@forwardimpact/basecamp 2.9.1 → 2.9.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@forwardimpact/basecamp",
-  "version": "2.9.1",
+  "version": "2.9.2",
   "description": "Claude Code-native personal knowledge system with autonomous agents",
   "license": "Apache-2.0",
   "repository": {

package/template/.claude/agents/recruiter.md

@@ -30,11 +30,11 @@ reference framework data — never rely on subjective impressions.
 Every candidate progresses through three assessment stages. Each stage has a
 dedicated skill and produces a specific artifact:
 
-| Stage | Skill | Trigger | Output | Decision |
-|-------|-------|---------|--------|----------|
-| 1. Screen | `screen-cv` | CV arrives | `screening.md` | Interview or Pass |
-| 2. Assess | `assess-interview` | Transcript arrives | `interview-{date}.md`, `panel.md` | Continue or Pass |
-| 3. Decide | `hiring-decision` | All stages complete | `recommendation.md` | Hire or Not |
+| Stage     | Skill              | Trigger             | Output                            | Decision          |
+| --------- | ------------------ | ------------------- | --------------------------------- | ----------------- |
+| 1. Screen | `screen-cv`        | CV arrives          | `screening.md`                    | Interview or Pass |
+| 2. Assess | `assess-interview` | Transcript arrives  | `interview-{date}.md`, `panel.md` | Continue or Pass  |
+| 3. Decide | `hiring-decision`  | All stages complete | `recommendation.md`               | Hire or Not       |
 
 **Stage progression rules:**
 

package/template/.claude/skills/assess-interview/SKILL.md

@@ -46,8 +46,8 @@ Run this skill:
 ## Outputs
 
 - `knowledge/Candidates/{Name}/interview-{date}.md` — per-interview assessment
-- `knowledge/Candidates/{Name}/panel.md` — brief for next-stage
-  interviewers (if further interviews are planned)
+- `knowledge/Candidates/{Name}/panel.md` — brief for next-stage interviewers (if
+  further interviews are planned)
 - Updated `knowledge/Candidates/{Name}/brief.md` — pipeline and notes enriched
 
 ---
@@ -56,19 +56,19 @@ Run this skill:
 
 Read the transcript file(s). For each transcript, extract:
 
-| Field                         | What to look for                                          |
-| ----------------------------- | --------------------------------------------------------- |
-| **Interview type**            | Screening, decomposition, panel, technical, etc.          |
-| **Interviewers**              | Who conducted the interview                               |
-| **Date**                      | When the interview took place                             |
-| **Skill demonstrations**      | Concrete examples of skills applied in real-time          |
-| **Behaviour observations**    | How the candidate acted under pressure, with others       |
-| **Self-identified strengths** | What the candidate claims they're good at                 |
-| **Self-identified gaps**      | What the candidate acknowledges as growth areas           |
-| **Red flags**                 | Contradictions with CV, concerning patterns               |
-| **Interviewer feedback**      | Direct quotes or observations from interviewers           |
-| **Level signals**             | Autonomy, scope, complexity demonstrated in responses     |
-| **Track signals**             | Business immersion vs platform thinking in their answers  |
+| Field                         | What to look for                                         |
+| ----------------------------- | -------------------------------------------------------- |
+| **Interview type**            | Screening, decomposition, panel, technical, etc.         |
+| **Interviewers**              | Who conducted the interview                              |
+| **Date**                      | When the interview took place                            |
+| **Skill demonstrations**      | Concrete examples of skills applied in real-time         |
+| **Behaviour observations**    | How the candidate acted under pressure, with others      |
+| **Self-identified strengths** | What the candidate claims they're good at                |
+| **Self-identified gaps**      | What the candidate acknowledges as growth areas          |
+| **Red flags**                 | Contradictions with CV, concerning patterns              |
+| **Interviewer feedback**      | Direct quotes or observations from interviewers          |
+| **Level signals**             | Autonomy, scope, complexity demonstrated in responses    |
+| **Track signals**             | Business immersion vs platform thinking in their answers |
 
 ## Step 2: Load Framework Reference
 
@@ -122,23 +122,23 @@ how someone acts, not what they've done.
 
 For each framework behaviour, look for:
 
-| Behaviour                  | Interview Evidence                                              |
-| -------------------------- | --------------------------------------------------------------- |
-| Own the Outcome            | Takes responsibility, doesn't deflect, drives to resolution     |
-| Think in Systems           | Considers second-order effects, trade-offs, system boundaries   |
-| Communicate with Precision | Clear explanations, appropriate detail level, listens actively  |
-| Be Polymath Oriented       | Draws on diverse knowledge, makes unexpected connections        |
-| Don't Lose Your Curiosity  | Asks good questions, explores alternatives, admits not knowing  |
+| Behaviour                  | Interview Evidence                                             |
+| -------------------------- | -------------------------------------------------------------- |
+| Own the Outcome            | Takes responsibility, doesn't deflect, drives to resolution    |
+| Think in Systems           | Considers second-order effects, trade-offs, system boundaries  |
+| Communicate with Precision | Clear explanations, appropriate detail level, listens actively |
+| Be Polymath Oriented       | Draws on diverse knowledge, makes unexpected connections       |
+| Don't Lose Your Curiosity  | Asks good questions, explores alternatives, admits not knowing |
 
 Rate each behaviour using maturity levels:
 
-| Maturity        | Interview Signal                                              |
-| --------------- | ------------------------------------------------------------- |
-| `emerging`      | Behaviour not observed or only when prompted                  |
-| `developing`    | Behaviour present but inconsistent or surface-level           |
-| `practicing`    | Behaviour consistent and natural throughout the interview     |
-| `role_modeling` | Behaviour demonstrated at high level, influenced the room     |
-| `exemplifying`  | Behaviour exceptional, set the standard for the conversation  |
+| Maturity        | Interview Signal                                             |
+| --------------- | ------------------------------------------------------------ |
+| `emerging`      | Behaviour not observed or only when prompted                 |
+| `developing`    | Behaviour present but inconsistent or surface-level          |
+| `practicing`    | Behaviour consistent and natural throughout the interview    |
+| `role_modeling` | Behaviour demonstrated at high level, influenced the room    |
+| `exemplifying`  | Behaviour exceptional, set the standard for the conversation |
 
