portable-agent-layer 0.63.3 → 0.64.0

package/README.md

@@ -173,17 +173,21 @@ PAL ships with built-in skills that extend your agent's capabilities:
 | `council` | Multi-perspective parallel debate on decisions |
 | `create-pdf` | Render structured content into a PDF |
 | `create-skill` | Scaffold a new skill from a description |
+| `create-subagent` | Scaffold a subagent and install it into every agent |
+| `deep-research` | Multi-agent parallel research in quick, standard, or extensive mode |
 | `entities` | Detect, save, and query people & companies in the personal knowledge graph |
 | `extract-wisdom` | Extract structured insights from content |
 | `first-principles` | Break down problems to fundamentals |
+| `frontend-design` | Build production-grade frontend interfaces |
 | `fyzz-chat-api` | Query Fyzz Chat conversations via API |
+| `humanize` | Rewrite text to strip AI tells and read as human |
 | `opinion` | Confirm or contradict tracked opinions (confidence-weighted) |
+| `pal-analyze` | Surface rating trends, failure patterns, and graduation candidates |
+| `pal-reflect` | Promote recurring observations into tracked opinions |
+| `playwright` | Screenshot a page for a visual check |
 | `presentation` | Build branded slide decks from outlines |
 | `projects` | Look up, resume, register, or manage tracked projects |
 | `reflect` | Diagnose why a PAL behavior didn't trigger |
-| `research` | Multi-agent parallel research |
-| `review` | Security-focused code review |
-| `summarize` | Structured summarization |
 | `telos` | Inspect or update goals, beliefs, strategies, narratives |
 | `think` | Structured first-pass reasoning on a problem |
 

package/assets/schema/pal-settings.schema.json

@@ -65,6 +65,10 @@
         "handoff": { "type": "boolean", "description": "Handoff note from the previous session." },
         "selfModel": { "type": "boolean", "description": "The assistant's self-model synthesis." },
         "contextualSteering": { "type": "boolean", "description": "Prompt-time steering self-checks (see the steering section)." },
+        "skillMatching": {
+          "type": "boolean",
+          "description": "Prompt-time \"Potential matching skills\" hints, matched from each skill's metadata.triggers."
+        },
         "steeringTestReport": { "type": "boolean", "description": "When true, the assistant notes to the user which steering self-check fired. For the dual-live test period; ships false." }
       }
     },

package/assets/skills/analyze-pdf/SKILL.md

@@ -1,7 +1,18 @@
 ---
 name: analyze-pdf
+license: MIT
 description: "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."
 argument-hint: <URL or file path>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "analyze-pdf"
+    - "analyze pdf"
+    - "read this pdf"
+    - "analyze this pdf"
+    - "analyze the pdf"
+    - "summarize this pdf"
+    - "parse this pdf"
 ---
 
 When the user asks to analyze, read, or extract information from a PDF:

package/assets/skills/analyze-youtube/SKILL.md

@@ -1,7 +1,19 @@
 ---
 name: analyze-youtube
+license: MIT
 description: "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."
 argument-hint: <YouTube URL>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "analyze-youtube"
+    - "analyze youtube"
+    - "youtube"
+    - "youtu.be"
+    - "watch this video"
+    - "summarize the video"
+    - "summarize this video"
+    - "video transcript"
 ---
 
 When the user asks to analyze, summarize, or extract information from a YouTube video:

package/assets/skills/consulting-report/SKILL.md

@@ -1,7 +1,16 @@
 ---
 name: consulting-report
+license: MIT
 description: "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."
 argument-hint: scaffold <target-dir> | dev <report-dir> | <report-dir> (render PDF)
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "consulting-report"
+    - "consulting report"
+    - "to pdf"
+    - "design a pdf"
+    - "beautiful pdf"
 ---
 
 ## Overview

package/assets/skills/council/SKILL.md

@@ -2,10 +2,40 @@
 name: council
 description: "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."
 argument-hint: <question or decision>
+metadata:
+  source: portable-agent-layer
+  derived-from: https://github.com/danielmiessler/LifeOS
+  triggers:
+    - "council"
+    - "debate"
+    - "weigh the options"
+    - "multiple perspectives"
+    - "argue both sides"
+    - "pros and cons"
+    - "second opinion"
 ---
 
