → build → present. Output: a per-deck subdir with a self-contained HTML and a concatenated markdown sibling. 14 layouts including data-display patterns (big-stat, metric-grid). Use when creating slide decks, talks, workshop slides, lectures, or pitch decks.

Diagnose why a PAL behavior did not trigger as expected — trace hooks, instructions, and logic to find the gap. Use when a hook, skill, or automation didn't fire or behaved unexpectedly.

Multi-agent parallel research — quick/standard/extensive modes with specialized researcher agents for depth, breadth, and verification. Use when researching a topic, finding information, or investigating something thoroughly.

Security-focused code review with severity ratings. Use when reviewing code for security issues, vulnerabilities, or OWASP concerns.

Structured summarization of documents, URLs, or conversations. Use when summarizing content, creating overviews, or distilling key points.

Personal context management. Use when discussing goals, beliefs, challenges, identity, updating telos, life context, changing a goal, what do I believe, current obstacles, mission, or strategies.

Thinking mode router — selects the right analytical approach for a question. Use when thinking through a problem, analyzing deeply, brainstorming ideas, debating options, decomposing to root cause, challenging assumptions, or exploring from multiple perspectives.

Evaluate a PAL inference prompt using the promptfoo harness in eval/. Use when a prompt constant in src/ has changed or may have regressed, when scaffolding a new prompt eval from scratch, or when comparing a v2 candidate against the current baseline.

Run a maintainer algorithm-update session — synthesize the collected Q2 ("smarter algorithm") reflections, cluster the recurring ideas, and fold approved changes into ALGORITHM.md. Use when the session reminder shows "Algorithm Review Due", or when asked to review/update the algorithm from reflections.

Opinion tracker for relationship notes. PROACTIVE: When the user confirms a preference ('yes exactly', 'keep doing that'), contradicts one ('no, don't do that', 'stop'), or you observe a recurring behavioral pattern — invoke this to update opinion confidence.