@forwardimpact/basecamp 2.6.1 → 2.8.0

package/template/.claude/skills/{analyze-cv → screen-cv}/SKILL.md

@@ -1,28 +1,33 @@
 ---
-name: analyze-cv
+name: screen-cv
 description: >
-  Analyze candidate CVs against the engineering career framework using
-  fit-pathway as the reference point. Assess skill alignment, identify track
-  fit (forward_deployed vs platform), estimate career level, and produce
-  structured assessments. Use when the user asks to evaluate a CV, compare a
-  candidate to a role, or assess engineering fit.
+  Screen candidate CVs against the engineering career framework to decide
+  whether to invest interview time. Produces a structured screening assessment
+  with interview/pass recommendation and suggested interview focus areas.
+  Use when the user asks to evaluate a CV or when a new CV is detected.
 ---
 
-# Analyze CV
+# Screen CV
 
-Analyze a candidate's CV against the engineering career framework defined in
-`fit-pathway`. Produces a structured assessment: estimated career level, track
-fit, skill alignment, gaps, and a hiring recommendation. Every assessment is
-grounded in the framework — no subjective impressions.
+Screen a candidate's CV against the engineering career framework defined in
+`fit-pathway`. The sole question this skill answers: **is this candidate worth
+interviewing?** Every assessment is grounded in the framework — no subjective
+impressions.
+
+This is Stage 1 of a three-stage hiring pipeline:
+
+1. **Screen CV** (this skill) — CV arrives → interview or pass
+2. **Assess Interview** — transcript arrives → updated evidence profile
+3. **Hiring Decision** — all stages complete → hire or not
 
 ## Trigger
 
 Run this skill:
 
-- When the user asks to analyze, evaluate, or assess a CV
 - When a new CV is added to `knowledge/Candidates/{Name}/`
-- When the user asks "is this person a fit for {role}?"
-- When comparing a candidate's background against a specific job level and track
+- When a CV appears in `~/Downloads/` and is associated with a candidate
+- When the user asks to screen, evaluate, or assess a CV
+- When the user asks "is this person worth interviewing?"
 
 ## Prerequisites
 
@@ -37,13 +42,28 @@ Run this skill:
 - Target role (optional): `{discipline} {level} --track={track}`
 - Existing candidate brief (if available):
   `knowledge/Candidates/{Name}/brief.md`
+- Role file (if candidate has a `Req`): `knowledge/Roles/*.md` — provides
+  `Level`, `Discipline`, `Hiring manager`, and `Domain lead` for
+  more accurate screening
 
 ## Outputs
 
-- `knowledge/Candidates/{Name}/assessment.md` — structured CV assessment
+- `knowledge/Candidates/{Name}/screening.md` — structured screening assessment
 - Updated `knowledge/Candidates/{Name}/brief.md` — skills and summary enriched
   from CV analysis
 
+## Output Filename Convention
+
+The screening assessment MUST be written to `screening.md` — no other filename.
+Do not use `assessment.md`, `cv-screening.md`, `evaluation.md`, or any variant.
+
+Before writing, check whether a file with a different name already exists that
+contains a CV screening (look for `# CV Screening` in the header). If found,
+delete the misnamed file after writing `screening.md` to avoid duplicates.
+
+When linking from `brief.md`, always use the exact text:
+`- [CV Screening](./screening.md)`
+
 ---
 
 ## Step 1: Read the CV
@@ -62,11 +82,31 @@ Read the candidate's CV file. Extract:
 | **Communication**       | Publications, talks, open source, documentation     |
 | **Gender**              | Pronouns, gendered titles (never infer from names)  |
 
+## Step 1b: Read Role File for Context
+
+If the candidate's brief has a `Req` field, look up the corresponding Role file:
+
+```bash
+ls knowledge/Roles/ | grep "{req_number}"
+cat "knowledge/Roles/{matching file}"
+```
+
+The Role file provides:
+
+- **Level** and **Discipline** — use as the target role if no explicit target
+  was specified by the user. This is more accurate than estimating from the CV.
+- **Hiring manager** and **Domain lead** — include in the screening output
+  header for context.
+
+If the Role file specifies a Level and Discipline, use them as the target role
+for framework comparison (unless the user explicitly specified a different
+target).
+
 ## Step 2: Look Up the Framework Reference
 
 Use `fit-pathway` to load the reference data for assessment.
 
-### If a target role is specified
+### If a target role is specified (or derived from the Role file)
 
 ```bash
 # Get the full job definition
@@ -185,42 +225,43 @@ Classify each skill as:
   clear project evidence, **or** meets the level but evidence is thin
 - **Gap** — candidate is two or more levels below expected proficiency
 - **Not evidenced** — CV doesn't mention this skill area. **Treat as a gap** for
-  recommendation purposes — absence of evidence is not evidence of skill
+  screening purposes — absence of evidence is not evidence of skill
 
-**Threshold rule:** If more than **one third** of the target job's skills are
-Gap or Not evidenced, the candidate cannot receive "Proceed." If more than
-**half** are Gap or Not evidenced, the candidate cannot receive "Proceed with
-reservations."
-
-## Step 6: Write Assessment
+## Step 6: Write Screening Assessment
 
-Create `knowledge/Candidates/{Name}/assessment.md`:
+Create `knowledge/Candidates/{Name}/screening.md`:
 
 ```markdown
-# CV Assessment — {Full Name}
+# CV Screening — {Full Name}
 
 **Assessed against:** {Discipline} {Level} — {Track}
+**Req:** {Req number and title, or "—" if no req}
+**Hiring manager:** {Name from Role file, or "—"}
+**Domain lead:** {Name from Role file, or "—"}
 **Date:** {YYYY-MM-DD}
 **CV source:** [{filename}](./{filename})
 
 ## Summary
 
-{2-3 sentence summary: overall fit, key strengths, primary concerns}
+{2-3 sentence summary: overall fit, key strengths, primary concerns.
+Frame around the screening question: is this worth an interview?}
 
 ## Estimated Profile
 
-| Dimension        | Assessment                                |
-| ---------------- | ----------------------------------------- |
-| **Level**        | {estimated level and confidence}          |
-| **Track fit**    | {forward_deployed / platform / either}    |
-| **Discipline**   | {best discipline match}                   |
-| **Gender**       | {Woman / Man / —}                         |
+| Dimension      | Assessment                             |
+| -------------- | -------------------------------------- |
+| **Level**      | {estimated level and confidence}       |
+| **Track fit**  | {forward_deployed / platform / either} |
+| **Discipline** | {best discipline match}                |
+| **Gender**     | {Woman / Man / —}                      |
 
 ## Skill Alignment
 
+Framework reference: `{discipline} {level} --track={track}`
+
 | Skill | Expected | Estimated | Status |
 | --- | --- | --- | --- |
-| {skill} | {framework level} | {CV-based estimate} | {Strong/Adequate/Gap/Not evidenced} |
+| {skill} | {framework level} | {CV-based estimate} | {✅ Strong match / 🟡 Adequate / ❌ Gap / ⬜ Not evidenced} |
 
 ### Key Strengths
 - {Strength 1 — with CV evidence}
@@ -234,28 +275,33 @@ Create `knowledge/Candidates/{Name}/assessment.md`:
 
 | Behaviour | Expected Maturity | CV Evidence | Signal |
 | --- | --- | --- | --- |
-| {behaviour} | {maturity} | {evidence or "—"} | {Strong/Weak/None} |
+| {behaviour} | {maturity} | {evidence or "—"} | {Strong / Weak / None} |
 
 ## Track Fit Analysis
 
 {Paragraph explaining why this candidate fits forward_deployed, platform,
 or could work on either. Reference specific CV evidence.}
 
-## Hiring Recommendation
+## Screening Recommendation
 
 **⚠️ Advisory only — human decision required.**
 
-**Recommendation:** {Proceed / Proceed with reservations / Do not proceed}
+**Recommendation:** {Interview / Interview with focus areas / Pass}
 
 Apply these **decision rules** strictly:
 
-| Recommendation               | Criteria                                                                |
-| ---------------------------- | ----------------------------------------------------------------------- |
-| **Proceed**                  | ≥ 70% Strong match, no core skill gaps, strong behaviour signals        |
-| **Proceed with reservations** | ≥ 50% Strong match, ≤ 2 gaps in non-core skills, no behaviour red flags |
-| **Do not proceed**           | All other candidates — including those with thin evidence               |
+| Recommendation                   | Criteria                                                                  |
+| -------------------------------- | ------------------------------------------------------------------------- |
+| **Interview**                    | ≥ 70% Strong match, no core skill gaps, strong behaviour signals          |
+| **Interview with focus areas**   | ≥ 50% Strong match, ≤ 2 gaps in non-core skills, no behaviour red flags  |
+| **Pass**                         | All other candidates — including those with thin evidence                 |
 
-When in doubt, choose the stricter recommendation. "Proceed with reservations"
+**Threshold rule:** If more than **one third** of the target job's skills are
+Gap or Not evidenced, the candidate cannot receive "Interview." If more than
+**half** are Gap or Not evidenced, the candidate cannot receive "Interview with
+focus areas."
+
+When in doubt, choose the stricter recommendation. "Interview with focus areas"
 should be rare — it signals a strong candidate with a specific, addressable
 concern, not a marginal candidate who might work out.
 
@@ -263,9 +309,24 @@ concern, not a marginal candidate who might work out.
 Reference specific skill gaps or strengths and their impact on the role.
 Explicitly state the skill match percentage and gap count.}
 
-**Interview focus areas:**
-- {Area 1 — what to probe in interviews to validate}
-- {Area 2 — what to probe in interviews to validate}
+## Interview Focus Areas
+
+{Only present if recommendation is Interview or Interview with focus areas.
+These are the specific uncertainties that interviews must resolve.}
+
+- **{Area 1}:** {What to probe and why — link to a specific gap or thin evidence}
+- **{Area 2}:** {What to probe and why — link to a specific gap or thin evidence}
+
+### Suggested Interview Questions
+
+{Generate role-specific questions using the framework:}
+
+```bash
+npx fit-pathway interview {discipline} {level} --track={track}
+```
+
+{Select 3-5 questions most relevant to the identified gaps and focus areas.
+For each question, note which gap or uncertainty it targets.}
 ```
 
 ## Step 7: Enrich Candidate Brief
@@ -275,7 +336,7 @@ If `knowledge/Candidates/{Name}/brief.md` exists, update it with findings:
 - Add or update the **Skills** section with framework skill IDs
 - Update **Summary** if the CV provides better context
 - Set the **Gender** field if identifiable from the CV and not already set
-- Add a link to the assessment: `- [CV Assessment](./assessment.md)`
+- Add a link to the assessment: `- [CV Screening](./screening.md)`
 
 **Use precise edits — don't rewrite the entire file.**
 
@@ -292,10 +353,16 @@ to create the candidate profile from email threads.
 - [ ] "Not evidenced" skills are counted as gaps in the recommendation
 - [ ] Recommendation follows the decision rules table — verify match percentages
       and gap counts before choosing a tier
-- [ ] "Proceed with reservations" is only used for strong candidates with a
+- [ ] "Interview with focus areas" is only used for strong candidates with a
       specific, named concern — never as a soft "maybe"
 - [ ] Track fit analysis references specific skill modifiers from the framework
-- [ ] Gaps are actionable — they suggest interview focus areas
+- [ ] Interview focus areas are specific and tied to identified gaps
+- [ ] Suggested interview questions target the right uncertainties
+- [ ] Output file is named exactly `screening.md` — not `assessment.md` or any
+      variant
+- [ ] No duplicate screening file exists under a different name in the candidate
+      folder
 - [ ] Assessment file uses correct path format and links to CV
-- [ ] Candidate brief updated with skill tags and assessment link
+- [ ] Candidate brief links to screening using exact text
+      `[CV Screening](./screening.md)`
 - [ ] Gender field set only from explicit pronouns/titles (never name-inferred)

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

@@ -28,6 +28,9 @@ Run this skill:
 
 - `~/.cache/fit/basecamp/apple_mail/*.md` — synced email threads
 - `~/.cache/fit/basecamp/apple_mail/attachments/` — CV/resume attachments
+- `~/.cache/fit/basecamp/apple_calendar/*.json` — synced calendar events (for
+  cross-source inference)
+- `knowledge/Roles/*.md` — open role/requisition files (for metadata inheritance)
 - `~/.cache/fit/basecamp/state/graph_processed` — tracks processed files (shared
   with `extract-entities`)
 - `USER.md` — user identity for self-exclusion
@@ -37,6 +40,7 @@ Run this skill:
 - `knowledge/Candidates/{Full Name}/brief.md` — candidate profile note
 - `knowledge/Candidates/{Full Name}/CV.pdf` — local copy of CV (or `CV.docx`)
 - `knowledge/Candidates/{Full Name}/headshot.jpeg` — candidate headshot photo
+- `knowledge/Roles/*.md` — created/updated role files (candidate tables rebuilt)
 - `~/.cache/fit/basecamp/state/graph_processed` — updated with processed threads
 
 ---
@@ -77,6 +81,101 @@ Also scan `knowledge/People/`, `knowledge/Organizations/`, and
 `knowledge/Projects/` to resolve recruiter names, agency orgs, and project
 links.
 
+## Step 0b: Role Sync
+
+Synchronize `knowledge/Roles/` with the current candidate pipeline. This ensures
+role files stay current and enables metadata inheritance.
+
+### Build Role Index
+
+```bash
+ls knowledge/Roles/
+```
+
+Read each Role file's Info block to build a lookup of: Req → Role file path,
+plus Hiring manager, Domain lead, recruiter, Channel for each role.
+
+### Ensure Role Files Exist
+
+Scan all candidate briefs for `**Req:**` values:
+
+```bash
+rg "^\*\*Req:\*\*" knowledge/Candidates/*/brief.md
+```
+
+For each distinct req number found in candidate briefs that does **not** have a
+matching Role file, create a stub Role file:
+
+```markdown
+# {Title from candidate Req field}
+
+## Info
+**Req:** {req number}
+**Title:** {title from Req field}
+**Level:** —
+**Track:** —
+**Discipline:** —
+**Domain lead:** —
+**Hiring manager:** —
+**Locations:** —
+**Positions:** —
+**Channel:** hr
+**Status:** open
+**Opened:** —
+**Last activity:** {today}
+
+## Connected to
+- Staffing/recruitment project
+
+## Candidates
+<!-- Rebuilt each cycle -->
+
+## Notes
+- Stub created automatically — enrich with data from emails, calendar, and imports.
+```
+
+Then attempt to enrich the stub by searching for the req number across the
+knowledge graph:
+
+```bash
+rg "{req_number}" knowledge/
+```
+
+Look for mentions in project timeline entries, People notes, and email threads.
+Extract hiring manager, domain lead, recruiter, locations, and level from the
+surrounding context.
+
+### Rebuild Candidate Tables
+
+For each Role file, rebuild the `## Candidates` table by scanning briefs:
+
+```bash
+rg -l "Req:.*{req_number}" knowledge/Candidates/*/brief.md
+```
+
+For each matching candidate, read their Status and First seen, then rebuild the
+table:
+
+```markdown
+## Candidates
+| Candidate | Status | Channel | First seen |
+|---|---|---|---|
+| [[Candidates/{Name}/brief\|{Name}]] | {status} | {channel} | {date} |
+```
+
+Sort by First seen (newest first).
+
+### Resolve Domain Lead
+
+If a Role file has a hiring manager but no domain lead, attempt to resolve it:
+
+1. Read the hiring manager's People note for a `**Reports to:**` field.
+2. Walk up the reporting chain until reaching a VP or senior leader listed in
+   a stakeholder map or organizational hierarchy note.
+3. Set `Domain lead` on the Role file.
+
+---
+
 ## Step 1: Identify Recruitment Emails
 
 For each new/changed email thread, determine if it contains candidate
@@ -145,6 +244,9 @@ For each candidate found in a recruitment email, extract:
 | **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        |
+| **Channel**           | `hr` or `vendor` — see derivation rules below                | Yes                 |
+| **Hiring manager**    | Cross-source inference — see below                           | If determinable     |
+| **Domain lead**       | Resolved from hiring manager reporting chain                 | If determinable     |
 | **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        |
@@ -153,6 +255,52 @@ For each candidate found in a recruitment email, extract:
 | **LinkedIn**          | Email body, CV                                               | If available        |
 | **Also known as**     | Alternate name spellings or transliterations                 | If available        |
 
+### Determining Channel
+
+Set `Channel` based on the candidate's source:
+
+- **`vendor`** — if the `Source` field links to an `[[Organizations/...]]` that
+  is a recruitment vendor/partner (check the org note for keywords: supplier,
+  recruitment partner, contractor, staffing), or if the `Req` field contains
+  "via {vendor name}" rather than a system ID.
+- **`hr`** — if the candidate came through a hiring system (has a numeric Req),
+  applied internally, or was submitted by an internal recruiter.
+
+### Cross-Source Inference for Hiring Manager and Domain Lead
+
+These fields are rarely available in a single email. Use the following
+resolution chain, stopping at the first match:
+
+1. **Req-first inheritance:** If the candidate has a `Req`, look up the matching
+   `knowledge/Roles/*.md` file. Inherit `Hiring manager` and `Domain lead`
+   from the Role file.
+
+2. **Calendar inference:** Search synced calendar events for interview events
+   mentioning the candidate's name:
+   ```bash
+   rg -l "{Candidate Name}" ~/.cache/fit/basecamp/apple_calendar/
+   ```
+   Read matching events. The **organizer** of an interview event (who is not the
+   user from `USER.md`) is likely the hiring manager. Record this on the
+   candidate brief and update the Role file if it was missing.
+
+3. **Email inference:** In the email thread where the candidate was submitted,
+   check the To/CC fields for internal recipients (besides the user).
+   Cross-reference against `knowledge/People/` notes — if a CC'd person has a
+   role indicating hiring manager, record them.
+
+4. **Reporting chain resolution:** Once a hiring manager is known, look up their
+   People note for a `**Reports to:**` field. Walk up the reporting chain until
+   reaching a VP or senior leader listed in a stakeholder map or organizational
+   hierarchy note — that person is the domain lead.
+
+5. **Staffing project timeline:** Search for the candidate name or their vendor
+   in the staffing/recruitment project notes. Surrounding context often mentions
+   the hiring manager.
+
+If none of these resolve a value, use `—` and leave it for enrichment in future
+cycles as more data arrives.
+
 ### Determining Gender
 
 Record the candidate's gender when **explicitly stated** in the email or CV:
@@ -322,6 +470,9 @@ Then create `knowledge/Candidates/{Full Name}/brief.md`:
 ## Connected to
 - [[Organizations/{Agency}]] — sourced by
 - [[People/{Recruiter}]] — recruiter
+- [[Roles/{Role filename without .md}]] — applied to
+- [[People/{Hiring manager}]] — hiring manager
+- [[People/{Domain lead}]] — domain lead
 
 ## Pipeline
 - **{date}**: {event}
@@ -348,7 +499,10 @@ available:
 
 ```markdown
 **Role:** {internal requisition profile, e.g. "Staff Engineer"}
-**Req:** {requisition ID, e.g. "4950237 — Principal Software Engineer"}
+**Req:** {requisition ID — backlink to Role file, e.g. "[[Roles/4950237 — PSE Forward Deployed|4950237]]"}
+**Channel:** {hr / vendor}
+**Hiring manager:** {[[People/{name}]] or "—"}
+**Domain lead:** {[[People/{name}]] or "—"}
 **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}
@@ -358,6 +512,12 @@ available:
 **Also known as:** {alternate name spellings}
 ```
 
+When a `Req` is known, the value should backlink to the corresponding Role file
+in `knowledge/Roles/`. Use the format:
+`[[Roles/{filename without .md}|{req number}]] — {title}` for system reqs, or
+`[[Roles/{filename without .md}|Vendor]] — {description}` for vendor pipeline
+candidates.
+
 ### Additional Sections
 
 Some candidates accumulate richer profiles over time. These optional sections go
@@ -413,11 +573,12 @@ Format: one bullet per insight under `## Placement Notes`, with
 
 After writing candidate notes, verify links go both ways:
 
-| If you add...            | Then also add...                            |
-| ------------------------ | ------------------------------------------- |
-| Candidate → Organization | Organization → Candidate                    |
-| Candidate → Recruiter    | Recruiter → Candidate (in Activity section) |
-| Candidate → Project      | Project → Candidate (in People section)     |
+| If you add...            | Then also add...                                          |
+| ------------------------ | --------------------------------------------------------- |
+| Candidate → Organization | Organization → Candidate                                  |
+| Candidate → Recruiter    | Recruiter → Candidate (in Activity section)               |
+| Candidate → Project      | Project → Candidate (in People section)                   |
+| Candidate → Role         | Role → Candidate (in Candidates table — rebuilt by sync)  |
 
 Use absolute paths: `[[Candidates/Name/brief|Name]]`,
 `[[Organizations/Agency]]`, `[[People/Recruiter]]`.
@@ -449,8 +610,8 @@ Use framework skill IDs (e.g. `data_integration`, `full_stack_development`,
 `architecture_and_design`) in the **Skills** section of the candidate brief
 instead of free-form tags. This enables consistent cross-candidate comparison.
 
-If a candidate has a CV attachment, flag them for the `analyze-cv` skill which
-produces a full framework-aligned assessment.
+If a candidate has a CV attachment, flag them for the `screen-cv` skill which
+produces a framework-aligned screening assessment.
 
 ## Quality Checklist
 
@@ -473,5 +634,11 @@ produces a full framework-aligned assessment.
 - [ ] Skills tagged using framework skill IDs where possible
 - [ ] Gender field populated only from explicit pronouns/titles (never
       name-inferred)
+- [ ] Channel field set on every candidate (`hr` or `vendor`)
+- [ ] Hiring manager and Domain lead populated via cross-source inference where
+      determinable
+- [ ] Req field backlinks to corresponding Role file in `knowledge/Roles/`
+- [ ] Connected to section includes backlink to Role file
+- [ ] Role files have up-to-date Candidates tables (rebuilt by Step 0b)
 - [ ] Headshots searched in email attachments and `~/Downloads/` (recursive)
 - [ ] Found headshots copied as `headshot.jpeg` into candidate directory

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

@@ -43,6 +43,7 @@ Run this skill:
 
 - `knowledge/Candidates/{Full Name}/brief.md` — candidate profile note
 - `knowledge/Candidates/{Full Name}/CV.md` — resume text rendered as markdown
+- `knowledge/Roles/{Req ID} — {Title}.md` — created or updated role file
 - Updated existing candidate briefs if candidate already exists
 
 ---
@@ -161,6 +162,76 @@ 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 1b: Create or Update Role File
+
+After parsing the export, create or update the corresponding Role file in
+`knowledge/Roles/`. The filename convention is `{Req ID} — {Short Title}.md`.
+
+```bash
+ls knowledge/Roles/ | grep "{Req ID}"
+```
+
+### If the Role file does NOT exist
+
+Create it using the requisition metadata from the export:
+
+```markdown
+# {Requisition Title}
+
+## Info
+**Req:** {Req ID}
+**Title:** {Full title from export}
+**Level:** {Infer from title: "Principal" → J100, "Staff" → J090, "Director" → J100 M-track, "Senior" → J070}
+**Track:** {P-track for IC roles, M-track for Director/Manager roles}
+**Discipline:** {Infer: "Software Engineer" → software_engineering, "Data Engineer" → data_engineering, "Data Scientist" → data_science}
+**Domain lead:** —
+**Hiring manager:** {From export metadata if available, or "—"}
+**Locations:** {Primary Location from export}
+**Positions:** —
+**Channel:** hr
+**Status:** open
+**Opened:** {Recruiting Start Date from export}
+**Last activity:** {today}
+
+## Connected to
+- Staffing/recruitment project
+
+## Candidates
+<!-- Rebuilt by track-candidates role sync -->
+
+## Notes
+- Created from requisition export on {today}.
+```
+
+### Resolving Domain Lead
+
+The export rarely contains organizational hierarchy information directly. Use
+cross-referencing to resolve it:
+
+1. **Search the knowledge graph** for mentions of the req number:
+   ```bash
+   rg "{Req ID}" knowledge/
+   ```
+   Look in project timelines, People notes, and Topics for context about which
+   area/VP owns this req.
+
+2. **Check the Hiring Manager** (if available from export): look up their People
+   note for `**Reports to:**` and walk up the chain to a VP or senior leader in
+   a stakeholder map or organizational hierarchy note.
+
+3. **Fallback**: If neither resolves, set `Domain lead: —` for enrichment by
+   later cycles of `track-candidates` or `extract-entities`.
+
+### If the Role file ALREADY exists
+
+Update it with any new metadata from the export:
+
+- Set `Hiring manager` if the export provides it and the Role file has `—`
+- Update `Last activity` to today
+- Add a Notes entry: `- Requisition export processed on {today}: {N} candidates`
+
+---
+
 ## Step 2: Build Candidate Index
 
 Scan existing candidate notes to avoid duplicates:
@@ -259,7 +330,10 @@ Then create `knowledge/Candidates/{Clean Name}/brief.md` using the
 **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}
+**Req:** [[Roles/{Role filename without .md}|{Req ID}]] — {Req Title}
+**Channel:** hr
+**Hiring manager:** {From Role file or "—"}
+**Domain lead:** {From Role file or "—"}
 **Internal/External:** {Internal / External / External (Prior Worker)}
 **Current title:** {Current Job Title at Current Company}
 **Email:** {Email or "—"}
@@ -273,6 +347,9 @@ strengths. If no resume text, use Current Job Title + Total Years Experience.}
 - [CV.md](./CV.md)
 
 ## Connected to
+- [[Roles/{Role filename without .md}]] — applied to
+- {[[People/{Hiring manager}]] — hiring manager, if known}
+- {[[People/{Domain lead}]] — domain lead, if known}
 - {Referred by person, if present}
 
 ## Pipeline
@@ -351,8 +428,8 @@ 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.
+has a CV.md, flag them for the `screen-cv` skill for a framework-aligned
+screening assessment.
 
 ## Quality Checklist
 
@@ -369,6 +446,11 @@ assessment.
 - [ ] 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)
+- [ ] Gender field set to `—` (exports don't include gender signals)
+- [ ] Role file created or updated in `knowledge/Roles/`
+- [ ] Channel set to `hr` on all imported candidates
+- [ ] Hiring manager and Domain lead inherited from Role file where available
+- [ ] Req field backlinks to Role file
+- [ ] Connected to section includes backlink to Role file
 - [ ] Insights.md updated with strategic observations
 - [ ] No duplicate candidate directories created