@forwardimpact/outpost 3.3.4 → 3.4.0

package/templates/.claude/skills/upstream-instructions/references/examples.md

@@ -0,0 +1,97 @@
+# Changelog Examples
+
+Reference output for `upstream-instructions` Step 5. There is **one** root
+`CHANGELOG.md` with reverse-chronological entries. Each entry's **Scope** names
+the surface(s) it touched — `CLAUDE.md`, `agent:<name>`, `skill:<name>` — and a
+single entry may span several.
+
+## Cross-surface change (one change, many files)
+
+```markdown
+## 2026-06-18
+
+**Scope:** KB structure; CLAUDE.md; agents: librarian, chief-of-staff, recruiter; skills: extract-entities, anarlog-process, meeting-prep, req-decide
+**Type:** removed
+
+**What:** Dropped the Goals entity type; Priorities is now the only user-set
+strategic layer.
+
+**Why:** One strategic layer is simpler than two — time-bound targets fold into
+Priorities, removing the Project↔Goal↔Priority coupling that earned nothing.
+
+**Details:**
+- Deleted `Knowledge/Goals/`; repointed live backlinks to `Priorities/C - Onboarding`.
+- CLAUDE.md workspace-layout tree no longer lists `Goals/`.
+- Agents: dropped Goals from the librarian index/triage, chief-of-staff state
+  sources, and recruiter strategic links.
+- extract-entities: removed Goals from resolution/index; renamed
+  `templates-goals-priorities.md` → `templates-priorities.md`; deleted Goal link
+  rules. anarlog-process / meeting-prep / req-decide: dropped Goals inputs.
+
+---
+```
+
+## Modified skill
+
+```markdown
+## 2026-03-01
+
+**Scope:** skill: req-track
+**Type:** modified
+
+**What:** Added gender field extraction for diversity tracking.
+
+**Why:** The recruitment pipeline lacked diversity metrics — pool composition was
+invisible without structured gender data.
+
+**Details:**
+- Added a Gender field to the candidate brief template (Woman / Man / —).
+- Added extraction rules (pronouns, gendered titles) and a note that the field
+  has no bearing on hiring decisions.
+- Updated the quality checklist to verify the field.
+
+---
+```
+
+## Modified agent
+
+```markdown
+## 2026-06-19
+
+**Scope:** agents: all six profiles
+**Type:** modified
+
+**What:** Agents now read `Knowledge/Priorities/` at the start of every wake and
+flag anything that threatens a priority.
+
+**Why:** Sync, triage, and drafting were ignoring strategic context; signals that
+could block a priority passed silently.
+
+**Details:**
+- Added a uniform `## Priorities` section and a `Priority Watch` output line to
+  the five worker agents.
+- The chief-of-staff consolidates each agent's `Priority Watch` flags into a
+  dedicated section of the daily briefing.
+
+---
+```
+
+## New skill
+
+```markdown
+## 2026-03-01
+
+**Scope:** skill: anarlog-process
+**Type:** added
+
+**What:** New skill for processing Anarlog meeting recordings.
+
+**Why:** Meeting notes were being lost — Anarlog captures transcriptions but they
+weren't integrated into the knowledge base.
+
+**Details:**
+- Reads transcription files, extracts people/decisions/action items, and links
+  attendees to `Knowledge/People/`.
+
+---
+```

package/templates/CLAUDE.md

@@ -2,7 +2,8 @@
 
 You are the user's personal knowledge assistant. You help draft emails, prep for
 meetings, track projects, and answer questions, backed by a live knowledge graph
-built from their emails, calendar, and meeting notes, all stored locally.
+built from their emails, calendar, and meeting notes, all stored as plain files on
+the user's machine.
 
 ## Ethics & Integrity — NON-NEGOTIABLE
 
@@ -27,26 +28,31 @@ When in doubt, err toward discretion.
 
 ## Voice
 
-Be supportive, direct, and lightly warm. Explain complex things clearly without
-hedging. When the next step is obvious, take it. Ask at most one clarifying
-question, and only at the start. Reference files by full path. Confirm before
-destructive actions.
+Be supportive and direct. Explain complex things clearly without hedging. When
+the next step is obvious, take it. Ask at most one clarifying question, at the
+start. Reference files by full path. Confirm before destructive actions.
 
 ## Dependencies
 
 - **ripgrep** (`rg`) for fast knowledge graph searches — `brew install ripgrep`.
 
-## Workspace Layout
+## Workspace Layout & Sharing
+
+The **root is personal and local — never shared.** Only `Knowledge/` is shared
+with the team over a synced filesystem; each member keeps their own root,
+`Drafts/`, and `Briefings/`. KBs are **not** Git repositories — they sync as
+plain files. `CLAUDE.md` and `.claude/` are yours to tweak; use the `fit-outpost`
+CLI to install or update the standard instruction set.
 
 ```
-./
-├── knowledge/         # The knowledge graph (Obsidian-compatible)
-│   ├── People/ Organizations/ Projects/ Topics/
-│   └── Candidates/ Goals/ Priorities/ Conditions/ Roles/
-├── .claude/skills/    # Auto-discovered skill files
-├── drafts/            # Email drafts (draft-emails skill)
-├── CLAUDE.md          # This file
-└── .mcp.json          # MCP server configurations (optional)
+./                      # Personal root — never shared
+├── CLAUDE.md           # This file
+├── .claude/            # Agent profiles + auto-discovered skills
+├── Knowledge/          # Knowledge graph — SHARED (Obsidian-compatible)
+│   └── People/ Organizations/ Projects/ Topics/ Candidates/ Priorities/ Conditions/ Roles/
+├── Drafts/             # Email/chat drafts (personal)
+├── Briefings/          # Daily briefings (personal)
+└── .mcp.json           # MCP config (optional)
 ```
 
 ## Agents
@@ -54,29 +60,29 @@ destructive actions.
 Agents in `.claude/agents/` maintain this KB, woken on a schedule by the Outpost
 scheduler. Each wake: observe state, decide the most valuable action, execute.
 
-| Agent              | Domain                          | Schedule        | Skills                                                                                       |
-| ------------------ | ------------------------------- | --------------- | -------------------------------------------------------------------------------------------- |
-| **postman**        | Communication triage and drafts | Every 5 min     | sync-apple-mail, sync-teams, draft-emails                                                    |
-| **concierge**      | Meeting prep and transcripts    | Every 10 min    | sync-apple-calendar, meeting-prep, anarlog-process                                          |
-| **librarian**      | Knowledge graph maintenance     | Every 15 min    | extract-entities, organize-files                                                             |
-| **recruiter**      | Engineering recruitment         | Every 30 min    | req-track, req-screen, req-assess, req-decide, req-workday, req-forget, fit-pathway, fit-map |
-| **head-hunter**    | Passive talent scouting         | Every 60 min    | req-scan, fit-pathway, fit-map                                                               |
-| **chief-of-staff** | Daily briefings and priorities  | 7am, Mon 7:30am | _(reads all state for daily briefings)_                                                      |
+Each agent's skills are declared in its own profile under `.claude/agents/`.
+
+| Agent              | Domain                          | Schedule        |
+| ------------------ | ------------------------------- | --------------- |
+| **postman**        | Communication triage and drafts | Every 5 min     |
+| **concierge**      | Meeting prep and transcripts    | Every 10 min    |
+| **librarian**      | Knowledge graph maintenance     | Every 15 min    |
+| **recruiter**      | Engineering recruitment         | Every 30 min    |
+| **head-hunter**    | Passive talent scouting         | Every 60 min    |
+| **chief-of-staff** | Daily briefings and priorities  | 7am, Mon 7:30am |
 
 Each agent writes `~/.cache/fit/outpost/state/{agent}_triage.md` per wake. The
-**chief-of-staff** reads all five to write daily briefings in
-`knowledge/Briefings/`.
+**chief-of-staff** reads all of them to write daily briefings in `Briefings/`.
 
 ## Cache Directory (`~/.cache/fit/outpost/`)
 
-Synced data and runtime state live outside the KB; only notes and drafts live
-inside it.
+Synced data and runtime state live outside the KB; only notes, drafts, and
+briefings live inside it.
 
-**Resolve `~` before passing a path to a tool.** Paths like
-`~/.cache/fit/outpost/` are shorthand; read `$HOME` at runtime and never hardcode
-it. Shell commands expand `~`, but the Write and Edit tools do not — a literal
-`~/...` given to those creates a stray `.cache/` inside the KB. Always pass them
-the full `$HOME/...` path.
+**Resolve `~` before passing a path to a tool.** Shell commands expand `~`, but
+the Write and Edit tools do not — a literal `~/...` creates a stray `.cache/`
+inside the KB. Read `$HOME` at runtime and pass the full `$HOME/...` path. Read
+meetings, emails, and messages directly from the source dirs below.
 
 - `apple_mail/` — Mail threads as `.md` (plus `attachments/`)
 - `apple_calendar/` — Calendar events as `.json`
@@ -90,38 +96,26 @@ the full `$HOME/...` path.
 Plain markdown with Obsidian-style `[[backlinks]]`.
 
 ```bash
-ls knowledge/People/                     # List entities
-rg "Sarah Chen" knowledge/               # Search by name
-cat "knowledge/People/Sarah Chen.md"     # Read a note
+rg "Sarah Chen" Knowledge/               # Search by name
+cat "Knowledge/People/Sarah Chen.md"     # Read a note
 ```
 
 **Always search broadly first.** When the user mentions any person, org, project,
-or topic, run `rg "keyword" knowledge/` to surface every note first — one note is
-never the full story. Use it for tasks involving named entities, people, projects,
-meetings, emails, or calendar data; skip general knowledge and brainstorming.
-
-## Synced Sources
-
-Read upcoming meetings, recent emails, and messages directly from:
-
-- `~/.cache/fit/outpost/apple_mail/`
-- `~/.cache/fit/outpost/apple_calendar/`
-- `~/.cache/fit/outpost/teams_chat/`
+or topic, run `rg "keyword" Knowledge/` to surface every note — one note is never
+the full story. Skip it only for general knowledge and brainstorming.
 
 ## Skills
 
-Skills auto-discover from `.claude/skills/` and load by context: data sync (Apple
-Mail, Calendar, Teams), knowledge-graph maintenance (extract-entities, recruitment
-pipeline), and communication (draft-emails, send-chat, meeting-prep, decks, docs).
+Skills auto-discover from `.claude/skills/` and load by context — data sync,
+knowledge-graph maintenance, recruitment, and communication.
 
 ## User Identity
 
 The current user's identity is cached at
-`~/.cache/fit/outpost/state/identity.md` — read it directly. If it is missing or
-stale, run the `identify-user` skill to refresh it from the corporate directory.
+`~/.cache/fit/outpost/state/identity.md` — read it directly. If missing or stale,
+run the `identify-user` skill to refresh it from the corporate directory.
 
 ## Working Outside This Directory
 
-You have full filesystem access (macOS). For tasks outside this KB
-(organizing the Desktop, finding files in Downloads), use shell commands
-directly.
+You have full filesystem access (macOS). For tasks outside this KB, use shell
+commands directly.

package/templates/.claude/skills/extract-entities/references/templates-goals-priorities.md

@@ -1,63 +0,0 @@
-# Goal and Priority Templates
-
-Goals and Priorities are **never auto-created** by `extract-entities`. They are
-set deliberately by the user. These templates are for manual creation only —
-`extract-entities` and `anarlog-process` only **link to** and **update progress
-on** existing notes.
-
-## Priorities
-
-```markdown
-# {Priority Name}
-
-## About
-{2-3 sentences: what this strategic direction means and why it matters}
-
-**Status:** {active|paused|retired}
-**Owner:** [[People/{Person}]]
-**Set:** {YYYY-MM-DD}
-
-## What this means
-{Bullet list of concrete implications — what does pursuing this priority look like?}
-
-## Goals
-{Time-bound targets that ladder to this priority — backlinks to knowledge/Goals/}
-
-## Projects
-- [[Projects/{Project}]] — {relationship}
-
-## Key facts
-{substantive facts only — leave empty if none}
-```
-
-## Goals
-
-```markdown
-# {Goal Name}
-
-## Info
-**Priority:** [[Priorities/{Priority}]]
-**Status:** {on track|at risk|off track|achieved|abandoned}
-**Owner:** [[People/{Person}]]
-**Target date:** {YYYY-MM-DD}
-**Set:** {YYYY-MM-DD}
-
-## Outcome
-{1-2 sentences: what measurable success looks like}
-
-## Blockers
-{Active Conditions that impede this goal — link to knowledge/Conditions/}
-- [[Conditions/{Condition}]] — {impact on this goal}
-
-## Projects
-- [[Projects/{Project}]] — {how it contributes}
-
-## Progress
-- **{YYYY-MM-DD}**: {Update on progress toward the outcome}
-
-## Key facts
-{substantive facts only — leave empty if none}
-
-## Risks
-{known risks to achieving this goal — leave empty if none}
-```

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

@@ -1,130 +0,0 @@
----
-name: upstream-skill
-description: Track changes made to skills in this installation and produce a changelog that can be included upstream. Use when skills have been modified, added, or removed locally and those changes should be contributed back to the monorepo.
----
-
-# Upstream
-
-Track changes to skills in this installation and produce a structured changelog
-so improvements can be contributed back to the upstream monorepo.
-
-## Trigger
-
-- The user asks to prepare local skill changes for upstream contribution.
-- Skills in `.claude/skills/` have been modified, added, or removed.
-- The user wants to document what changed locally before syncing upstream.
-
-## Prerequisites
-
-- A working Outpost installation with `.claude/skills/`.
-- Git available for change detection.
-
-## Inputs
-
-- `.claude/skills/*/SKILL.md` — current skill files.
-- Git history — change detection.
-
-## Outputs
-
-- `.claude/skills/<skill>/CHANGELOG.md` — one per modified skill,
-  reverse-chronological.
-
-<do_confirm_checklist goal="Verify changelogs are upstream-ready">
-
-- [ ] 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 (not
-      "updated SKILL.md" / "fixed stuff").
-- [ ] New skills include a brief description of their purpose.
-- [ ] Removed skills explain why they were removed.
-- [ ] Dates come from git history, not guessed.
-- [ ] No duplicate entries for the same change.
-
-</do_confirm_checklist>
-
-## Procedure
-
-### 1. Identify changed skills
-
-Use git to find skills added, modified, or deleted since the last changelog
-entry (or since initial commit if no changelog exists):
-
-```bash
-# Latest changelog date for a skill (if any)
-head -20 .claude/skills/<skill>/CHANGELOG.md 2>/dev/null
-
-# All changes touching skills
-git log --oneline --name-status -- '.claude/skills/'
-
-# Changes since last documented date for one skill
-git log --after="<last-entry-date>" --name-status -- '.claude/skills/<skill>/'
-```
-
-If no changelog exists for a skill, consider all commits that touched that
-skill's directory.
-
-### 2. Classify each change
-
-| Type       | Description                                          |
-| ---------- | ---------------------------------------------------- |
-| `added`    | New skill that doesn't exist upstream                |
-| `modified` | Existing skill updated (workflow, checklists, tools) |
-| `removed`  | Skill deleted from the installation                  |
-| `renamed`  | Skill directory or file renamed                      |
-
-For modifications, diff the current file against the prior version:
-
-```bash
-git diff HEAD~N -- '.claude/skills/<skill>/SKILL.md'
-git diff <commit> -- '.claude/skills/<skill>/SKILL.md'
-```
-
-### 3. Describe each change
-
-Every entry must answer:
-
-1. **What changed?** — the specific section or behaviour modified.
-2. **Why?** — the problem encountered or improvement discovered in use.
-3. **How?** — a summary of the actual change (not a full diff).
-
-Good: "Added a safety check to Step 3 — agents were skipping validation when the
-source directory was empty, causing silent failures."
-
-Bad: "Updated SKILL.md" / "Fixed stuff" / "Changed line 42".
-
-### 4. Write the changelog
-
-For each changed skill, create or update `.claude/skills/<skill>/CHANGELOG.md`
-using this format (newest first):
-
-```markdown
-# <skill> Changelog
-
-Changes to this skill that should be considered for upstream inclusion in
-the Forward Impact monorepo.
-
-## <YYYY-MM-DD>
-
-**What:** <one-line summary>
-
-**Why:** <problem or improvement that motivated it>
-
-**Details:**
-<2–5 lines describing the specific changes>
-
----
-```
-
-For **new** skills, write a single `added` entry describing the skill's purpose.
-For **removed** skills, the changelog is the last file remaining in the
-directory and explains the removal.
-
-Worked examples in [references/examples.md](references/examples.md).
-
-## Notes
-
-- This skill **documents only** — it does not push or merge anything.
-- Per-skill changelogs are consumed by the **downstream** skill in the upstream
-  monorepo.
-- When in doubt about whether a change is upstream-worthy, include it; the
-  upstream maintainer decides what to incorporate.

package/templates/.claude/skills/upstream-skill/references/examples.md

@@ -1,80 +0,0 @@
-# Changelog Examples
-
-Reference output for `upstream-skill` Step 4. Each modified skill has its own
-`CHANGELOG.md` with reverse-chronological entries.
-
-## Modified skill
-
-`.claude/skills/req-track/CHANGELOG.md`:
-
-```markdown
-# req-track Changelog
-
-Changes to this skill that should be considered for upstream inclusion in
-the Forward Impact monorepo.
-
-## 2026-03-01
-
-**What:** Added gender field extraction for diversity tracking
-
-**Why:** Recruitment pipeline lacked diversity metrics — pool composition
-was invisible without structured gender data.
-
-**Details:**
-- Added Gender field to candidate brief template (Woman / Man / —)
-- Added extraction rules: pronouns, gendered titles
-- Added explicit note that the field has no bearing on hiring decisions
-- Updated quality checklist to verify the gender field
-
----
-```
-
-## New skill
-
-`.claude/skills/anarlog-process/CHANGELOG.md`:
-
-```markdown
-# anarlog-process 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 Anarlog meeting recordings
-
-**Why:** Meeting notes were being lost — Anarlog captures transcriptions
-but they weren't being integrated into the knowledge base.
-
-**Details:**
-- Reads transcription files from `~/.cache/fit/outpost/anarlog/`
-- Extracts people, decisions, and action items
-- Creates meeting notes in `knowledge/Meetings/`
-- Links attendees to `knowledge/People/` entries
-
----
-```
-
-## Tweak to existing skill
-
-`.claude/skills/extract-entities/CHANGELOG.md`:
-
-```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
-
-**Why:** Processing was too slow for large inboxes — 5 files per batch
-meant dozens of runs to catch up after a week of email.
-
-**Details:**
-- Changed batch size constant from 5 to 10 in Step 1
-- Added a note about context window limits for batches > 15
-
----
-```