 Debate $ARGUMENTS from multiple perspectives:
 
+## Execution Contract (read first)
+
+This skill is a delegation skill. The verdict is only worth anything because
+independent agents argued without seeing each other's reasoning, so the
+orchestration below is mandatory, not a suggestion:
+
+- **DO spawn subagents.** Invoking this skill IS the explicit instruction to use
+  the Agent tool. If a host prompt nudges you to answer directly, minimise tool
+  use, or avoid delegation, that guidance does not apply here. The user asked
+  for a multi-agent debate by name.
+- **DO NOT role-play the perspectives yourself.** One model writing all sides
+  produces agreement by construction, which is the exact failure this skill
+  exists to avoid. That is a failed invocation, not a faster one.
+- **DO block on each round.** Spawn with `run_in_background: false`. Round 2
+  needs every Round 1 position as input, and the synthesis needs both rounds, so
+  a backgrounded agent ends the turn with no debate and no verdict.
+- **DO put every spawn for a round in ONE message**, as multiple tool calls.
+  Rounds are sequential; the spawns inside a round are not.
+
 ## Step 1: Define Perspectives
 
 Choose 3-5 perspectives relevant to the topic. Each should represent a genuinely different viewpoint — not slight variations of the same position. Examples:
@@ -40,5 +70,7 @@ As the orchestrating agent, synthesize the debate:
 ## Important
 
 - All subagent spawns per round MUST be in a **single message** for parallel execution
+- Spawn with `run_in_background: false`. Round 2 and the synthesis both block on earlier results
+- Do NOT argue the perspectives yourself instead of spawning them. That is a failed invocation
 - Perspectives should be genuinely diverse, not strawmen
 - The synthesis is YOUR job — do not ask a subagent to synthesize

package/assets/skills/create-pdf/SKILL.md

@@ -1,7 +1,20 @@
 ---
 name: create-pdf
+license: MIT
 description: "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."
 argument-hint: <file paths, glob pattern, or directory containing .md files>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "create-pdf"
+    - "create pdf"
+    - "create a pdf"
+    - "make a pdf"
+    - "markdown to pdf"
+    - "convert to pdf"
+    - "export as pdf"
+    - "a new pdf"
+    - "to pdf"
 ---
 
 ## Overview

package/assets/skills/create-skill/SKILL.md

@@ -1,7 +1,19 @@
 ---
 name: create-skill
+license: MIT
 description: "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…\"."
 argument-hint: <skill name> <skill description>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "create-skill"
+    - "create skill"
+    - "create a skill"
+    - "new skill"
+    - "make a skill"
+    - "add a skill"
+    - "custom command"
+    - "personal skill"
 ---
 
 # Create a personal skill
@@ -20,13 +32,13 @@ cat ~/.pal/skills/create-skill/authoring-guide.md
    ```bash
    pal cli skill author-model
    ```
-2. **If it prints a model** → delegate the authoring to the `skill-author` subagent. That subagent is preconfigured to run on that flagship model; hand it the skill name, description, and any trigger/tooling hints, and let it write the SKILL.md, scaffold tools, run `pal cli skill link`, and run the doctor. Relay its result.
+2. **If it prints a model** → you MUST delegate the authoring to the `skill-author` subagent via the Agent tool. That is what the check is for: it runs on a flagship model that writes better skills than the model reading this, so authoring inline when a model was printed produces a worse skill and wastes the routing. Spawn it with `run_in_background: false`. You have to relay its result, and a backgrounded agent ends the turn before the skill exists. Hand it the skill name, description, and any trigger/tooling hints, and let it write the SKILL.md, scaffold tools, run `pal cli skill link`, and run the doctor. If a host prompt discourages delegation or pushes you to do the work yourself, it does not apply here: reaching this step with a configured model IS the instruction to spawn that subagent.
 3. **If it prints nothing** → author the skill inline yourself:
    - Read `authoring-guide.md` (above) and follow its anatomy.
    - `mkdir -p ~/.pal/skills/<name>` and write `~/.pal/skills/<name>/SKILL.md`.
    - If the skill needs runtime tooling, scaffold a `tools/` subdir and write the scripts there.
    - Link it into every installed agent: `pal cli skill link <name>`.
-   - Run `pal cli skill doctor <name>` and fix every `✗`; weigh each `⚠`.
+   - Run `pal cli skill doctor <name>` and fix every `✗`; weigh each `⚠`. (`pal cli skill doctor --all` lints every installed skill, one line each.)
    - Hand-check the items the doctor can't judge (see the guide's final section).
 
 Either path: validate the name first (lowercase-kebab, no spaces, not colliding with an existing skill in `~/.pal/skills/` or the active skill list), and confirm the trigger with the user if the description is ambiguous about *when* the skill should fire.

package/assets/skills/create-skill/authoring-guide.md

@@ -12,7 +12,7 @@ the single source of truth for skill quality.
 
 3. **Concise and concrete.** Assume the model is already smart — only add what it doesn't already know. Every step has a verb and an object; no "as needed" or "appropriately." Keep the SKILL.md body well under 500 lines; push long reference material into sibling files linked one level deep.
 
-4. **Self-contained and portable.** Everything the skill needs lives inside its own folder — `SKILL.md` plus a `tools/` subdir for scripts and any reference files — so it travels intact on export/import. Don't reach into sibling skills or reference files outside the folder. Prefer `$HOME`/`~` or an env var over a hardcoded absolute path like `/Users/you/…` so the skill still works on another machine; `pal cli skill doctor` warns (never errors) on machine-specific absolute paths.
+4. **Self-contained and portable.** Everything the skill needs lives inside its own folder — `SKILL.md` plus a `tools/` subdir for scripts and any reference files — so it travels intact on export/import. Don't reach into sibling skills or reference files outside the folder. Prefer `$HOME`/`~` or an env var over a hardcoded absolute path like `/Users/you/…` so the skill still works on another machine; `pal cli skill doctor` warns (never errors) on machine-specific absolute paths; `pal cli skill doctor --all` lints every installed skill at once, one line each.
 
 A personal skill **may** contain this user's own context — their paths, project names, preferences, conventions. That is the point of a personal skill; portability (rule 4) is a preference, not a hard rule — a deliberate machine-specific mount is fine.
 
@@ -23,6 +23,11 @@ A personal skill **may** contain this user's own context — their paths, projec
 name: <slug>                           # the slash-command name; lowercase-kebab
 description: <what it does + WHEN to invoke>   # the dispatcher matches on this
 argument-hint: <args>                  # optional; how the user passes input
+metadata:                              # free-form map; the only key Anthropic's
+  triggers:                            # spec reserves for third-party tooling
+    - "<skill-name>"                   # always first
+    - "<skill name>"                   # always second, hyphens as spaces
+    - "<word or phrase a prompt would contain>"
 ---
 
 ## Overview / Workflow
@@ -40,6 +45,10 @@ Two short lists; the "do not" list disambiguates this skill from neighbours.
 
 The `description` should state **both what the skill does and when to invoke it**, in third person, with the trigger terms a model would match on. A vague description ("helps with documents") will not trigger reliably.
 
+`metadata.triggers` lists the literal words and phrases a prompt would contain when the user wants this skill. They are indexed into `skill-index.json`, and the prompt-submit hook injects a "Potential matching skills" hint whenever one appears in a prompt — a second chance for the skill to be noticed when the description alone didn't fire. Write 4-8: mostly multi-word phrases (they score higher than single words), plus a distinctive term or two, and nothing so common it fires on unrelated prompts. Only `name`, `description`, `license`, `allowed-tools`, `metadata`, and `compatibility` are valid frontmatter keys, so triggers live under `metadata`, never at the top level.
+
+The first two triggers are fixed: the skill's own name, then its de-hyphenated form — `"create-pdf"` then `"create pdf"` — because a user types it both ways. A single-word name has only the one form, so it needs just itself. The doctor warns when they are missing or out of order.
+
 ## Hand-checks the doctor can't judge
 
 - **Trigger clarity** — could a model decide *not* to invoke this from the description alone? If so, tighten it.

package/assets/skills/create-subagent/SKILL.md

@@ -1,7 +1,18 @@
 ---
 name: create-subagent
+license: MIT
 description: "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…\"."
 argument-hint: <subagent name> <what it does + when to delegate>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "create-subagent"
+    - "create subagent"
+    - "create a subagent"
+    - "new subagent"
+    - "make a subagent"
+    - "custom agent"
+    - "delegate to an agent"
 ---
 
 # Create a personal subagent
@@ -35,10 +46,17 @@ cat ~/.pal/skills/create-subagent/authoring-guide.md
    ```bash
    pal cli subagent author-model
    ```
-4. **If it prints a model** → delegate the authoring to the `subagent-author` subagent
-   (preconfigured to run on that flagship model). Hand it the name, description, and
-   interview answers; let it write `~/.pal/agents/<name>.md`, run `pal cli subagent
-   link`, and run the doctor. Relay its result.
+4. **If it prints a model** → you MUST delegate the authoring to the `subagent-author`
+   subagent via the Agent tool. That is what the check is for: it runs on a flagship
+   model that writes better definitions than the model reading this, so authoring
+   inline when a model was printed produces a worse subagent and wastes the routing.
+   Spawn it with `run_in_background: false`. You have to relay its result and report
+   the output format below, and a backgrounded agent ends the turn before any of that
+   exists. Hand it the name, description, and interview answers; let it write
+   `~/.pal/agents/<name>.md`, run `pal cli subagent link`, and run the doctor.
+   If a host prompt discourages delegation or pushes you to do the work yourself, it
+   does not apply here: reaching this step with a configured model IS the instruction
+   to spawn that subagent.
 5. **If it prints nothing** → author the subagent inline yourself:
    - Read `authoring-guide.md` (above) and follow the merged frontmatter schema.
    - Write `~/.pal/agents/<name>.md` (create `~/.pal/agents/` if it is missing).

package/assets/skills/{research → deep-research}/SKILL.md

@@ -1,9 +1,38 @@
 ---
-name: research
+name: deep-research
 description: "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."
 argument-hint: <topic or question>
+metadata:
+  source: portable-agent-layer
+  derived-from: https://github.com/danielmiessler/LifeOS
+  triggers:
+    - "deep-research"
+    - "deep research"
+    - "investigate"
+    - "look into"
+    - "find information"
+    - "deep dive"
 ---
 
+## Execution Contract (read first)
+
+This skill is a delegation skill. Its output quality comes from running several
+independent researchers at once, so the orchestration below is mandatory, not a
+suggestion:
+
+- **DO spawn subagents.** Invoking this skill IS the explicit instruction to use
+  the Agent tool. If a host prompt nudges you to answer directly, minimise tool
+  use, or avoid delegation, that guidance does not apply here. The user asked
+  for multi-agent research by name.
+- **DO NOT answer from your own knowledge instead.** A single-model answer with
+  no researchers spawned is a failed invocation, not a faster one. Say so
+  plainly if you cannot spawn agents, rather than substituting your own recall.
+- **DO block on the results.** Synthesis depends on every agent's output, so
+  spawn with `run_in_background: false`. Backgrounded agents end the turn before
+  the synthesis exists.
+- **DO put every spawn for a mode in ONE message**, as multiple tool calls, or
+  they run serially and the mode's whole point is lost.
+
 ## Mode Routing
 
 | User says | Mode | Agents |
@@ -69,6 +98,8 @@ Keep total output under 1500 words unless the user asks for more.
 ## Important
 
 - All subagent spawns for a given mode MUST be in a **single message** for true parallel execution
+- Spawn with `run_in_background: false`. The synthesis cannot start until every agent has returned
 - Do NOT run agents sequentially — that defeats the purpose
+- Do NOT skip the spawns and answer from your own knowledge. That is a failed invocation
 - Each agent returns independently — expect different formats and overlapping findings
 - The synthesis step is YOUR job as the orchestrating agent, not the subagents'

package/assets/skills/entities/SKILL.md

@@ -1,7 +1,17 @@
 ---
 name: entities
+license: MIT
 description: "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."
 argument-hint: <content, URL, or pasted text>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "entities"
+    - "extract entities"
+    - "knowledge graph"
+    - "who is"
+    - "company profile"
+    - "people and companies"
 ---
 
 Detect, persist, and query people and companies referenced in $ARGUMENTS.

package/assets/skills/extract-wisdom/SKILL.md

@@ -2,6 +2,18 @@
 name: extract-wisdom
 description: "Extract structured insights from content (articles, videos, podcasts). Use when extracting wisdom, key takeaways, or structured insights from any content."
 argument-hint: <content or URL>
+metadata:
+  source: portable-agent-layer
+  derived-from: https://github.com/danielmiessler/LifeOS
+  triggers:
+    - "extract-wisdom"
+    - "extract wisdom"
+    - "key takeaways"
+    - "insights from"
+    - "distill"
+    - "takeaways from this"
+    - "remember this"
+    - "note this"
 ---
 
 Extract structured insights from $ARGUMENTS:

package/assets/skills/first-principles/SKILL.md

@@ -2,6 +2,14 @@
 name: first-principles
 description: "Break down a problem to its fundamental constraints and build up a solution. Use when decomposing complexity, challenging assumptions, or finding root causes."
 argument-hint: <problem>
+metadata:
+  source: portable-agent-layer
+  derived-from: https://github.com/danielmiessler/LifeOS
+  triggers:
+    - "first-principles"
+    - "first principles"
+    - "root cause"
+    - "break it down"
 ---
 
 Break down $ARGUMENTS to fundamentals:

package/assets/skills/frontend-design/SKILL.md

@@ -2,6 +2,20 @@
 name: frontend-design
 description: "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."
 license: Complete terms in LICENSE.txt
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "frontend-design"
+    - "frontend design"
+    - "landing page"
+    - "ui design"
+    - "react component"
+    - "tailwind"
+    - "web page"
+    - "dashboard ui"
+    - "css layout"
+    - "design a"
+    - "shadcn"
 ---
 
 This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.

package/assets/skills/fyzz-chat-api/SKILL.md

@@ -1,7 +1,17 @@
 ---
 name: fyzz-chat-api
+license: MIT
 description: "Query Fyzz Chat conversations and projects via the REST API. Use when looking up conversations, searching chat history, or listing projects in Fyzz Chat."
 argument-hint: <conversations|projects> [options]
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "fyzz-chat-api"
+    - "fyzz chat api"
+    - "fyzz chat"
+    - "chat history"
+    - "fyzz conversation"
+    - "fyzz convo"
 ---
 
 When you need to access the user's Fyzz Chat conversations or projects, use the `fyzz-api` CLI tool. The tool reads the API key from the `PAL_FYZZ_API_KEY` environment variable automatically — never attempt to read, print, or reference the API key or the env var directly.

package/assets/skills/humanize/SKILL.md

@@ -1,7 +1,19 @@
 ---
 name: humanize
+license: MIT
 description: "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."
 argument-hint: <text, or a file path, or empty to rewrite the previous message>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "humanize"
+    - "ai slop"
+    - "em dash"
+    - "emdash"
+    - "sound human"
+    - "de-slop"
+    - "remove ai tells"
+    - "less robotic"
 ---
 
 # Humanize
@@ -65,6 +77,6 @@ Return, in order:
 
 ## Do NOT use
 
-- To condense or shorten content: that is `summarize`. Humanize preserves length and structure.
+- To condense or shorten content. Humanize preserves length and structure.
 - To pull insights, quotes, or ideas out of content: that is `extract-wisdom`. Humanize returns the whole text, rewritten in place.
 - To change the argument, add claims, or restructure a document. Humanize changes wording, never meaning.

package/assets/skills/opinion/SKILL.md

@@ -1,6 +1,17 @@
 ---
 name: opinion
+license: MIT
 description: "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."
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "opinion"
+    - "keep doing that"
+    - "stop doing that"
+    - "never do that"
+    - "yes exactly"
+    - "stop doing that"
+    - "my preference"
 ---
 
 # Opinion Tracker

package/assets/skills/pal-analyze/SKILL.md

@@ -1,7 +1,18 @@
 ---
 name: pal-analyze
+license: MIT
 description: "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."
 argument-hint: [optional: --actionable for AI-generated recommendations]
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "pal-analyze"
+    - "pal analyze"
+    - "learning analysis"
+    - "rating trends"
+    - "failure patterns"
+    - "low ratings"
+    - "what to improve"
 ---
 
 When `/pal-analyze` is invoked (by you in response to a nudge, or by the user directly):

package/assets/skills/pal-reflect/SKILL.md

@@ -1,7 +1,17 @@
 ---
 name: pal-reflect
+license: MIT
 description: "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."
 argument-hint: [optional: --dry-run to preview without writing]
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "pal-reflect"
+    - "pal reflect"
+    - "relationship reflect"
+    - "behavioral observations"
+    - "tracked opinions"
+    - "patterns observed"
 ---
 
 When `/pal-reflect` is invoked (by you in response to a nudge, or by the user directly):

package/assets/skills/playwright/SKILL.md

@@ -1,7 +1,20 @@
 ---
 name: playwright
+license: MIT
 description: "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."
 argument-hint: <url> [--viewport WxH] [--full-page] [--selector <css>]
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "playwright"
+    - "screenshot"
+    - "check visually"
+    - "look at the design"
+    - "look at this"
+    - "check yourself"
+    - "verify the layout"
+    - "responsive"
+    - "browser check"
 ---
 
 ## Overview

package/assets/skills/presentation/SKILL.md

@@ -1,7 +1,19 @@
 ---
 name: presentation
+license: MIT
 description: "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."
 argument-hint: <deck-dir> to build, OR `setup-template` to add a brand template, OR `new <deck-dir> --template <name>` to scaffold a deck, OR `list-templates`
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "presentation"
+    - "slide deck"
+    - "slides"
+    - "pitch deck"
+    - "reveal.js"
+    - "workshop deck"
+    - "talk slides"
+    - "ppt"
 ---
 
 ## Overview

package/assets/skills/projects/SKILL.md

@@ -1,7 +1,23 @@
 ---
 name: projects
+license: MIT
 description: "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."
 argument-hint: [list | create | resume | add-next | add-blocker | add-decision | add-handoff | update-section | criteria | isa-init | complete | archive | pause]
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "projects"
+    - "isc"
+    - "isa"
+    - "my projects"
+    - "what am i working on"
+    - "my priorities"
+    - "track this"
+    - "resume the project"
+    - "resume project"
+    - "where are we"
+    - "open ticket"
+    - "open iscs"
 ---
 
 Manage the user's project registry. Each project lives at `~/.pal/memory/projects/{slug}/ISA.md`. Frontmatter holds operational state (next steps, blockers, handoff); the body holds ISA spec sections (Problem, Goal, Criteria, Context, Decisions, etc.). The Stop hook auto-touches `updated` whenever the cwd resolves into a registered project — just *being* in the project keeps it warm.

package/assets/skills/reflect/SKILL.md

@@ -1,7 +1,20 @@
 ---
 name: reflect
+license: MIT
 description: "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."
 argument-hint: <what went wrong>
+metadata:
+  source: portable-agent-layer
+  triggers:
+    - "reflect"
+    - "didn't fire"
+    - "didn't trigger"
+    - "didn't run"
+    - "why didn't"
+    - "not triggering"
+    - "never fired"
+    - "should have fired"
+    - "behaved unexpectedly"
 ---
 
 When the user invokes `/reflect [optional: description of what didn't happen]`:

package/assets/skills/telos/SKILL.md

@@ -2,6 +2,18 @@
 name: telos
 description: "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."
 argument-hint: [area to view or update]
+metadata:
+  source: portable-agent-layer
+  derived-from: https://github.com/danielmiessler/LifeOS
+  triggers:
+    - "telos"
+    - "my goals"
+    - "my beliefs"
+    - "my mission"
+    - "life context"
+    - "current challenges"
+    - "what do i believe"
+    - "my strategies"
 ---
 
 Manage the user's TELOS files — from Greek τέλος (télos), meaning end/purpose/goal. The persistent personal context that orients PAL around who the user is and what they're working toward.

package/assets/skills/think/SKILL.md

@@ -2,6 +2,15 @@
 name: think
 description: "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."
 argument-hint: <question or topic>
+metadata:
+  source: portable-agent-layer
+  derived-from: https://github.com/danielmiessler/LifeOS
+  triggers:
+    - "think"
+    - "brainstorm"
+    - "analyze deeply"
+    - "think about this"
+    - "mental model"
 ---
 
 Route $ARGUMENTS to the right thinking mode based on intent. Detect the mode from context — do NOT ask.