@forwardimpact/outpost 3.0.3

package/templates/.claude/skills/meeting-prep/SKILL.md

@@ -0,0 +1,180 @@
+---
+name: meeting-prep
+description: Prepare for meetings by gathering context from the knowledge base and calendar. Use when the user asks to prep for a meeting or wants a briefing on upcoming meetings. Creates personalized briefings with attendee history, open items, and suggested talking points.
+---
+
+# Meeting Prep
+
+Help the user prepare for meetings by gathering context from the knowledge base
+and calendar. Creates personalized briefing documents with attendee history,
+open items, and suggested talking points.
+
+## Trigger
+
+Run when the user asks to prep for a meeting, or wants a briefing on upcoming
+meetings.
+
+## Prerequisites
+
+- Calendar data synced in `~/.cache/fit/outpost/apple_calendar/`
+- Knowledge base populated (from `extract-entities` skill)
+
+## Inputs
+
+- `~/.cache/fit/outpost/apple_calendar/*.json` — calendar events
+- `knowledge/People/*.md` — attendee context
+- `knowledge/Organizations/*.md` — company context
+- `knowledge/Projects/*.md` — project context
+- `knowledge/Goals/*.md` — active goals relevant to the meeting topic
+- `knowledge/Priorities/*.md` — strategic context for framing
+- `knowledge/Candidates/*/brief.md` — candidate context (for interview meetings)
+- `knowledge/Roles/*.md` — role/requisition context (for interview meetings)
+
+## Outputs
+
+- Meeting brief printed to the user (not saved to a file)
+
+---
+
+## Critical: Always Look Up Context First
+
+**BEFORE creating any meeting brief, you MUST look up the attendees in the
+knowledge base.**
+
+When the user asks to prep for a meeting:
+
+1. **STOP** — Do not create a generic brief
+2. **SEARCH** — Look up each attendee: `rg -l "Attendee Name" knowledge/`
+3. **READ** — Read their notes: `cat "knowledge/People/Attendee Name.md"`
+4. **UNDERSTAND** — Extract role, organization, history, open items
+5. **THEN BRIEF** — Create the meeting brief using this context
+
+## Key Principles
+
+**Ask, don't guess:**
+
+- If unclear which meeting, ASK
+- If multiple upcoming meetings, offer choices
+- **WRONG:** "Here's a generic meeting prep template"
+- **RIGHT:** "I see meetings with Sarah (2pm) and John (4pm). Which one?"
+
+**Be thorough, not generic:**
+
+- Include specific history, open items, and context from knowledge base
+- Reference actual past interactions and commitments
+
+## Processing Flow
+
+### Step 1: Identify the Meeting
+
+Use the calendar query script to find upcoming meetings:
+
+```bash
+# Next 2 hours of meetings as JSON
+node .claude/skills/sync-apple-calendar/scripts/query.mjs --upcoming 2h --json
+
+# Today's full schedule
+node .claude/skills/sync-apple-calendar/scripts/query.mjs --today
+```
+
+If "prep me for my next meeting":
+
+- Query upcoming events with `--upcoming 2h`
+- Find the next meeting with external attendees
+- Confirm with user if unclear
+
+### Step 2: Parse Calendar Event
+
+Extract: summary, start/end time, attendees (names and emails), description.
+
+### Step 3: Gather Context from Knowledge Base
+
+For each attendee:
+
+```bash
+rg -l "attendee_name" knowledge/People/
+rg -l "attendee_email" knowledge/People/
+cat "knowledge/People/Attendee Name.md"
+cat "knowledge/Organizations/Their Company.md"
+rg -l "attendee_name" knowledge/Projects/
+```
+
+Extract: role/title, company, key facts, previous interactions, open items.
+
+Also check `knowledge/Goals/` and `knowledge/Priorities/` for context relevant
+to the meeting topic — e.g. if the meeting is about hiring, surface the relevant
+hiring Goal's status and progress.
+
+### Step 4: Create Meeting Brief
+
+Format:
+
+```markdown
+Meeting Brief: {Attendee Name}
+{Time} today / {Company}
+
+About {First Name}
+{Role at company}. {Key background — 1-2 sentences}. {What they focus on}.
+
+Your History
+- {Date}: {Brief description of interaction/outcome}
+- {Date}: {Brief description}
+- {Date}: {Brief description}
+
+Open Items
+- {Action item} (they asked {date})
+- {Action item}
+
+Suggested Talking Points
+- {Concrete suggestion based on history}
+- {Reference relevant entities with [[wiki-links]]}
+```
+
+**Guidelines:**
+
+- Use `[[Name]]` wiki-link syntax for cross-references
+- Keep "About" section to 2-3 sentences max
+- History: reverse chronological, 3-5 most relevant items
+- Talking points: concrete, not generic
+- If no notes exist for a person, mention that and offer to create one
+
+### Interview Meeting Context
+
+When preparing for interview meetings (title contains "Interview", "Screening",
+"Decomposition", "Panel", or a candidate name from `knowledge/Candidates/`):
+
+1. **Read the candidate brief:** `knowledge/Candidates/{Name}/brief.md`
+2. **Read the Role file:** Look up the `Req` field and read the corresponding
+   `knowledge/Roles/*.md` file.
+3. **Include in the briefing:**
+   - Candidate's current status, skills, and screening recommendation
+   - Role context: hiring manager, domain lead, remaining positions
+   - Other candidates on the same requisition and their statuses (from the Role
+     file's Candidates table)
+   - Previous interview assessments if this is a second/later stage
+   - Panel brief if one exists (`panel.md`)
+4. **Format as a dedicated section:**
+
+```markdown
+## Candidate: {Name}
+**Role:** {Title from Role file} | **Req:** {req number}
+**Hiring manager:** {name} | **Domain lead:** {name}
+**Status:** {current pipeline status}
+**Screening:** {Interview / Interview with focus areas / Pass}
+
+### Pipeline for this req
+- {N} candidates total, {N} interviewed, {N} remaining positions
+
+### Key strengths
+- {from screening.md}
+
+### Focus areas for this interview
+- {from screening.md or panel.md}
+```
+
+## Constraints
+
+- Only prep for meetings with external attendees
+- Skip internal calendar blocks (DND, Focus Time, Lunch)
+- For meetings with multiple attendees, create sections for each key person
+- Prioritize recent interactions (last 30 days)

package/templates/.claude/skills/organize-files/SKILL.md

@@ -0,0 +1,146 @@
+---
+name: organize-files
+description: Organize, tidy up, and find files in ~/Desktop/ and ~/Downloads/. Use when the user asks to find, organize, clean up, or tidy files on their Mac. Always previews changes before acting and never deletes without explicit confirmation. Extracts entities from document files using the extract-entities skill.
+compatibility: Requires macOS filesystem access
+---
+
+# Organize Files
+
+Organize, tidy up, and find files in `~/Desktop/` and `~/Downloads/`. Always
+previews changes before acting and never deletes without explicit confirmation.
+
+After organizing, extract entities from document files by invoking the
+**`extract-entities`** skill.
+
+## Trigger
+
+Run when the user asks to find, organize, clean up, or tidy files on their Mac.
+
+## Prerequisites
+
+- macOS filesystem access
+
+## Inputs
+
+- User's description of what to organize or find
+- Source directories: `~/Desktop/` and `~/Downloads/`
+
+## Outputs
+
+- Organized files moved to logical subdirectories within `~/Desktop/` and
+  `~/Downloads/`
+- Entity extraction triggered on document files via the **`extract-entities`**
+  skill
+- Summary of actions taken
+
+---
+
+## Core Capabilities
+
+1. **Find files** — Locate files by name, type, or content in `~/Desktop/` and
+   `~/Downloads/`
+2. **Organize files** — Move files into logical subfolders
+3. **Tidy up** — Clean up cluttered `~/Desktop/` and `~/Downloads/`
+4. **Create structure** — Set up folder hierarchies
+5. **Extract entities** — After organizing, invoke the **`extract-entities`**
+   skill on document files to populate the knowledge graph
+
+## Key Principles
+
+**Always preview before acting:**
+
+- Show what files will be affected BEFORE moving/deleting
+- List proposed changes and ask for confirmation
+
+**Be conservative with destructive operations:**
+
+- Never delete without explicit confirmation
+- Prefer moving to a "to-review" folder over deleting
+
+## Summarizing Contents
+
+Get an overview of both directories:
+
+    node scripts/summarize.mjs
+
+## Finding Files
+
+```bash
+find ~/Downloads -maxdepth 1 -name "*.pdf" -type f
+find ~/Desktop -maxdepth 1 -iname "*AI*" -type f
+find ~/Desktop -maxdepth 1 -type f \( -name "*.png" -o -name "*.jpg" \)
+find ~/Downloads -maxdepth 1 -type f -mtime -7     # last 7 days
+find ~/Downloads -maxdepth 1 -type f -mtime +30    # older than 30 days
+find ~/Desktop -maxdepth 1 \( -name "Screenshot*" -o -name "Screen Shot*" \)
+```
+
+## Organizing by File Type
+
+Organize a directory into type-based subdirectories (Documents, Images,
+Archives, Installers, Screenshots):
+
+    node scripts/organize-by-type.mjs ~/Downloads
+    node scripts/organize-by-type.mjs ~/Desktop
+
+The script creates subdirectories and moves matching files. It does NOT delete
+anything.
+
+## Entity Extraction
+
+After organizing files, identify document files that may contain entity
+information (people, organizations, projects, topics) and invoke the
+**`extract-entities`** skill to process them.
+
+### Which files to send for extraction
+
+**Include:** `.pdf`, `.txt`, `.md`, `.rtf`, `.doc`, `.docx`, `.csv`, `.xlsx`
+
+**Exclude:** Images, installers, archives, media, system files
+
+### How to invoke
+
+After organizing, collect the paths of document files and invoke the
+**`extract-entities`** skill, passing the file paths as ad-hoc file inputs.
+
+## Output Format
+
+**Plan:**
+
+```
+Organization Plan: Desktop & Downloads Cleanup
+
+Found 47 files to organize:
+- 23 screenshots → ~/Desktop/Screenshots/
+- 12 PDFs → ~/Downloads/Documents/
+- 8 images → ~/Downloads/Images/
+- 4 DMGs → ~/Downloads/Installers/
+
+Document files for entity extraction: 12
+→ Will invoke extract-entities skill after organizing
+
+Should I proceed?
+```
+
+**Results:**
+
+```
+Organization Complete
+
+Moved 47 files:
+- 23 screenshots to ~/Desktop/Screenshots/
+- 12 PDFs to ~/Downloads/Documents/
+- 8 images to ~/Downloads/Images/
+- 4 DMGs to ~/Downloads/Installers/
+
+Entity extraction: invoked extract-entities on 12 document files
+```
+
+## Safety Rules
+
+1. **Never delete without permission** — "cleanup" means organize, not delete
+2. **Don't touch system folders** — /System, /Library, /Applications
+3. **Don't touch hidden files** — files starting with `.` unless asked
+4. **Limit scope** — only operate on `~/Desktop/` and `~/Downloads/`
+5. **Limit depth** — use `-maxdepth 1` unless user wants recursive
+6. **Show before doing** — always preview first
+7. **Quote paths** — handle spaces: `"$HOME/My Documents"`

package/templates/.claude/skills/organize-files/scripts/organize-by-type.mjs

@@ -0,0 +1,105 @@
+#!/usr/bin/env bun
+/**
+ * Organize files in a directory by type into subdirectories.
+ *
+ * Scans the top level of the given directory and moves files into category
+ * subdirectories: Screenshots, Documents, Images, Archives, and Installers.
+ * Categories are determined by file extension and name prefix. Files that do
+ * not match any category are left in place. Does NOT delete anything.
+ */
+
+import {
+  existsSync,
+  mkdirSync,
+  readdirSync,
+  renameSync,
+  statSync,
+} from "node:fs";
+import { extname, join } from "node:path";
+
+const HELP = `organize-by-type — sort files into type-based subdirectories
+
+Usage: node scripts/organize-by-type.mjs <directory> [-h|--help]
+
+Creates subdirectories (Documents, Images, Archives, Installers, Screenshots)
+and moves matching top-level files into them. Does NOT delete any files.`;
+
+if (process.argv.includes("-h") || process.argv.includes("--help")) {
+  console.log(HELP);
+  process.exit(0);
+}
+
+const CATEGORIES = [
+  {
+    name: "Screenshots",
+    test: (name) =>
+      name.startsWith("Screenshot") || name.startsWith("Screen Shot"),
+  },
+  {
+    name: "Documents",
+    test: (_name, ext) =>
+      [
+        ".pdf",
+        ".doc",
+        ".docx",
+        ".txt",
+        ".md",
+        ".rtf",
+        ".csv",
+        ".xlsx",
+      ].includes(ext),
+  },
+  {
+    name: "Images",
+    test: (_name, ext) =>
+      [".png", ".jpg", ".jpeg", ".gif", ".webp"].includes(ext),
+  },
+  {
+    name: "Archives",
+    test: (name, ext) =>
+      [".zip", ".rar"].includes(ext) || name.endsWith(".tar.gz"),
+  },
+  {
+    name: "Installers",
+    test: (_name, ext) => ext === ".dmg",
+  },
+];
+
+function main() {
+  const dir = process.argv[2];
+  if (!dir) {
+    console.error("Usage: node scripts/organize-by-type.mjs <directory>");
+    process.exit(1);
+  }
+  if (!existsSync(dir) || !statSync(dir).isDirectory()) {
+    console.error(`Error: Directory not found: ${dir}`);
+    process.exit(1);
+  }
+
+  // Create subdirectories
+  for (const cat of CATEGORIES) {
+    mkdirSync(join(dir, cat.name), { recursive: true });
+  }
+
+  let moved = 0;
+  for (const name of readdirSync(dir)) {
+    const fullPath = join(dir, name);
+    const stat = statSync(fullPath, { throwIfNoEntry: false });
+    if (!stat || !stat.isFile()) continue;
+
+    const ext = extname(name).toLowerCase();
+    for (const cat of CATEGORIES) {
+      if (cat.test(name, ext)) {
+        const dest = join(dir, cat.name, name);
+        renameSync(fullPath, dest);
+        console.log(`${name} -> ${cat.name}/`);
+        moved++;
+        break;
+      }
+    }
+  }
+
+  console.log(`\nOrganization complete: ${dir} (${moved} files moved)`);
+}
+
+main();

package/templates/.claude/skills/organize-files/scripts/summarize.mjs

@@ -0,0 +1,91 @@
+#!/usr/bin/env bun
+/**
+ * Summarize the contents of ~/Desktop/ and ~/Downloads/.
+ *
+ * Counts top-level files in both directories by type (Screenshots, PDFs,
+ * Images, Documents, Archives, Installers, Other) and prints a human-readable
+ * table for each. Used by the organize-files skill to preview directory
+ * contents before organizing.
+ */
+
+import { existsSync, readdirSync, statSync } from "node:fs";
+import { extname, join } from "node:path";
+import { homedir } from "node:os";
+
+const HELP = `summarize — count files by type in ~/Desktop/ and ~/Downloads/
+
+Usage: node scripts/summarize.mjs [-h|--help]
+
+Prints a summary of file types found at the top level of each directory.`;
+
+if (process.argv.includes("-h") || process.argv.includes("--help")) {
+  console.log(HELP);
+  process.exit(0);
+}
+
+const HOME = homedir();
+
+const IMAGE_EXTS = new Set([".png", ".jpg", ".jpeg", ".gif", ".webp"]);
+const DOC_EXTS = new Set([
+  ".doc",
+  ".docx",
+  ".txt",
+  ".md",
+  ".rtf",
+  ".csv",
+  ".xlsx",
+]);
+const ARCHIVE_EXTS = new Set([".zip", ".rar"]);
+
+function classifyFile(name, ext) {
+  if (name.startsWith("Screenshot") || name.startsWith("Screen Shot"))
+    return "Screenshots";
+  if (ext === ".pdf") return "PDFs";
+  if (IMAGE_EXTS.has(ext)) return "Images";
+  if (DOC_EXTS.has(ext)) return "Documents";
+  if (ARCHIVE_EXTS.has(ext) || name.endsWith(".tar.gz")) return "Archives";
+  if (ext === ".dmg") return "Installers";
+  return "Other";
+}
+
+function countFiles(dir) {
+  if (!existsSync(dir)) return null;
+
+  const counts = {
+    Screenshots: 0,
+    PDFs: 0,
+    Images: 0,
+    Documents: 0,
+    Archives: 0,
+    Installers: 0,
+    Other: 0,
+  };
+
+  for (const name of readdirSync(dir)) {
+    const fullPath = join(dir, name);
+    const stat = statSync(fullPath, { throwIfNoEntry: false });
+    if (!stat || !stat.isFile()) continue;
+    if (name.startsWith(".")) continue;
+
+    const category = classifyFile(name, extname(name).toLowerCase());
+    counts[category]++;
+  }
+
+  return counts;
+}
+
+function main() {
+  for (const dirName of ["Desktop", "Downloads"]) {
+    const dir = join(HOME, dirName);
+    const counts = countFiles(dir);
+    if (!counts) continue;
+
+    console.log(`=== ${dirName} ===`);
+    for (const [label, count] of Object.entries(counts)) {
+      console.log(`${label.padEnd(12)} ${count}`);
+    }
+    console.log("");
+  }
+}
+
+main();

package/templates/.claude/skills/req-assess/SKILL.md

@@ -0,0 +1,137 @@
+---
+name: req-assess
+description: >
+  Analyze interview transcripts against the agent-aligned engineering standard,
+  updating skill and behaviour ratings with observed evidence. Produces
+  per-interview assessments and panel briefs for subsequent interview stages.
+  Use when transcript files appear in a candidate's folder.
+---
+
+# Assess Interview
+
+Analyze a candidate's interview transcripts. Update their skill and behaviour
+profile with **observed** (not claimed) evidence. Interview evidence is
+higher-fidelity than CV evidence — it confirms or contradicts the screening
+assessment.
+
+This is **Stage 2** of the three-stage hiring pipeline:
+
+1. `req-screen` — CV → interview or pass.
+2. **Assess interview** (this skill) — transcript → updated profile.
+3. `req-decide` — all stages complete → hire / no hire.
+
+## Trigger
+
+- A new `transcript-*.md` file appears in `knowledge/Candidates/{Name}/`.
+- The user asks to analyze an interview or debrief.
+- The user asks to prepare a panel brief.
+- The concierge agent processes a Hyprnote interview recording.
+
+## Prerequisites
+
+- `fit-pathway` CLI installed.
+- At least one transcript in `knowledge/Candidates/{Name}/`.
+- `screening.md` should exist; if missing, run `req-screen` first (proceed
+  regardless).
+
+## Inputs
+
+- `knowledge/Candidates/{Name}/transcript-{date}.md`.
+- `knowledge/Candidates/{Name}/screening.md`.
+- `knowledge/Candidates/{Name}/brief.md` — target role.
+
+## Outputs
+
+- `knowledge/Candidates/{Name}/interview-{date}.md`.
+- `knowledge/Candidates/{Name}/panel.md` — only when more interviews are
+  planned.
+- Updated `knowledge/Candidates/{Name}/brief.md`.
+
+<do_confirm_checklist goal="Verify the assessment is grounded in transcript
+evidence">
+
+- [ ] Every skill re-rating cites a specific moment from the transcript.
+- [ ] Behaviour assessments reference observed actions, not claimed traits.
+- [ ] Level assessment uses standard progression criteria, not gut feel.
+- [ ] Interviewer observations are attributed by name.
+- [ ] Confirmed strengths and new concerns are distinguished.
+- [ ] Panel brief (if created) is written for non-technical readers and ties
+      suggested questions to remaining gaps.
+- [ ] Brief's Pipeline section, links, and Status are updated.
+- [ ] Gender field is **not** updated from interview observations.
+
+</do_confirm_checklist>
+
+## Procedure
+
+### 1. Read the transcript(s)
+
+Extract the fields listed in
+[references/rubric.md](references/rubric.md#what-to-extract-from-the-transcript).
+
+### 2. Load the standard reference
+
+Use the role recorded in `screening.md` or `brief.md`:
+
+```bash
+bunx fit-pathway job {discipline} {level} --track={track}
+bunx fit-pathway skill {skill_id}
+bunx fit-pathway behaviour --list
+```
+
+If screening recommended a different level than originally targeted (e.g. J100 →
+J090), load **both** for comparison.
+
+### 3. Re-rate skills
+
+For each skill where the interview produced evidence, apply the adjustments in
+[references/rubric.md](references/rubric.md#skill-re-rating). Cite a specific
+moment, quote, or observation per change.
+
+### 4. Re-rate behaviours
+
+Behaviours are better assessed in interviews than CVs — they describe how
+someone acts, not what they've done. Use the
+[behaviour signals](references/rubric.md#behaviour-signals) and the
+[behaviour maturity scale](references/rubric.md#behaviour-maturity-scale).
+
+### 5. Assess level fit
+
+```bash
+bunx fit-pathway progress {discipline} {level} --track={track}
+```
+
+Apply the [level signals](references/rubric.md#level-signals).
+
+### 6. Write the interview assessment
+
+Save to `knowledge/Candidates/{Name}/interview-{date}.md` using
+[references/interview-template.md](references/interview-template.md). Include
+only skills with new evidence — don't repeat the full matrix.
+
+### 7. Generate the panel brief (if applicable)
+
+When more interview stages are planned (panel, technical, etc.), pull question
+candidates:
+
+```bash
+bunx fit-pathway interview {discipline} {level} --track={track}
+```
+
+Save `knowledge/Candidates/{Name}/panel.md` using
+[references/panel-template.md](references/panel-template.md). Audience:
+next-stage interviewers, often non-engineers — explain without jargon and tie
+suggested questions to remaining gaps.
+
+### 8. Update the candidate brief
+
+Apply targeted Edit operations to `knowledge/Candidates/{Name}/brief.md`:
+
+- Append a Pipeline entry with date, type, and outcome.
+- Add `## Interview Notes` if missing, with key observations.
+- Append `- [Interview Assessment](./interview-{date}.md)`.
+- Append `- [Panel Brief](./panel.md)` when one was created.
+- Update `Status` to reflect the current pipeline stage.
+
+Never rewrite the file. Never update the Gender field from interview
+observations.