@forwardimpact/outpost 3.0.3

package/templates/.claude/skills/req-screen/references/rubric.md

@@ -0,0 +1,94 @@
+# Screening Rubric
+
+Reference data for `req-screen` Steps 1, 3, 4, 5, and 6 (recommendation).
+
+## What to extract from the CV
+
+| Field                   | What to look for                                               |
+| ----------------------- | -------------------------------------------------------------- |
+| **Current role**        | Most recent job title                                          |
+| **Years of experience** | Total and per-role tenure                                      |
+| **Technical skills**    | Languages, platforms, agent-aligned standards, tools mentioned |
+| **Domain experience**   | Industries, business domains, customer-facing work             |
+| **Education**           | Degrees, certifications, relevant courses                      |
+| **Leadership signals**  | Team size, mentoring, cross-team work, architecture            |
+| **Scope signals**       | Scale of systems, user base, revenue impact                    |
+| **Communication**       | Publications, talks, open source, documentation                |
+| **Gender**              | Pronouns or gendered titles only — never inferred from names   |
+
+## Level estimation heuristics
+
+| CV signal                                    | Likely level     |
+| -------------------------------------------- | ---------------- |
+| 0–2 years, junior titles, learning signals   | J040 (Level I)   |
+| 2–5 years, mid-level titles, independent     | J060 (Level II)  |
+| 5–8 years, senior titles, mentoring signals  | J070 (Level III) |
+| 8–12 years, staff/lead titles, area scope    | J090 (Staff)     |
+| 12+ years, principal titles, org-wide impact | J100 (Principal) |
+
+## Track-fit signals
+
+| Forward Deployed signals             | Platform signals                        |
+| ------------------------------------ | --------------------------------------- |
+| Customer-facing projects             | Internal tooling / shared services      |
+| Business domain immersion            | Infrastructure / platform-as-product    |
+| Rapid prototyping, MVPs              | Architecture, system design             |
+| Data integration, analytics          | CI/CD, DevOps, reliability              |
+| Stakeholder management               | Code quality, technical-debt management |
+| Cross-functional work                | Scalability, performance engineering    |
+| Multiple industries / domain breadth | Deep platform ownership                 |
+
+## Proficiency mapping
+
+| Proficiency    | CV evidence                                             |
+| -------------- | ------------------------------------------------------- |
+| `awareness`    | Mentioned but no project evidence                       |
+| `foundational` | Used in projects, basic application                     |
+| `working`      | Primary tool/skill in multiple roles, independent usage |
+| `practitioner` | Led teams using this skill, mentored others, deep work  |
+| `expert`       | Published, shaped org practice, industry recognition    |
+
+### Scepticism rule
+
+CVs inflate. Default **two levels below** what the CV implies unless the
+candidate provides concrete, quantified evidence (metrics, named systems, team
+sizes, user/revenue scale). Vague phrases like "improved performance" or "led
+initiatives" do not count. A skill listed only in a "Skills" section with no
+project context is `awareness` at most.
+
+## Behaviour signals
+
+| Behaviour                  | CV evidence                                        |
+| -------------------------- | -------------------------------------------------- |
+| Own the Outcome            | End-to-end ownership, P&L impact, delivery metrics |
+| Think in Systems           | Architecture decisions, system-wide reasoning      |
+| Communicate with Precision | Technical writing, documentation, talks            |
+| Be Polymath Oriented       | Cross-domain work, diverse tech stack              |
+| Don't Lose Your Curiosity  | Side projects, continuous learning, certifications |
+
+## Skill alignment classification
+
+- **Strong match** — meets or exceeds expected proficiency **and** evidence is
+  concrete (metrics, project specifics, scope indicators).
+- **Adequate** — exactly one level below expected with clear project evidence,
+  **or** at level but evidence thin.
+- **Gap** — two or more levels below expected.
+- **Not evidenced** — CV doesn't mention this skill area. **Treat as a gap**:
+  absence of evidence is not evidence of skill.
+
+## Recommendation decision rules
+
+| 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**                       | Everything else — including thin evidence                                |
+
+**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 — strong candidate with a specific, named concern, not a marginal
+candidate.

package/templates/.claude/skills/req-screen/references/template.md

@@ -0,0 +1,91 @@
+# Screening Output Template
+
+Reference template for `req-screen` Step 6. Save to
+`knowledge/Candidates/{Name}/screening.md`. Filename **must** be `screening.md`
+— not `assessment.md`, `cv-screening.md`, or any variant. If a misnamed
+screening file exists in the folder (look for `# CV Screening` in the header),
+delete it after writing.
+
+```markdown
+# CV Screening — {Full Name}
+
+**Assessed against:** {Discipline} {Level} — {Track}
+**Req:** {Req number and title, or "—"}
+**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 sentences: 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 / —}                      |
+
+## Skill Alignment
+
+Standard reference: `{discipline} {level} --track={track}`
+
+| Skill | Expected | Estimated | Status |
+| --- | --- | --- | --- |
+| {skill} | {standard level} | {CV-based estimate} | {✅ Strong / 🟡 Adequate / ❌ Gap / ⬜ Not evidenced} |
+
+### Key Strengths
+- {Strength 1 — with CV evidence}
+- {Strength 2 — with CV evidence}
+
+### Key Gaps
+- {Gap 1 — what's missing and why it matters}
+- {Gap 2 — what's missing and why it matters}
+
+## Behaviour Indicators
+
+| Behaviour | Expected Maturity | CV Evidence | Signal |
+| --- | --- | --- | --- |
+| {behaviour} | {maturity} | {evidence or "—"} | {Strong / Weak / None} |
+
+## Track Fit Analysis
+
+{Paragraph explaining why the candidate fits forward_deployed,
+platform, or either. Reference specific CV evidence.}
+
+## Screening Recommendation
+
+**⚠️ Advisory only — human decision required.**
+
+**Recommendation:** {Interview / Interview with focus areas / Pass}
+
+**Rationale:** {3–5 sentences grounded in standard data. Cite specific
+gaps or strengths, the skill match percentage, and the gap count.}
+
+## Interview Focus Areas
+
+{Only when the recommendation is Interview or Interview with focus
+areas. These are uncertainties the 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}
+
+### Suggested Interview Questions
+
+Generate with `bunx fit-pathway interview {discipline} {level}
+--track={track}`. Pick 3–5 questions most relevant to the gaps and
+focus areas; note which gap each targets.
+```
+
+## Brief link
+
+In `brief.md`, link the screening with this exact text:
+
+```markdown
+- [CV Screening](./screening.md)
+```

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

@@ -0,0 +1,189 @@
+---
+name: req-track
+description: Scan synced email threads for recruitment candidates, extract structured profiles, and create/update notes in knowledge/Candidates/. Use when the user asks to track candidates, process recruitment emails, or update the hiring pipeline.
+---
+
+# Track Candidates
+
+Scan synced email threads from `~/.cache/fit/outpost/apple_mail/` for
+recruitment candidates. Extract structured candidate profiles and create or
+update notes in `knowledge/Candidates/`. Builds a local, searchable recruitment
+pipeline from scattered email threads.
+
+## Trigger
+
+- The user asks to track, process, or update candidates.
+- The user asks about recruitment pipeline status.
+- After `sync-apple-mail` has pulled new threads.
+
+## Prerequisites
+
+- Synced email data in `~/.cache/fit/outpost/apple_mail/` (from
+  `sync-apple-mail`).
+- User identity configured in `USER.md`.
+
+## Inputs
+
+- `~/.cache/fit/outpost/apple_mail/*.md` — synced email threads.
+- `~/.cache/fit/outpost/apple_mail/attachments/` — CV/resume attachments.
+- `~/.cache/fit/outpost/apple_calendar/*.json` — calendar events (for
+  cross-source inference).
+- `knowledge/Roles/*.md` — open role/requisition files (metadata inheritance).
+- `~/.cache/fit/outpost/state/graph_processed` — processed-file index (shared
+  with `extract-entities`).
+- `USER.md` — user identity for self-exclusion.
+
+## Outputs
+
+- `knowledge/Candidates/{Full Name}/brief.md` — candidate profile note.
+- `knowledge/Candidates/{Full Name}/CV.pdf` (or `CV.docx`) — local CV copy.
+- `knowledge/Candidates/{Full Name}/headshot.jpeg` — candidate photo.
+- `knowledge/Roles/*.md` — created/updated role files (Candidates tables
+  rebuilt).
+- `~/.cache/fit/outpost/state/graph_processed` — updated with processed threads.
+
+<do_confirm_checklist goal="Verify candidate processing batch is complete and
+correct">
+
+- [ ] Required Info fields present on every brief (Title, Source, Status, First
+      seen, Last activity, Channel).
+- [ ] Pipeline status reflects latest thread activity; timeline in chronological
+      order.
+- [ ] Bidirectional links present (Candidate ↔ Org / Recruiter / Role /
+      Project).
+- [ ] Role files synced — Candidates tables rebuilt, stubs created for any
+      unknown reqs.
+- [ ] CV and headshot copied into the candidate directory when available.
+- [ ] Skills tagged with agent-aligned engineering standard IDs from
+      `bunx fit-pathway skill --list`.
+- [ ] Gender field populated only from explicit pronouns or titles.
+- [ ] No duplicate candidate notes; all processed threads marked in the state
+      file.
+
+</do_confirm_checklist>
+
+## Procedure
+
+Process **10 files per run**.
+
+### 1. Load context and pick the batch
+
+Read `USER.md` for the user's name, email, and domain. List new or changed
+source files:
+
+```bash
+node .claude/skills/extract-entities/scripts/state.mjs check
+```
+
+Filter the output to `apple_mail/*.md` only — calendar files are not relevant
+here.
+
+### 2. Build candidate, people, and org indexes
+
+```bash
+ls -d knowledge/Candidates/*/
+```
+
+Read each existing brief's header (Name, Role, Source, Status) to build a mental
+index. Also scan `knowledge/People/`, `knowledge/Organizations/`, and
+`knowledge/Projects/` to resolve recruiter names, agency orgs, and project
+links.
+
+### 3. Sync `knowledge/Roles/`
+
+This keeps role metadata current and enables inheritance.
+
+1. Read each Role file's Info block to map Req → Role file path, Hiring manager,
+   Domain lead, recruiter, Channel.
+2. Find Reqs referenced by candidate briefs but missing a Role file:
+   `rg "^\*\*Req:\*\*" knowledge/Candidates/*/brief.md`. For each missing Req,
+   create a stub using the **Role file stub** in
+   [references/templates.md](references/templates.md), then enrich by searching
+   the graph: `rg "{req_number}" knowledge/`.
+3. Rebuild each Role file's `## Candidates` table by scanning briefs:
+   `rg -l "Req:.*{req_number}" knowledge/Candidates/*/brief.md`. Use the **Role
+   Candidates table** format from `references/templates.md`. Sort by First seen,
+   newest first.
+4. If a Role file has a hiring manager but no domain lead, walk the
+   `**Reports to:**` chain in `knowledge/People/` to a VP or senior leader.
+
+### 4. Identify recruitment threads
+
+For each thread in the batch, decide whether it contains recruitment content
+using the signals in [references/signals.md](references/signals.md). Skip
+threads that match no signal.
+
+### 5. Extract candidate data
+
+For each candidate found, populate the field map from
+[references/fields.md](references/fields.md). That reference covers field
+sources, the `Channel` rule, the hiring-manager / domain-lead resolution chain,
+gender rules, source/recruiter resolution, CV copying, and headshot discovery.
+
+### 6. Determine pipeline status
+
+Assign a status using the table and advancement signals in
+[references/statuses.md](references/statuses.md). Default to `new`. Read the
+full thread chronologically; the most recent signal wins.
+
+### 7. Build the pipeline timeline
+
+Extract a chronological timeline — one `**{date}**: {event}` line per meaningful
+event, capturing who did what. Skip noise (signature blocks, disclaimers,
+forwarded headers).
+
+### 8. Write or update the candidate note
+
+For **new** candidates, create `knowledge/Candidates/{Full Name}/brief.md` from
+the **Candidate brief** template in
+[references/templates.md](references/templates.md). Place the **Extra Info
+fields** after `Last activity` in the order shown there. Add the **Optional
+sections** when data warrants. Omit `## CV` if no attachment.
+
+For **existing** candidates, apply targeted edits — do not rewrite the file:
+update `Status` and `Last activity`, append Pipeline entries, fill in newly
+known Info fields, and add new Skills.
+
+### 9. Capture cross-candidate insights
+
+Update `knowledge/Candidates/Insights.md` only when an observation is
+high-signal: candidate may suit a **different role**, is a **strong match** for
+a specific team or leader, a meaningful **comparison between candidates**, or a
+hiring trade-off needs to be **remembered across sessions**.
+
+Skip per-candidate status and generic strengths/weaknesses — those belong on
+`brief.md`. Format: one bullet under `## Placement Notes` with
+`[[Candidates/Name/brief|Name]]` and relevant people/org backlinks.
+
+### 10. Ensure bidirectional links
+
+| If you add...            | Then also add...                                           |
+| ------------------------ | ---------------------------------------------------------- |
+| Candidate → Organization | Organization → Candidate                                   |
+| Candidate → Recruiter    | Recruiter → Candidate (in Activity)                        |
+| Candidate → Project      | Project → Candidate (in People section)                    |
+| Candidate → Role         | Role → Candidate (in Candidates table — rebuilt by Step 3) |
+
+Use absolute paths: `[[Candidates/Name/brief|Name]]`,
+`[[Organizations/Agency]]`, `[[People/Recruiter]]`. Only add a backlink when the
+target note doesn't already reference the candidate.
+
+### 11. Mark each thread processed
+
+```bash
+node .claude/skills/extract-entities/scripts/state.mjs update "{file_path}"
+```
+
+Shares state with `extract-entities`, so the thread won't be re-scanned by
+either skill until it changes.
+
+### 12. Tag skills against the standard
+
+```bash
+bunx fit-pathway skill --list
+```
+
+Use agent-aligned engineering standard IDs (e.g. `data_integration`,
+`full_stack_development`, `architecture_and_design`) in the `## Skills` section
+instead of free-form tags. Flag any candidate with a CV attachment for
+`req-screen`.

package/templates/.claude/skills/req-track/references/fields.md

@@ -0,0 +1,114 @@
+# Candidate Field Extraction
+
+Field map and resolution rules for Step 2 of `req-track`.
+
+## Fields
+
+| Field             | Source                                                       | Required            |
+| ----------------- | ------------------------------------------------------------ | ------------------- |
+| 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            | Pronouns or gendered titles only                             | 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        |
+| Channel           | `hr` or `vendor` — see below                                 | Yes                 |
+| Hiring manager    | Cross-source inference — see below                           | If determinable     |
+| Domain lead       | Resolved from hiring manager's 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        |
+| 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        |
+
+## Channel
+
+- `vendor` — Source links to an `[[Organizations/...]]` flagged as
+  vendor/partner (keywords: supplier, recruitment partner, contractor,
+  staffing), or Req contains "via {vendor name}" rather than a system ID.
+- `hr` — candidate came through a hiring system (numeric Req), applied
+  internally, or was submitted by an internal recruiter.
+
+## Hiring manager and domain lead — resolution chain
+
+Stop at the first match:
+
+1. **Req-first inheritance** — look up `knowledge/Roles/*.md` for the matching
+   Req; inherit Hiring manager and Domain lead from the Role file.
+2. **Calendar inference** —
+   `rg -l "{Candidate Name}" ~/.cache/fit/outpost/apple_calendar/`. The non-user
+   organizer of an interview event is likely the hiring manager.
+3. **Email inference** — internal To/CC recipients (besides the user)
+   cross-checked against `knowledge/People/`.
+4. **Reporting chain** — read the hiring manager's `**Reports to:**` field; walk
+   up to a VP / senior leader for the domain lead.
+5. **Staffing project timeline** — search staffing notes for the candidate or
+   vendor; surrounding context often names the manager.
+
+If none resolve, set `—` and revisit on the next cycle.
+
+## Gender
+
+Record only when **explicitly stated**:
+
+- Pronouns from the recruiter ("she is available", "her CV attached")
+- Gendered titles ("Ms.", "Mrs.", "Mr.")
+
+Record as `Woman`, `Man`, or `—` (unknown). When uncertain, use `—`. **Never
+infer gender from names** — name-based inference is unreliable and culturally
+biased. The field supports aggregate diversity tracking; it has no bearing on
+hiring decisions, assessment criteria, or candidate visibility.
+
+## Source and recruiter
+
+- Map sender email domain to an organization in `knowledge/Organizations/`.
+- The person who sent or forwarded the profile is the recruiter — link with
+  `[[People/Name]]`.
+- Create the organization or recruiter notes if missing.
+
+## CV attachment
+
+```bash
+ls ~/.cache/fit/outpost/apple_mail/attachments/{thread_id}/
+mkdir -p "knowledge/Candidates/{Full Name}"
+cp "~/.cache/fit/outpost/apple_mail/attachments/{thread_id}/{file}" \
+   "knowledge/Candidates/{Full Name}/CV.pdf"
+```
+
+Use `CV.pdf` (PDF) or `CV.docx` (Word). The `## CV` link is `./CV.pdf`.
+
+## Headshot discovery
+
+Search both locations:
+
+1. **Email attachments** —
+   `~/.cache/fit/outpost/apple_mail/attachments/{thread_id}/`. Filter to
+   portrait images (skip logos, signatures, `image001.png`).
+2. **Downloads** —
+
+   ```bash
+   find ~/Downloads -maxdepth 3 -type f \
+     \( -iname "*.jpg" -o -iname "*.jpeg" \
+       -o -iname "*.png" -o -iname "*.heic" \) 2>/dev/null
+   ```
+
+Match by name fragment (case-insensitive). Prefer the Downloads match. Always
+write `headshot.jpeg`:
+
+```bash
+cp "{src}" "knowledge/Candidates/{Full Name}/headshot.jpeg"
+# PNG → JPEG
+magick "{src}.png" "knowledge/Candidates/{Full Name}/headshot.jpeg"
+# HEIC → JPEG
+magick "{src}.heic" "knowledge/Candidates/{Full Name}/headshot.jpeg"
+```

package/templates/.claude/skills/req-track/references/signals.md

@@ -0,0 +1,42 @@
+# Recruitment Signals
+
+Decide whether an email thread is recruitment-related. Skip threads that match
+no signal — most email is not.
+
+## CV/resume attachments
+
+`~/.cache/fit/outpost/apple_mail/attachments/{thread_id}/` contains `.pdf` or
+`.docx` files with candidate names in the filename.
+
+## Recruiter sender domains
+
+Sender domain maps to an organization in `knowledge/Organizations/` tagged as a
+recruitment agency. When no agencies are catalogued yet, treat these patterns as
+hints:
+
+- Multiple candidates presented by the same sender
+- Structured profile formatting (rate, availability, skills)
+- Forwarding candidate CVs on behalf of others
+
+## Profile presentation patterns
+
+Structured candidate descriptions containing:
+
+- "Rate:" or rate/cost information
+- "Availability:" or notice period
+- "English:" or language level
+- "Location:" or country/city
+- Candidate name + role formatting (e.g. "Staff Software Engineer")
+- "years of experience" / "YoE"
+- Skills/tech stack listings
+
+## Interview scheduling
+
+- "schedule a call", "schedule an interview"
+- "first interview", "second interview", "technical interview"
+- "interview slot", "available for a call"
+
+## Follow-up on existing candidates
+
+A thread mentions a candidate already in `knowledge/Candidates/` by name —
+process it to update pipeline status.

package/templates/.claude/skills/req-track/references/statuses.md

@@ -0,0 +1,32 @@
+# Pipeline Statuses
+
+Used by Step 3 of `req-track`. Default to `new` if no advancement signals are
+found. Read the full thread chronologically; the most recent signal wins.
+
+## Statuses
+
+| Status             | Signal                                                |
+| ------------------ | ----------------------------------------------------- |
+| `new`              | CV/profile received, no response yet                  |
+| `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         |
+
+## Advancement signals (hiring-manager 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`
+- No response to profile → remains `new`