 ## Step 5: Assess Level Fit
 
@@ -150,13 +150,13 @@ should change:
 npx fit-pathway progress {discipline} {level} --track={track}
 ```
 
-| Level Signal in Interview                                            | Implication                    |
+| Level Signal in Interview                                           | Implication                    |
 | ------------------------------------------------------------------- | ------------------------------ |
-| Candidate needed guidance on structuring their approach              | Level may be lower than est.   |
-| Candidate self-directed, made sound trade-offs independently         | Level estimate confirmed        |
-| Candidate mentored or coached others during the exercise             | Level may be higher than est.  |
-| Candidate struggled with complexity appropriate to the target level  | Level should be downgraded     |
-| Interviewer explicitly suggested a different level                   | Strong signal — weight heavily |
+| Candidate needed guidance on structuring their approach             | Level may be lower than est.   |
+| Candidate self-directed, made sound trade-offs independently        | Level estimate confirmed       |
+| Candidate mentored or coached others during the exercise            | Level may be higher than est.  |
+| Candidate struggled with complexity appropriate to the target level | Level should be downgraded     |
+| Interviewer explicitly suggested a different level                  | Strong signal — weight heavily |
 
 ## Step 6: Write Interview Assessment
 
@@ -368,7 +368,8 @@ Update `knowledge/Candidates/{Name}/brief.md`:
 
 - Add the interview to the **Pipeline** section with date, type, and outcome
 - Add **Interview Notes** section if not present, with key observations
-- Link to the interview assessment: `- [Interview Assessment](./interview-{date}.md)`
+- Link to the interview assessment:
+  `- [Interview Assessment](./interview-{date}.md)`
 - Link to panel brief if created: `- [Panel Brief](./panel.md)`
 - Update **Status** field to reflect current pipeline stage
 

package/template/.claude/skills/extract-entities/SKILL.md

@@ -401,8 +401,8 @@ Scan email subjects and bodies for requisition numbers (e.g. 7-digit Workday
 IDs). When found:
 
 1. Check if a Role file exists: `ls knowledge/Roles/ | grep "{req_number}"`
-2. If **no Role file exists**, create a stub (see `track-candidates` Step 0b
-   for the template). Search the knowledge graph for context:
+2. If **no Role file exists**, create a stub (see `track-candidates` Step 0b for
+   the template). Search the knowledge graph for context:
    ```bash
    rg "{req_number}" knowledge/
    ```
@@ -412,6 +412,7 @@ IDs). When found:
 ### Hiring Manager Inference from Calendar Events
 
 When a calendar event title matches interview-related patterns:
+
 - "Interview", "Screening", "Screen", "Decomposition", "Panel", "Technical
   Assessment", "Candidate"
 - Combined with a person name (cross-reference `knowledge/Candidates/`)
@@ -421,8 +422,8 @@ Extract the **organizer** of the event. If the organizer is NOT the user (from
 
 1. Look up the organizer in `knowledge/People/` — check if they have a role
    indicating they manage a team or are described as a hiring manager.
-2. Look up which candidate is being interviewed — check their `brief.md` for
-   a `Req` field.
+2. Look up which candidate is being interviewed — check their `brief.md` for a
+   `Req` field.
 3. If a Req is known, update the corresponding `knowledge/Roles/*.md` file's
    `Hiring manager` field (only if currently `—`).
 4. Update the candidate's `brief.md` `Hiring manager` field if currently `—`.
@@ -436,8 +437,8 @@ When processing email threads that reference candidates (by name match against
 2. If a CC'd person's note mentions "recruiter", "talent acquisition", or a
    similar recruiting role, they are likely the internal recruiter for this
    candidate's role.
-3. Update the candidate's `brief.md` recruiter field and the corresponding
-   Role file if the field is currently `—`.
+3. Update the candidate's `brief.md` recruiter field and the corresponding Role
+   file if the field is currently `—`.
 
 ### Domain Lead Resolution
 
@@ -445,8 +446,8 @@ When a hiring manager is newly identified (from calendar or email inference),
 attempt to resolve the domain lead:
 
 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.
+2. Walk up the reporting chain until reaching a VP or senior leader listed in a
+   stakeholder map or organizational hierarchy note.
 3. Update both the Role file's `Domain lead` and the candidate brief's
    `Domain lead`.
 

package/template/.claude/skills/hiring-decision/SKILL.md

@@ -32,7 +32,8 @@ Run this skill:
 
 - `fit-pathway` CLI installed (`npx fit-pathway` must work)
 - Screening assessment: `knowledge/Candidates/{Name}/screening.md`
-- At least one interview assessment: `knowledge/Candidates/{Name}/interview-*.md`
+- At least one interview assessment:
+  `knowledge/Candidates/{Name}/interview-*.md`
 - Candidate brief: `knowledge/Candidates/{Name}/brief.md`
 - Transcripts provide additional context but are not strictly required if
   interview assessments exist
@@ -72,9 +73,9 @@ Read in order:
 
 Build a chronological evidence timeline:
 
-| Date | Stage | Source | Key Finding |
-|------|-------|--------|-------------|
-| {date} | CV Screening | screening.md | {key finding} |
+| Date   | Stage            | Source              | Key Finding   |
+| ------ | ---------------- | ------------------- | ------------- |
+| {date} | CV Screening     | screening.md        | {key finding} |
 | {date} | {Interview type} | interview-{date}.md | {key finding} |
 
 ## Step 2: Build Final Skill Profile
@@ -104,14 +105,14 @@ For each skill, record:
 - **Final rating** — the proficiency level supported by the best evidence
 - **Best evidence source** — which stage provided the strongest signal
 - **Trajectory** — did the rating improve, decline, or hold across stages?
-- **Confidence** — high (demonstrated live), medium (discussed well), low
-  (CV only or thin evidence)
+- **Confidence** — high (demonstrated live), medium (discussed well), low (CV
+  only or thin evidence)
 
 ## Step 3: Build Final Behaviour Profile
 
 For each framework behaviour, determine the **final maturity** using the same
-evidence hierarchy. Behaviours assessed in interviews carry far more weight
-than CV signals.
+evidence hierarchy. Behaviours assessed in interviews carry far more weight than
+CV signals.
 
 ```bash
 npx fit-pathway behaviour --list
@@ -125,7 +126,8 @@ For each behaviour:
 
 ## Step 4: Confirm Level and Track
 
-Using the complete evidence profile, make a final level and track recommendation:
+Using the complete evidence profile, make a final level and track
+recommendation:
 
 ```bash
 # Compare adjacent levels
@@ -134,13 +136,13 @@ npx fit-pathway job {discipline} {target_level} --track={track}
 npx fit-pathway progress {discipline} {lower_level} --track={track}
 ```
 
-| Question                                                    | Answer informs          |
-| ----------------------------------------------------------- | ----------------------- |
+| Question                                                     | Answer informs          |
+| ------------------------------------------------------------ | ----------------------- |
 | Does the candidate meet ≥ 70% of skills at the target level? | Level confirmation      |
-| Were level concerns from screening resolved in interviews?  | Level upgrade/downgrade |
-| Did interviewers explicitly suggest a different level?      | Strong level signal     |
-| Does the candidate's scope and autonomy match the level?    | Level fit               |
-| Which track energized the candidate in interviews?          | Track confirmation      |
+| Were level concerns from screening resolved in interviews?   | Level upgrade/downgrade |
+| Did interviewers explicitly suggest a different level?       | Strong level signal     |
+| Does the candidate's scope and autonomy match the level?     | Level fit               |
+| Which track energized the candidate in interviews?           | Track confirmation      |
 
 ## Step 4b: Read Role Context
 
@@ -337,14 +339,16 @@ rests with the hiring manager. All assessments are advisory.*
 
 Update `knowledge/Candidates/{Name}/brief.md`:
 
-- Update **Status** to reflect the recommendation (`recommended` / `not-recommended`)
+- Update **Status** to reflect the recommendation (`recommended` /
+  `not-recommended`)
 - Add link: `- [Hiring Recommendation](./recommendation.md)`
 - Add final pipeline entry with the recommendation date and outcome
 
 Update `knowledge/Candidates/Insights.md` with any cross-candidate observations:
 
 - If this candidate is the strongest at their level, note it
-- If this candidate revealed a pattern about a sourcing channel, note the channel
+- If this candidate revealed a pattern about a sourcing channel, note the
+  channel
 - If the level adjustment has implications for other candidates, note it
 
 **Use precise edits — don't rewrite entire files.**

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

@@ -143,8 +143,8 @@ When preparing for interview meetings (title contains "Interview", "Screening",
 3. **Include in the briefing:**
    - Candidate's current status, skills, and screening recommendation
    - Role context: hiring manager, domain lead, remaining positions
-   - Other candidates on the same requisition and their statuses (from the
-     Role file's Candidates table)
+   - Other candidates on the same requisition and their statuses (from the Role
+     file's Candidates table)
    - Previous interview assessments if this is a second/later stage
    - Panel brief if one exists (`panel.md`)
 4. **Format as a dedicated section:**

package/template/.claude/skills/screen-cv/SKILL.md

@@ -43,8 +43,8 @@ Run this skill:
 - 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
+  `Level`, `Discipline`, `Hiring manager`, and `Domain lead` for more accurate
+  screening
 
 ## Outputs
 
@@ -231,7 +231,7 @@ Classify each skill as:
 
 Create `knowledge/Candidates/{Name}/screening.md`:
 
-```markdown
+````markdown
 # CV Screening — {Full Name}
 
 **Assessed against:** {Discipline} {Level} — {Track}
@@ -323,10 +323,11 @@ These are the specific uncertainties that interviews must resolve.}
 
 ```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.}
 
-{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
@@ -366,3 +367,4 @@ to create the candidate profile from email threads.
 - [ ] 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

@@ -30,7 +30,8 @@ Run this skill:
 - `~/.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)
+- `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
@@ -170,8 +171,8 @@ Sort by First seen (newest first).
 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.
+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.
 
 ---
@@ -272,14 +273,16 @@ 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.
+   `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.
@@ -573,12 +576,12 @@ 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)                   |
-| Candidate → Role         | Role → Candidate (in Candidates table — rebuilt by sync)  |
+| 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]]`.

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

@@ -209,9 +209,11 @@ 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.
 

package/template/CLAUDE.md

@@ -81,14 +81,14 @@ 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                                                 |
+| 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, screen-cv, assess-interview, hiring-decision, workday-requisition, right-to-be-forgotten, fit-pathway, fit-map |
-| **head-hunter**    | Passive talent scouting        | Every 60 min    | scan-open-candidates, fit-pathway, fit-map                                                     |
-| **chief-of-staff** | Daily briefings and priorities | 7am, Mon 7:30am | weekly-update _(Mon)_, _(reads all state for daily briefings)_                                 |
+| **head-hunter**    | Passive talent scouting        | Every 60 min    | scan-open-candidates, 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`: