@forwardimpact/basecamp 2.3.0 → 2.4.0

package/README.md

@@ -165,6 +165,25 @@ vi ~/.fit/basecamp/scheduler.json
 { "type": "once", "runAt": "2025-02-12T10:00:00Z" }
 ```
 
+## Updating
+
+When you upgrade Basecamp (install a new `.pkg`), the installer automatically
+runs `--update` on all configured knowledge bases. This pushes the latest
+`CLAUDE.md`, skills, and agents into each KB without touching your data.
+
+You can also run it manually at any time:
+
+```bash
+# Update all configured knowledge bases
+/Applications/Basecamp.app/Contents/MacOS/fit-basecamp --update
+
+# Update a specific knowledge base
+/Applications/Basecamp.app/Contents/MacOS/fit-basecamp --update ~/Documents/Personal
+```
+
+The update merges `.claude/settings.json` non-destructively — new entries are
+added but your existing permissions are preserved.
+
 ## CLI Reference
 
 ```
@@ -172,6 +191,7 @@ fit-basecamp                     Run due tasks once and exit
 fit-basecamp --daemon            Run continuously (poll every 60s)
 fit-basecamp --run <task>        Run a specific task immediately
 fit-basecamp --init <path>       Initialize a new knowledge base
+fit-basecamp --update [path]     Update KB skills, agents, and CLAUDE.md
 fit-basecamp --status            Show knowledge bases and task status
 fit-basecamp --validate          Validate agents and skills exist
 fit-basecamp --help              Show this help

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@forwardimpact/basecamp",
-  "version": "2.3.0",
+  "version": "2.4.0",
   "description": "Claude Code-native personal knowledge system with autonomous agents",
   "license": "Apache-2.0",
   "repository": {
@@ -28,5 +28,8 @@
   ],
   "engines": {
     "node": ">=18.0.0"
+  },
+  "dependencies": {
+    "xlsx": "^0.18.5"
   }
 }

package/template/.claude/skills/sync-apple-mail/SKILL.md

@@ -26,6 +26,8 @@ their email.
 
 - `~/.cache/fit/basecamp/state/apple_mail_last_sync` — last sync timestamp
   (single-line text file)
+- `~/.cache/fit/basecamp/state/apple_mail_last_rowid` — highest message ROWID
+  seen at last sync (single-line text file)
 - `~/Library/Mail/V*/MailData/Envelope Index` — Apple Mail SQLite database
 
 ## Outputs
@@ -36,6 +38,8 @@ their email.
   attachment files for each thread (PDFs, images, documents, etc.)
 - `~/.cache/fit/basecamp/state/apple_mail_last_sync` — updated with new sync
   timestamp
+- `~/.cache/fit/basecamp/state/apple_mail_last_rowid` — updated with highest
+  ROWID seen
 
 ---
 
@@ -53,13 +57,17 @@ The script:
 1. Finds the Mail database (`~/Library/Mail/V*/MailData/Envelope Index`)
 2. Loads last sync timestamp (or defaults to `--days` days ago for first sync)
 3. Discovers the thread grouping column (`conversation_id` or `thread_id`)
-4. Finds threads with new messages since last sync (up to 500)
-5. For each thread: fetches messages, batch-fetches recipients and attachment
+4. Loads last-seen ROWID (or defaults to 0 for first sync)
+5. Finds threads with new messages since last sync (up to 500), using both
+   timestamp and ROWID to catch late-arriving emails (emails downloaded after
+   a delay may have `date_received` before the last sync timestamp, but their
+   ROWID will be higher than the last-seen ROWID)
+6. For each thread: fetches messages, batch-fetches recipients and attachment
    metadata, parses `.emlx` files for full email bodies (falling back to
    database summaries), copies attachment files to the output directory
-6. Writes one markdown file per thread to `~/.cache/fit/basecamp/apple_mail/`
-7. Updates sync state timestamp
-8. Reports summary (threads processed, files written)
+7. Writes one markdown file per thread to `~/.cache/fit/basecamp/apple_mail/`
+8. Updates sync state (timestamp and max ROWID)
+9. Reports summary (threads processed, files written)
 
 The script imports `scripts/parse-emlx.mjs` to extract plain text bodies from
 `.emlx` / `.partial.emlx` files (handles HTML-only emails by stripping tags).

package/template/.claude/skills/track-candidates/SKILL.md

@@ -130,18 +130,27 @@ For each candidate found in a recruitment email, extract:
 
 | Field             | Source                                            | Required            |
 | ----------------- | ------------------------------------------------- | ------------------- |
-| **Name**          | Filename, email body, CV                          | Yes                 |
-| **Role**          | Email body, CV                                    | Yes                 |
-| **Rate**          | Email body (e.g. "$120/hr", "€80/h")              | If available        |
-| **Availability**  | Email body (e.g. "1 month notice", "immediately") | If available        |
-| **English**       | Email body (e.g. "B2", "Upper-intermediate")      | If available        |
-| **Location**      | Email body, CV                                    | If available        |
-| **Source agency** | Sender domain → Organization                      | Yes                 |
-| **Recruiter**     | Email sender or CC'd recruiter                    | Yes                 |
-| **CV path**       | Attachment directory                              | If available        |
-| **Skills**        | Email body, CV                                    | If available        |
-| **Gender**        | Name, pronouns, recruiter context                 | If identifiable     |
-| **Summary**       | Email body, CV                                    | Yes — 2-3 sentences |
+| **Name**             | Filename, email body, CV                                        | Yes                 |
+| **Title**            | Email body, CV — the candidate's professional title/function    | Yes                 |
+| **Rate**             | Email body (e.g. "$120/hr", "€80/h")                            | If available        |
+| **Availability**     | Email body (e.g. "1 month notice", "immediately")               | If available        |
+| **English**          | Email body (e.g. "B2", "Upper-intermediate")                    | If available        |
+| **Location**         | Email body, CV                                                  | If available        |
+| **Source agency**    | Sender domain → Organization                                    | Yes                 |
+| **Recruiter**        | Email sender or CC'd recruiter                                  | Yes                 |
+| **CV path**          | Attachment directory                                            | If available        |
+| **Skills**           | Email body, CV                                                  | If available        |
+| **Gender**           | Name, pronouns, recruiter context                               | If identifiable     |
+| **Summary**          | Email body, CV                                                  | Yes — 2-3 sentences |
+| **Role**             | Internal requisition profile being hired against                | If available        |
+| **Req**              | Requisition ID from hiring system                               | If available        |
+| **Internal/External**| Whether candidate is internal or external                       | If available        |
+| **Model**            | Engagement model (B2B, Direct Hire, etc.)                       | If available        |
+| **Current title**    | CV or email body                                                | If available        |
+| **Email**            | Email body, CV, signature                                       | If available        |
+| **Phone**            | Email body, CV, signature                                       | If available        |
+| **LinkedIn**         | Email body, CV                                                  | If available        |
+| **Also known as**    | Alternate name spellings or transliterations                    | If available        |
 
 ### Determining Gender
 
@@ -193,9 +202,11 @@ Assign a status based on the email context:
 | `screening`        | Under review, questions asked about the candidate     |
 | `first-interview`  | First interview scheduled or completed                |
 | `second-interview` | Second interview scheduled or completed               |
+| `work-trial`       | Paid work trial or assessment project in progress     |
 | `offer`            | Offer extended                                        |
 | `hired`            | Accepted and onboarding                               |
 | `rejected`         | Explicitly passed on ("not a fit", "pass", "decline") |
+| `withdrawn`        | Candidate withdrew from the process                   |
 | `on-hold`          | Paused, waiting on notice period, or deferred         |
 
 **Default to `new`** if no response signals are found. Read the full thread
@@ -207,7 +218,10 @@ Look for these patterns in the hiring manager's replies:
 
 - "let's schedule" / "set up an interview" → `first-interview`
 - "second round" / "follow-up interview" → `second-interview`
+- "work trial" / "assessment project" / "paid trial" → `work-trial`
 - "not what we're looking for" / "pass" → `rejected`
+- "candidate withdrew" / "no longer interested" / "accepted another offer" →
+  `withdrawn`
 - "extend an offer" / "make an offer" → `offer`
 - "they've accepted" / "start date" → `hired`
 - "put on hold" / "come back to later" → `on-hold`
@@ -244,7 +258,7 @@ Then create `knowledge/Candidates/{Full Name}/brief.md`:
 # {Full Name}
 
 ## Info
-**Role:** {role title}
+**Title:** {professional title/function}
 **Rate:** {rate or "—"}
 **Availability:** {availability or "—"}
 **English:** {level or "—"}
@@ -254,6 +268,7 @@ Then create `knowledge/Candidates/{Full Name}/brief.md`:
 **Status:** {pipeline status}
 **First seen:** {date profile was shared, YYYY-MM-DD}
 **Last activity:** {date of most recent thread activity, YYYY-MM-DD}
+{extra fields here — see below}
 
 ## Summary
 {2-3 sentences: role, experience level, key strengths}
@@ -271,7 +286,11 @@ Then create `knowledge/Candidates/{Full Name}/brief.md`:
 ## Skills
 {comma-separated skill tags}
 
+## Interview Notes
+{interview feedback, structured by date — omit section if no interviews yet}
+
 ## Notes
+{free-form observations — always present, even if empty}
 ```
 
 If a CV attachment exists, **copy it into the candidate directory** before
@@ -279,6 +298,37 @@ writing the note.
 
 If no CV attachment exists, omit the `## CV` section entirely.
 
+### Extra Info Fields
+
+Place any of these **after Last activity** in the order shown, only when
+available:
+
+```markdown
+**Role:** {internal requisition profile, e.g. "Staff Engineer"}
+**Req:** {requisition ID, e.g. "4950237 — Principal Software Engineer"}
+**Internal/External:** {Internal / External / External (Prior Worker)}
+**Model:** {engagement model, e.g. "B2B (via Agency) — conversion to FTE not possible"}
+**Current title:** {current job title and employer}
+**Email:** {personal or work email}
+**Phone:** {phone number}
+**LinkedIn:** {LinkedIn profile URL}
+**Also known as:** {alternate name spellings}
+```
+
+### Additional Sections
+
+Some candidates accumulate richer profiles over time. These optional sections go
+**after Skills and before Notes**, in this order:
+
+1. `## Education` — degrees, institutions, years
+2. `## Certifications` — professional certifications
+3. `## Work History` — chronological career history (when extracted from CV)
+4. `## Key Facts` — notable bullet points from CV review
+5. `## Interview Notes` — structured by date as `### YYYY-MM-DD — {description}`
+
+`## Notes` is always the **last section**. If an `## Open Items` section exists
+(pending questions or follow-ups), place it after Notes.
+
 ### For EXISTING candidates
 
 Read `knowledge/Candidates/{Full Name}/brief.md`, then apply targeted edits:
@@ -364,6 +414,11 @@ produces a full framework-aligned assessment.
 - [ ] Scanned all new/changed email threads for recruitment signals
 - [ ] Extracted all candidates found (check attachment directories too)
 - [ ] Each candidate has a complete note with all available fields
+- [ ] Info fields are in standard order (Title, Rate, Availability, English,
+      Location, Gender, Source, Status, First seen, Last activity, then extras)
+- [ ] Sections are in standard order (Info → Summary → CV → Connected to →
+      Pipeline → Skills → Education/Certifications/Work History/Key Facts →
+      Interview Notes → Notes → Open Items)
 - [ ] CV paths are correct and point to actual files
 - [ ] Pipeline status reflects the latest thread activity
 - [ ] Timeline entries are in chronological order

package/template/.claude/skills/upstream-skill/SKILL.md

@@ -29,7 +29,8 @@ Run this skill when:
 
 ## Outputs
 
-- `.claude/skills/CHANGELOG.md` — structured changelog of all local skill changes
+- `.claude/skills/<skill-name>/CHANGELOG.md` — per-skill changelog of local
+  changes, one per modified skill directory
 
 ---
 
@@ -41,21 +42,22 @@ Use git to find all skill files that have been added, modified, or deleted since
 the last changelog entry (or since initial commit if no changelog exists).
 
 ```bash
-# Find the date of the last changelog entry (if any)
-head -20 .claude/skills/CHANGELOG.md 2>/dev/null
+# Find the date of the last changelog entry for a skill (if any)
+head -20 .claude/skills/<skill-name>/CHANGELOG.md 2>/dev/null
 
 # List changed skill files since last documented change
 git log --oneline --name-status -- '.claude/skills/'
 ```
 
-If `.claude/skills/CHANGELOG.md` already exists, read the most recent entry date
-and only look at changes after that date:
+If a skill already has a `.claude/skills/<skill-name>/CHANGELOG.md`, read the
+most recent entry date and only look at changes after that date:
 
 ```bash
-git log --after="<last-entry-date>" --name-status -- '.claude/skills/'
+git log --after="<last-entry-date>" --name-status -- '.claude/skills/<skill-name>/'
 ```
 
-If no changelog exists, consider all commits that touched `.claude/skills/`.
+If no changelog exists for a skill, consider all commits that touched that
+skill's directory.
 
 ### Step 2: Classify Each Change
 
@@ -106,18 +108,17 @@ Bad descriptions:
 
 ### Step 4: Write the Changelog
 
-Create or update `.claude/skills/CHANGELOG.md` with the following format:
+For each changed skill, create or update its
+`.claude/skills/<skill-name>/CHANGELOG.md` with the following format:
 
 ```markdown
-# Skill Changelog
+# <skill-name> Changelog
 
-Changes to skills in this installation that should be considered for upstream
-inclusion in the Forward Impact monorepo.
+Changes to this skill that should be considered for upstream inclusion in the
+Forward Impact monorepo.
 
 ## <YYYY-MM-DD>
 
-### <skill-name> (added|modified|removed)
-
 **What:** <one-line summary of the change>
 
 **Why:** <the problem or improvement that motivated it>
@@ -128,14 +129,20 @@ inclusion in the Forward Impact monorepo.
 ---
 ```
 
-Entries are in **reverse chronological order** (newest first). Group changes
-from the same date under a single date heading.
+Entries are in **reverse chronological order** (newest first). Each skill has
+its own changelog file inside its directory.
+
+For **new skills**, create the `CHANGELOG.md` alongside the `SKILL.md` with a
+single `added` entry describing the skill's purpose.
+
+For **removed skills**, the changelog should be the last file remaining in the
+skill directory, documenting why the skill was removed.
 
-### Step 5: Review the Changelog
+### Step 5: Review the Changelogs
 
-After writing, read the changelog back and verify:
+After writing, read each changelog back and verify:
 
-- [ ] Every changed skill has an entry
+- [ ] Every changed skill has a `CHANGELOG.md` in its directory
 - [ ] Each entry has What, Why, and Details sections
 - [ ] Descriptions are specific enough for an upstream maintainer to act on
 - [ ] New skills include a brief description of their purpose
@@ -145,16 +152,16 @@ After writing, read the changelog back and verify:
 
 ## Example Output
 
+`.claude/skills/track-candidates/CHANGELOG.md`:
+
 ```markdown
-# Skill Changelog
+# track-candidates Changelog
 
-Changes to skills in this installation that should be considered for upstream
-inclusion in the Forward Impact monorepo.
+Changes to this skill that should be considered for upstream inclusion in the
+Forward Impact monorepo.
 
 ## 2026-03-01
 
-### track-candidates (modified)
-
 **What:** Added gender field extraction for diversity tracking
 
 **Why:** Recruitment pipeline lacked diversity metrics — pool composition was
@@ -166,7 +173,18 @@ invisible without structured gender data.
 - Added explicit note that field has no bearing on hiring decisions
 - Updated quality checklist to include gender field verification
 
-### process-hyprnote (added)
+---
+```
+
+`.claude/skills/process-hyprnote/CHANGELOG.md`:
+
+```markdown
+# process-hyprnote Changelog
+
+Changes to this skill that should be considered for upstream inclusion in the
+Forward Impact monorepo.
+
+## 2026-03-01
 
 **What:** New skill for processing Hyprnote meeting recordings
 
@@ -180,10 +198,17 @@ they weren't being integrated into the knowledge base.
 - Links attendees to `knowledge/People/` entries
 
 ---
+```
 
-## 2026-02-15
+`.claude/skills/extract-entities/CHANGELOG.md`:
 
-### extract-entities (modified)
+```markdown
+# extract-entities Changelog
+
+Changes to this skill that should be considered for upstream inclusion in the
+Forward Impact monorepo.
+
+## 2026-02-15
 
 **What:** Increased batch size from 5 to 10 files per run
 
@@ -200,7 +225,8 @@ dozens of runs to catch up after a week of email.
 ## Notes
 
 - This skill only **documents** changes — it does not push or merge anything
-- The changelog is consumed by the **downstream** skill in the upstream monorepo
+- The per-skill changelogs are consumed by the **downstream** skill in the
+  upstream monorepo
 - Keep descriptions actionable: an upstream maintainer should be able to
   understand and apply each change without access to this installation
 - When in doubt about whether a change is upstream-worthy, include it — the

package/template/.claude/skills/workday-requisition/SKILL.md

@@ -0,0 +1,341 @@
+---
+name: workday-requisition
+description: >
+  Import candidates from a Workday requisition export (.xlsx) into
+  knowledge/Candidates/. Parses requisition metadata and candidate data,
+  creates candidate briefs and CV.md files from resume text, and integrates
+  with the existing track-candidates pipeline. Use when the user provides a
+  Workday export file or asks to import candidates from an XLSX requisition
+  export.
+---
+
+# Workday Requisition Import
+
+Import candidates from a Workday requisition export (`.xlsx`) into
+`knowledge/Candidates/`. Extracts requisition metadata and candidate profiles,
+creates standardized candidate briefs and `CV.md` files from the embedded resume
+text, and integrates with the existing `track-candidates` pipeline format.
+
+## Trigger
+
+Run this skill:
+
+- When the user provides a Workday requisition export file (`.xlsx`)
+- When the user asks to import candidates from Workday or an XLSX export
+- When the user mentions a requisition ID and asks to process the export
+
+## Prerequisites
+
+- A Workday requisition export file (`.xlsx`) accessible on the filesystem
+  (typically in `~/Downloads/`)
+- The `xlsx` npm package installed in the KB root:
+  ```bash
+  npm install xlsx
+  ```
+- User identity configured in `USER.md`
+
+## Inputs
+
+- Path to the `.xlsx` file (e.g.
+  `~/Downloads/4951493_Principal_Software_Engineer_–_Forward_Deployed_(Open).xlsx`)
+
+## Outputs
+
+- `knowledge/Candidates/{Full Name}/brief.md` — candidate profile note
+- `knowledge/Candidates/{Full Name}/CV.md` — resume text rendered as markdown
+- Updated existing candidate briefs if candidate already exists
+
+---
+
+## Workday Export Format
+
+The Workday requisition export contains multiple sheets. This skill uses:
+
+### Sheet 1 — Requisition Metadata
+
+Key-value pairs, one per row:
+
+| Row | Field                 | Example                                |
+| --- | --------------------- | -------------------------------------- |
+| 1   | Title header          | `4951493 Principal Software Engineer…` |
+| 2   | Recruiting Start Date | `02/10/2026`                           |
+| 3   | Target Hire Date      | `02/10/2026`                           |
+| 4   | Primary Location      | `USA - NY - Headquarters`              |
+| 5   | Hiring Manager Title  | `Hiring Manager`                       |
+| 6   | Hiring Manager        | Name                                   |
+| 7   | Recruiter Title       | `Recruiter`                            |
+| 8   | Recruiter             | Name                                   |
+
+### Sheet 3 — Candidates
+
+Row 3 contains column headers. Data rows start at row 4. After the last
+candidate, stage-summary rows appear (these are not candidates).
+
+| Column | Field                  | Maps to brief field…     |
+| ------ | ---------------------- | ------------------------ |
+| B      | Candidate name         | `# {Name}`               |
+| C      | Stage                  | Status derivation        |
+| D      | Step / Disposition     | Status derivation        |
+| G      | Resume filename        | Reference only (no file) |
+| H      | Date Applied           | **First seen**           |
+| I      | Current Job Title      | **Current title**, Title |
+| J      | Current Company        | **Current title** suffix |
+| K      | Source                 | **Source**               |
+| L      | Referred by            | **Source** suffix        |
+| N      | Availability Date      | **Availability**         |
+| O      | Visa Requirement       | Notes                    |
+| P      | Eligible to Work       | Notes                    |
+| Q      | Relocation             | Notes                    |
+| R      | Salary Expectations    | **Rate**                 |
+| S      | Non-Compete            | Notes                    |
+| T      | Candidate Location     | **Location**             |
+| U      | Phone                  | **Phone**                |
+| V      | Email                  | **Email**                |
+| W      | Total Years Experience | Summary context          |
+| X      | All Job Titles         | Work History context     |
+| Y      | Companies              | Work History context     |
+| Z      | Degrees                | Education                |
+| AA     | Fields of Study        | Education                |
+| AB     | Language               | **English** / Language   |
+| AC     | Resume Text            | `CV.md` content          |
+
+#### Name Annotations
+
+Names may include parenthetical annotations:
+
+- `(Prior Worker)` → Internal/External = `External (Prior Worker)`
+- `(Internal)` → Internal/External = `Internal`
+- No annotation + source contains "Internal" → `Internal`
+- Otherwise → `External`
+
+## Before Starting
+
+1. Read `USER.md` to get the user's name, email, and domain.
+2. Confirm the XLSX file path with the user (or use the provided path).
+3. Ensure the `xlsx` package is installed:
+   ```bash
+   npm list xlsx 2>/dev/null || npm install xlsx
+   ```
+
+## Step 1: Parse the Export
+
+Run the parse script to extract structured data:
+
+```bash
+node .claude/skills/workday-requisition/scripts/parse-workday.mjs "<path-to-xlsx>" --summary
+```
+
+This prints a summary of the requisition and all candidates. Review the output
+to confirm the file parsed correctly and note the total candidate count.
+
+For the full JSON output (used in subsequent steps):
+
+```bash
+node .claude/skills/workday-requisition/scripts/parse-workday.mjs "<path-to-xlsx>"
+```
+
+The full output is a JSON object with:
+
+- `requisition` — metadata (id, title, location, hiringManager, recruiter)
+- `candidates` — array of candidate objects with all extracted fields
+
+## Step 2: Build Candidate Index
+
+Scan existing candidate notes to avoid duplicates:
+
+```bash
+ls -d knowledge/Candidates/*/ 2>/dev/null
+```
+
+For each existing candidate, check if they match any imported candidate by name.
+Use fuzzy matching — the Workday name may differ slightly from an existing note
+(e.g. middle names, accents, spelling variations).
+
+## Step 3: Determine Pipeline Status
+
+Map Workday stage and step/disposition to the `track-candidates` pipeline
+status:
+
+| Workday Step / Disposition   | Pipeline Status    |
+| ---------------------------- | ------------------ |
+| `Considered`                 | `new`              |
+| `Manager Resume Screen`      | `screening`        |
+| `Assessment`                 | `screening`        |
+| `Interview` / `Phone Screen` | `first-interview`  |
+| `Second Interview`           | `second-interview` |
+| `Reference Check`            | `second-interview` |
+| `Offer`                      | `offer`            |
+| `Employment Agreement`       | `offer`            |
+| `Background Check`           | `hired`            |
+| `Ready for Hire`             | `hired`            |
+| `Rejected` / `Declined`      | `rejected`         |
+
+If the step is identical to the stage (e.g. both "Considered"), default to
+`new`.
+
+## Step 4: Create CV.md from Resume Text
+
+For each candidate with resume text, create
+`knowledge/Candidates/{Clean Name}/CV.md`:
+
+```markdown
+# {Clean Name} — Resume
+
+> Extracted from Workday requisition export {Req ID} on {today's date}.
+> Original file: {Resume filename from column G}
+
+---
+
+{Resume text from column AC, preserving original formatting}
+```
+
+**Formatting rules for resume text:**
+
+- Preserve paragraph breaks (double newlines)
+- Convert ALL-CAPS section headers to `## Heading` format
+- Preserve bullet points and lists
+- Clean up excessive whitespace but keep structure
+- Do not rewrite or summarize — reproduce faithfully
+
+If a candidate has no resume text, skip the CV.md file.
+
+## Step 5: Write Candidate Brief
+
+### For NEW candidates
+
+Create the candidate directory and brief:
+
+```bash
+mkdir -p "knowledge/Candidates/{Clean Name}"
+```
+
+Then create `knowledge/Candidates/{Clean Name}/brief.md` using the
+`track-candidates` format:
+
+```markdown
+# {Clean Name}
+
+## Info
+**Title:** {Current Job Title or "—"}
+**Rate:** {Salary Expectations or "—"}
+**Availability:** {Availability Date or "—"}
+**English:** {Language field or "—"}
+**Location:** {Candidate Location or "—"}
+**Gender:** —
+**Source:** {Source} {via Referred by, if present}
+**Status:** {pipeline status from Step 3}
+**First seen:** {Date Applied, YYYY-MM-DD}
+**Last activity:** {Date Applied, YYYY-MM-DD}
+**Req:** {Req ID} — {Req Title}
+**Internal/External:** {Internal / External / External (Prior Worker)}
+**Current title:** {Current Job Title at Current Company}
+**Email:** {Email or "—"}
+**Phone:** {Phone or "—"}
+
+## Summary
+{2-3 sentences based on resume text: role focus, years of experience, key
+strengths. If no resume text, use Current Job Title + Total Years Experience.}
+
+## CV
+- [CV.md](./CV.md)
+
+## Connected to
+- {Referred by person, if present}
+
+## Pipeline
+- **{Date Applied}**: Applied via {Source}
+
+## Skills
+{Extract key technical skills from resume text — use framework IDs where
+possible via `npx fit-pathway skill --list`}
+
+## Education
+{Degrees and Fields of Study from the export columns}
+
+## Work History
+{All Job Titles and Companies from the export columns, formatted as a list}
+
+## Notes
+{Include any noteworthy fields here:}
+{- Visa requirement (if present)}
+{- Eligible to work (if present)}
+{- Relocation willingness (if present)}
+{- Non-compete status (if present)}
+{- Total years of experience}
+```
+
+**Extra fields** (after Last activity, in order): Req, Internal/External,
+Current title, Email, Phone, LinkedIn — include only when available. Follow the
+order defined in the `track-candidates` skill.
+
+### For EXISTING candidates
+
+Read `knowledge/Candidates/{Name}/brief.md`, then apply targeted edits:
+
+- Add or update **Req** field with this requisition's ID
+- Update **Status** if the Workday stage is more advanced
+- Update **Last activity** date if this application is more recent
+- Add a new **Pipeline** entry:
+  `**{Date Applied}**: Applied to {Req ID} — {Req Title} via {Source}`
+- Update any missing fields (Email, Phone, Location) from the export
+- Do NOT overwrite existing richer data with sparser Workday data
+
+**Use precise edits — don't rewrite the entire file.**
+
+## Step 6: Process in Batches
+
+Workday exports can contain many candidates. Process in batches of **10
+candidates per run** to stay within context limits.
+
+For each batch:
+
+1. Parse the JSON output (or re-run the parse script)
+2. Process 10 candidates: create/update brief + CV.md
+3. Report progress: `Processed {N}/{Total} candidates`
+
+If the export has more than 10 candidates, tell the user how many remain and
+offer to continue.
+
+## Step 7: Capture Key Insights
+
+After processing all candidates, review the batch for strategic observations and
+add them to `knowledge/Candidates/Insights.md`:
+
+- Candidates who stand out as strong matches
+- Candidates better suited for a different role
+- Notable patterns (source quality, experience distribution, skill gaps)
+
+Follow the `track-candidates` Insights format: one bullet per insight under
+`## Placement Notes` with `[[Candidates/Name/brief|Name]]` links.
+
+## Step 8: Tag Skills with Framework IDs
+
+When resume text mentions technical skills, map them to the engineering
+framework:
+
+```bash
+npx fit-pathway skill --list
+```
+
+Use framework skill IDs in the **Skills** section of each brief. If a candidate
+has a CV.md, flag them for the `analyze-cv` skill for a full framework-aligned
+assessment.
+
+## Quality Checklist
+
+- [ ] XLSX parsed correctly — verify candidate count matches summary
+- [ ] Requisition metadata extracted (ID, title, hiring manager, recruiter)
+- [ ] Each candidate has a directory under `knowledge/Candidates/{Clean Name}/`
+- [ ] CV.md created for every candidate with resume text
+- [ ] CV.md faithfully reproduces resume text (no rewriting or summarizing)
+- [ ] Brief follows `track-candidates` format exactly
+- [ ] Info fields in standard order (Title → Rate → Availability → English →
+      Location → Gender → Source → Status → First seen → Last activity → extras)
+- [ ] Pipeline status correctly mapped from Workday stage/step
+- [ ] Internal/External correctly derived from name annotations and source
+- [ ] Name annotations stripped from directory names and headings
+- [ ] Existing candidates updated (not duplicated) with precise edits
+- [ ] Skills tagged using framework skill IDs where possible
+- [ ] Gender field set to `—` (Workday exports don't include gender signals)
+- [ ] Insights.md updated with strategic observations
+- [ ] No duplicate candidate directories created

package/template/.claude/skills/workday-requisition/scripts/parse-workday.mjs

@@ -0,0 +1,243 @@
+#!/usr/bin/env node
+/**
+ * Parse a Workday requisition export (.xlsx) and output structured JSON.
+ *
+ * Reads Sheet1 for requisition metadata and the "Candidates" sheet for
+ * candidate data. Outputs a JSON object to stdout with:
+ *   - requisition: { id, title, startDate, targetHireDate, location,
+ *                     hiringManager, recruiter }
+ *   - candidates:  [ { name, cleanName, stage, step, resumeFile, dateApplied,
+ *                       currentTitle, currentCompany, source, referredBy,
+ *                       availabilityDate, visaRequirement, eligibleToWork,
+ *                       relocation, salaryExpectations, nonCompete, location,
+ *                       phone, email, totalYearsExperience, allJobTitles,
+ *                       companies, degrees, fieldsOfStudy, language,
+ *                       resumeText, internalExternal } ]
+ *
+ * Usage:
+ *   node scripts/parse-workday.mjs <path-to-xlsx>
+ *   node scripts/parse-workday.mjs <path-to-xlsx> --summary
+ *   node scripts/parse-workday.mjs -h|--help
+ *
+ * Requires: npm install xlsx
+ */
+
+import { readFileSync } from "node:fs";
+
+if (
+  process.argv.includes("-h") ||
+  process.argv.includes("--help") ||
+  process.argv.length < 3
+) {
+  console.log(`parse-workday — extract candidates from a Workday requisition export
+
+Usage:
+  node scripts/parse-workday.mjs <path-to-xlsx>            Full JSON output
+  node scripts/parse-workday.mjs <path-to-xlsx> --summary  Name + status only
+  node scripts/parse-workday.mjs -h|--help                 Show this help
+
+Output (JSON):
+  { requisition: { id, title, ... }, candidates: [ { name, ... }, ... ] }
+
+Requires: npm install xlsx`);
+  process.exit(process.argv.length < 3 ? 1 : 0);
+}
+
+let XLSX;
+try {
+  XLSX = await import("xlsx");
+} catch {
+  console.error(
+    "Error: xlsx package not found. Install it first:\n  npm install xlsx",
+  );
+  process.exit(1);
+}
+
+const filePath = process.argv[2];
+const summaryMode = process.argv.includes("--summary");
+
+const data = readFileSync(filePath);
+const wb = XLSX.read(data, { type: "buffer", cellDates: true });
+
+// --- Sheet 1: Requisition metadata ---
+
+const ws1 = wb.Sheets[wb.SheetNames[0]];
+const sheet1Rows = XLSX.utils.sheet_to_json(ws1, { header: 1, defval: "" });
+
+/** Extract the requisition ID and title from the header row. */
+function parseReqHeader(headerText) {
+  // Format: "4951493 Principal Software Engineer – Forward Deployed: 4951493 ..."
+  const text = String(headerText).split(":")[0].trim();
+  const match = text.match(/^(\d+)\s+(.+)$/);
+  if (match) return { id: match[1], title: match[2] };
+  return { id: "", title: text };
+}
+
+/** Build a key-value map from Sheet1 rows (column A = label, column B = value). */
+function buildReqMetadata(rows) {
+  const meta = {};
+  for (const row of rows) {
+    const key = String(row[0] || "").trim();
+    const val = String(row[1] || "").trim();
+    if (key && val) meta[key] = val;
+  }
+  return meta;
+}
+
+const reqHeader = parseReqHeader(sheet1Rows[0]?.[0] || "");
+const reqMeta = buildReqMetadata(sheet1Rows.slice(1));
+
+/** Clean a metadata date string (e.g. "02/10/2026 - 22 days ago" → "2026-02-10"). */
+function cleanMetaDate(val) {
+  if (!val) return "";
+  const clean = val.replace(/\s*-\s*\d+\s+days?\s+ago$/i, "").trim();
+  // Convert MM/DD/YYYY → YYYY-MM-DD
+  const match = clean.match(/^(\d{2})\/(\d{2})\/(\d{4})$/);
+  if (match) return `${match[3]}-${match[1]}-${match[2]}`;
+  return clean;
+}
+
+const requisition = {
+  id: reqHeader.id,
+  title: reqHeader.title,
+  startDate: cleanMetaDate(reqMeta["Recruiting Start Date"]),
+  targetHireDate: cleanMetaDate(reqMeta["Target Hire Date"]),
+  location: reqMeta["Primary Location"] || "",
+  hiringManager: reqMeta["Hiring Manager"] || "",
+  recruiter: reqMeta["Recruiter"] || "",
+};
+
+// --- Sheet 3: Candidates ---
+
+// Find the "Candidates" sheet (usually index 2, but search by name to be safe)
+const candSheetName =
+  wb.SheetNames.find((n) => n.toLowerCase() === "candidates") ||
+  wb.SheetNames[2];
+const ws3 = wb.Sheets[candSheetName];
+const candRows = XLSX.utils.sheet_to_json(ws3, { header: 1, defval: "" });
+
+// Row 3 (index 2) has column headers. Data starts at row 4 (index 3).
+// Stage summary rows start when column A has a non-empty value that looks like
+// a label or number — detect by checking if column C (Stage) is empty and
+// column A has a value.
+const DATA_START = 3;
+
+/**
+ * Clean a candidate name by stripping annotations like (Prior Worker),
+ * (Internal), etc. Returns { cleanName, internalExternal }.
+ */
+function parseName(raw) {
+  const name = String(raw).trim();
+  if (!name) return { cleanName: "", internalExternal: "" };
+
+  const match = name.match(/^(.+?)\s*\(([^)]+)\)\s*$/);
+  if (match) {
+    const annotation = match[2].trim();
+    let ie = "";
+    if (/prior\s*worker/i.test(annotation)) ie = "External (Prior Worker)";
+    else if (/internal/i.test(annotation)) ie = "Internal";
+    else ie = annotation;
+    return { cleanName: match[1].trim(), internalExternal: ie };
+  }
+  return { cleanName: name, internalExternal: "" };
+}
+
+/** Detect source-based internal/external when name annotation is absent. */
+function inferInternalExternal(source, nameAnnotation) {
+  if (nameAnnotation) return nameAnnotation;
+  if (/internal/i.test(source)) return "Internal";
+  return "External";
+}
+
+/** Format a date value (may be Date object or string). */
+function fmtDate(val) {
+  if (!val) return "";
+  if (val instanceof Date) {
+    // Use local date parts to avoid UTC offset shifting the day
+    const y = val.getFullYear();
+    const m = String(val.getMonth() + 1).padStart(2, "0");
+    const d = String(val.getDate()).padStart(2, "0");
+    return `${y}-${m}-${d}`;
+  }
+  const s = String(val).trim();
+  // Strip trailing " 00:00:00" and relative text like " - 22 days ago"
+  return s
+    .replace(/\s+\d{2}:\d{2}:\d{2}$/, "")
+    .replace(/\s*-\s*\d+\s+days?\s+ago$/i, "");
+}
+
+/** Normalise multiline cell values into clean lists. */
+function multiline(val) {
+  if (!val) return "";
+  return String(val)
+    .split("\n")
+    .map((l) => l.trim())
+    .filter(Boolean)
+    .join(", ");
+}
+
+const candidates = [];
+
+for (let i = DATA_START; i < candRows.length; i++) {
+  const row = candRows[i];
+  const rawName = String(row[1] || "").trim(); // Column B (index 1)
+  const stage = String(row[2] || "").trim(); // Column C (index 2)
+
+  // Stop at stage-summary rows: column A has a value, column C (stage) is empty
+  if (!rawName || (!stage && String(row[0] || "").trim())) break;
+  if (!rawName) continue;
+
+  const { cleanName, internalExternal: nameIE } = parseName(rawName);
+  const source = String(row[10] || "").trim();
+
+  candidates.push({
+    name: rawName,
+    cleanName,
+    stage,
+    step: String(row[3] || "").trim(),
+    awaitingMe: String(row[4] || "").trim(),
+    awaitingAction: String(row[5] || "").trim(),
+    resumeFile: String(row[6] || "").trim(),
+    dateApplied: fmtDate(row[7]),
+    currentTitle: String(row[8] || "").trim(),
+    currentCompany: String(row[9] || "").trim(),
+    source,
+    referredBy: String(row[11] || "").trim(),
+    availabilityDate: fmtDate(row[13]),
+    visaRequirement: String(row[14] || "").trim(),
+    eligibleToWork: String(row[15] || "").trim(),
+    relocation: String(row[16] || "").trim(),
+    salaryExpectations: String(row[17] || "").trim(),
+    nonCompete: String(row[18] || "").trim(),
+    location: String(row[19] || "").trim(),
+    phone: String(row[20] || "").trim(),
+    email: String(row[21] || "").trim(),
+    totalYearsExperience: String(row[22] || "").trim(),
+    allJobTitles: multiline(row[23]),
+    companies: multiline(row[24]),
+    degrees: multiline(row[25]),
+    fieldsOfStudy: multiline(row[26]),
+    language: multiline(row[27]),
+    resumeText: String(row[28] || "").trim(),
+    internalExternal: inferInternalExternal(source, nameIE),
+  });
+}
+
+// --- Output ---
+
+if (summaryMode) {
+  console.log(`Requisition: ${requisition.id} — ${requisition.title}`);
+  console.log(`Location: ${requisition.location}`);
+  console.log(`Hiring Manager: ${requisition.hiringManager}`);
+  console.log(`Recruiter: ${requisition.recruiter}`);
+  console.log(`Candidates: ${candidates.length}`);
+  console.log();
+  for (const c of candidates) {
+    const resume = c.resumeText ? "has resume" : "no resume";
+    console.log(
+      `  ${c.cleanName} — ${c.step || c.stage} (${c.internalExternal}, ${resume})`,
+    );
+  }
+} else {
+  console.log(JSON.stringify({ requisition, candidates }, null, 2));
+}

package/template/CLAUDE.md

@@ -81,13 +81,13 @@ This knowledge base is maintained by a team of agents, each defined in
 `.claude/agents/`. They are woken on a schedule by the Basecamp scheduler. Each
 wake, they observe KB state, decide the most valuable action, and execute.
 
-| Agent              | Domain                         | Schedule        | Skills                                                         |
-| ------------------ | ------------------------------ | --------------- | -------------------------------------------------------------- |
-| **postman**        | Email triage and drafts        | Every 5 min     | sync-apple-mail, draft-emails                                  |
-| **concierge**      | Meeting prep and transcripts   | Every 10 min    | sync-apple-calendar, meeting-prep, process-hyprnote            |
-| **librarian**      | Knowledge graph maintenance    | Every 15 min    | extract-entities, organize-files, manage-tasks                 |
-| **recruiter**      | Engineering recruitment        | Every 30 min    | track-candidates, analyze-cv, right-to-be-forgotten, fit-pathway, fit-map |
-| **chief-of-staff** | Daily briefings and priorities | 7am, Mon 7:30am | weekly-update _(Mon)_, _(reads all state for daily briefings)_ |
+| Agent              | Domain                         | Schedule        | Skills                                                                                         |
+| ------------------ | ------------------------------ | --------------- | ---------------------------------------------------------------------------------------------- |
+| **postman**        | Email triage and drafts        | Every 5 min     | sync-apple-mail, draft-emails                                                                  |
+| **concierge**      | Meeting prep and transcripts   | Every 10 min    | sync-apple-calendar, meeting-prep, process-hyprnote                                            |
+| **librarian**      | Knowledge graph maintenance    | Every 15 min    | extract-entities, organize-files, manage-tasks                                                 |
+| **recruiter**      | Engineering recruitment        | Every 30 min    | track-candidates, analyze-cv, workday-requisition, right-to-be-forgotten, fit-pathway, fit-map |
+| **chief-of-staff** | Daily briefings and priorities | 7am, Mon 7:30am | weekly-update _(Mon)_, _(reads all state for daily briefings)_                                 |
 
 Each agent writes a triage file to `~/.cache/fit/basecamp/state/` every wake
 cycle. The naming convention is `{agent}_triage.md`:
@@ -200,16 +200,17 @@ Available skills (grouped by function):
 
 **Knowledge graph** — build and maintain structured notes:
 
-| Skill              | Purpose                                  |
-| ------------------ | ---------------------------------------- |
-| `extract-entities` | Process synced data into knowledge notes |
-| `manage-tasks`     | Per-person task boards with lifecycle    |
-| `track-candidates` | Recruitment pipeline from email threads  |
-| `analyze-cv`       | CV assessment against career framework   |
-| `right-to-be-forgotten` | GDPR data erasure with audit trail  |
-| `weekly-update`    | Weekly priorities from tasks + calendar  |
-| `process-hyprnote` | Extract entities from Hyprnote sessions  |
-| `organize-files`   | Tidy Desktop/Downloads, chain to extract |
+| Skill                   | Purpose                                  |
+| ----------------------- | ---------------------------------------- |
+| `extract-entities`      | Process synced data into knowledge notes |
+| `manage-tasks`          | Per-person task boards with lifecycle    |
+| `track-candidates`      | Recruitment pipeline from email threads  |
+| `workday-requisition`   | Import candidates from Workday XLSX      |
+| `analyze-cv`            | CV assessment against career framework   |
+| `right-to-be-forgotten` | GDPR data erasure with audit trail       |
+| `weekly-update`         | Weekly priorities from tasks + calendar  |
+| `process-hyprnote`      | Extract entities from Hyprnote sessions  |
+| `organize-files`        | Tidy Desktop/Downloads, chain to extract |
 
 **Communication** — draft, send, and present: