@forwardimpact/outpost 3.11.0 → 3.12.1

package/templates/.claude/skills/person-lookup/scripts/lookup.sh

@@ -3,17 +3,19 @@
 # input (an email address, or a first / last / full name) and print their
 # directory record(s).
 #
-# Sibling to `person-identify`, but for *other* people, not the current user:
+# Sibling to `person-identify`. Use it for *other* people. Do not use it for
+# the current user:
 #   - Searches the Global Catalog (port 3268, base "") so it reaches EVERY
-#     domain in the forest from a single ticket — colleagues in other regions
-#     are found, not just your own domain.
+#     domain in the forest from a single ticket. It finds colleagues in other
+#     regions. It does not stop at your own domain.
 #   - Uses Active Directory ANR (Ambiguous Name Resolution), so one filter
 #     matches an email, a login, or any part of a name.
-#   - Handles 0, 1, or many matches, and flags external Contacts / vendor
-#     accounts so an internal employee is never confused with an outside one.
-#   - NEVER writes the identity cache — this is a throwaway lookup.
+#   - Handles 0, 1, or many matches. Flags external Contacts / vendor
+#     accounts so you never confuse an internal employee with an outside one.
+#   - NEVER writes the identity cache. This is a throwaway lookup.
 #
-# Auth uses SASL/GSSAPI against the existing Kerberos ticket — no password.
+# Auth uses SASL/GSSAPI against the existing Kerberos ticket. It needs no
+# password.
 #
 # Robustness note: under load the directory intermittently returns an entry's
 # DN with NO attributes (exit 0, no error). Every attribute fetch below retries
@@ -22,9 +24,10 @@
 set -u
 
 # Org-specific: substring of the DN's OU that marks external/vendor *user*
-# accounts (external Contact objects are detected generically via objectClass).
-# Empty by default — set it to your directory's convention, e.g. "OU=Contractors"
-# or "OU=External", to label those accounts as "User (external / vendor)".
+# accounts. The script detects external Contact objects generically through
+# objectClass. Empty by default. Set it to your directory's convention, e.g.
+# "OU=Contractors" or "OU=External", to label those accounts as
+# "User (external / vendor)".
 VENDOR_OU_PATTERN=""
 
 QUERY="$*"
@@ -44,7 +47,7 @@ dom=$(printf '%s' "$realm" | tr '[:upper:]' '[:lower:]')
 dc=$(dig +short SRV "_ldap._tcp.dc._msdcs.$dom" | awk 'NR==1{print $4}' | sed 's/\.$//')
 [ -z "$dc" ] && dc=$(dig +short SRV "_ldap._tcp.$dom" | awk 'NR==1{print $4}' | sed 's/\.$//')
 if [ -z "$dc" ]; then
-  echo "Could not find a domain controller for $dom via DNS SRV." >&2
+  echo "Could not find a domain controller for $dom with DNS SRV." >&2
   exit 1
 fi
 
@@ -53,7 +56,7 @@ GC="ldap://$dc:3268"
 ATTRS="displayName givenName sn company title department employeeID mail telephoneNumber physicalDeliveryOfficeName objectClass manager"
 MAX_SHOW=12   # cap detailed output for very broad name matches
 
-# Pull one attribute out of an LDIF record (passed as $2), decoding base64 (::).
+# Pull one attribute out of an LDIF record (passed as $2). Decode base64 (::).
 field() { # $1=attr  $2=record
   local attr="$1" line
   line=$(printf '%s\n' "$2" | grep -m1 -E "^$attr:: ?|^$attr: ") || return 0
@@ -63,13 +66,13 @@ field() { # $1=attr  $2=record
   esac
 }
 
-# List matching DNs for a filter (no attributes requested → reliable under load).
+# List the DNs that match a filter. Request no attributes → reliable under load.
 dns_for() { # $1=filter
   ldapsearch -Y GSSAPI -LLL -o ldif-wrap=no -H "$GC" -b "" "$1" 1.1 2>/dev/null \
     | sed -n 's/^dn: //p'
 }
 
-# Fetch one entry's attributes by DN, retrying past the silent DN-only response.
+# Fetch one entry's attributes by DN. Retry past the silent DN-only response.
 fetch() { # $1=dn
   local dn="$1" out tries=0
   while [ "$tries" -lt 4 ]; do
@@ -100,7 +103,7 @@ kind_of() { # $1=record  $2=dn
 }
 
 # 2. Primary search (ANR), then a substring fallback if it finds nothing.
-#    (Portable array fill — macOS ships bash 3.2, which has no `mapfile`.)
+#    (Portable array fill. macOS ships bash 3.2, which has no `mapfile`.)
 read_dns() { # $1=filter  -> populates global DNS array
   DNS=()
   local line
@@ -138,7 +141,7 @@ if [ "${#DNS[@]}" -eq 1 ]; then
 fi
 
 # 3b. Several matches → a compact disambiguation list (no per-row manager call).
-echo "${#DNS[@]} matches for \"$QUERY\" — narrow with an email for an exact hit:"
+echo "${#DNS[@]} matches for \"$QUERY\". Narrow with an email for an exact hit:"
 echo
 shown=0
 for dn in "${DNS[@]}"; do

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

@@ -1,9 +1,9 @@
 ---
 name: req-assess
 description: >
-  Analyze interview transcripts against the agent-aligned engineering standard,
-  updating skill and behaviour ratings with observed evidence. Produces
-  per-interview assessments and panel briefs for subsequent interview stages.
+  Analyze interview transcripts against the agent-aligned engineering standard.
+  Update skill and behaviour ratings with observed evidence. Produces
+  per-interview assessments and panel briefs for later interview stages.
   Use when transcript files appear in a candidate's folder.
 ---
 
@@ -11,7 +11,7 @@ description: >
 
 Analyze a candidate's interview transcripts. Update their skill and behaviour
 profile with **observed** (not claimed) evidence. Interview evidence is
-higher-fidelity than CV evidence — it confirms or contradicts the screening
+higher-fidelity than CV evidence. It confirms or contradicts the screening
 assessment.
 
 This is **Stage 2** of the three-stage hiring pipeline:
@@ -25,14 +25,14 @@ This is **Stage 2** of the three-stage hiring pipeline:
 - A new `transcript-*.md` file appears in `Knowledge/Candidates/{Name}/`.
 - The user asks to analyze an interview or debrief.
 - The user asks to prepare a panel brief.
-- The concierge agent processes a Anarlog interview recording.
+- The concierge agent processes an Anarlog interview recording.
 
 ## Prerequisites
 
 - `fit-pathway` CLI installed.
 - At least one transcript in `Knowledge/Candidates/{Name}/`.
-- `screening.md` should exist; if missing, run `req-screen` first (proceed
-  regardless).
+- `screening.md` should exist. If it is missing, run `req-screen` first.
+  Proceed regardless.
 
 ## Inputs
 
@@ -50,15 +50,15 @@ This is **Stage 2** of the three-stage hiring pipeline:
 <do_confirm_checklist goal="Verify the assessment is grounded in transcript
 evidence">
 
-- [ ] Every skill re-rating cites a specific moment from the transcript.
-- [ ] Behaviour assessments reference observed actions, not claimed traits.
-- [ ] Level assessment uses standard progression criteria, not gut feel.
-- [ ] Interviewer observations are attributed by name.
-- [ ] Confirmed strengths and new concerns are distinguished.
-- [ ] Panel brief (if created) is written for non-technical readers and ties
-      suggested questions to remaining gaps.
-- [ ] Brief's Pipeline section, links, and Status are updated.
-- [ ] Gender field is **not** updated from interview observations.
+- [ ] Cite a specific moment from the transcript for every skill re-rating.
+- [ ] Base behaviour assessments on observed actions. Ignore claimed traits.
+- [ ] Assess the level with standard progression criteria. Ignore gut feel.
+- [ ] Attribute interviewer observations by name.
+- [ ] Distinguish confirmed strengths from new concerns.
+- [ ] Write the panel brief (if created) for non-technical readers. Tie the
+      suggested questions to the remaining gaps.
+- [ ] Update the brief's Pipeline section, links, and Status.
+- [ ] **Never** update the Gender field from interview observations.
 
 </do_confirm_checklist>
 
@@ -79,8 +79,8 @@ bunx fit-pathway skill {skill_id}
 bunx fit-pathway behaviour --list
 ```
 
-If screening recommended a different level than originally targeted (e.g. J100 →
-J090), load **both** for comparison.
+If screening recommended a level different from the original target (e.g. J100
+→ J090), load **both** for comparison.
 
 ### 3. Re-rate skills
 
@@ -90,8 +90,8 @@ moment, quote, or observation per change.
 
 ### 4. Re-rate behaviours
 
-Behaviours are better assessed in interviews than CVs — they describe how
-someone acts, not what they've done. Use the
+Interviews assess behaviours better than CVs. Behaviours describe how someone
+acts. They do not describe what someone did. Use the
 [behaviour signals](references/rubric.md#behaviour-signals) and the
 [behaviour maturity scale](references/rubric.md#behaviour-maturity-scale).
 
@@ -105,23 +105,23 @@ Apply the [level signals](references/rubric.md#level-signals).
 
 ### 6. Write the interview assessment
 
-Save to `Knowledge/Candidates/{Name}/interview-{date}.md` using
+Save to `Knowledge/Candidates/{Name}/interview-{date}.md` with
 [references/interview-template.md](references/interview-template.md). Include
-only skills with new evidence — don't repeat the full matrix.
+only skills with new evidence. Do not repeat the full matrix.
 
 ### 7. Generate the panel brief (if applicable)
 
-When more interview stages are planned (panel, technical, etc.), pull question
+When you plan more interview stages (panel, technical, etc.), pull question
 candidates:
 
 ```bash
 bunx fit-pathway interview {discipline} {level} --track={track}
 ```
 
-Save `Knowledge/Candidates/{Name}/panel.md` using
-[references/panel-template.md](references/panel-template.md). Audience:
-next-stage interviewers, often non-engineers — explain without jargon and tie
-suggested questions to remaining gaps.
+Save `Knowledge/Candidates/{Name}/panel.md` with
+[references/panel-template.md](references/panel-template.md). The audience is
+next-stage interviewers, often non-engineers. Explain without jargon. Tie the
+suggested questions to the remaining gaps.
 
 ### 8. Update the candidate brief
 

package/templates/.claude/skills/req-assess/references/interview-template.md

@@ -2,7 +2,7 @@
 
 Reference template for `req-assess` Step 6. Save to
 `Knowledge/Candidates/{Name}/interview-{date}.md`. Include only skills the
-interview produced new evidence for — don't repeat the full matrix.
+interview produced new evidence for. Do not repeat the full matrix.
 
 ```markdown
 # Interview Assessment — {Full Name}

package/templates/.claude/skills/req-assess/references/panel-template.md

@@ -1,8 +1,9 @@
 # Panel Brief Template
 
 Reference template for `req-assess` Step 7. Save to
-`Knowledge/Candidates/{Name}/panel.md`. Audience: **next-stage interviewers,
-often non-engineers** — explain without jargon, focus on behaviours and scope.
+`Knowledge/Candidates/{Name}/panel.md`. The audience is **next-stage
+interviewers, often non-engineers**. Explain without jargon. Focus on
+behaviours and scope.
 
 ```markdown
 # Panel Brief — {Full Name}

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

@@ -13,17 +13,17 @@ Reference data for `req-assess` Steps 1, 3, 4, and 5.
 | **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               |
+| **Red flags**                 | Contradictions with CV, patterns of concern               |
 | **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 |
 
 ## Skill re-rating
 
-**Interview evidence outranks CV evidence.** A candidate who claimed
-`practitioner` but demonstrated `foundational` should be re-rated. The reverse
-also applies. Every re-rating cites a specific moment, quote, or observation
-from the transcript — "seemed strong" is not evidence.
+**Interview evidence outranks CV evidence.** Re-rate a candidate who claimed
+`practitioner` but demonstrated `foundational`. The reverse also applies. Every
+re-rating cites a specific moment, quote, or observation from the transcript.
+The phrase "seemed strong" is not evidence.
 
 | Interview evidence                          | Rating adjustment                     |
 | ------------------------------------------- | ------------------------------------- |
@@ -36,13 +36,13 @@ from the transcript — "seemed strong" is not evidence.
 
 ## Behaviour signals
 
-| 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, 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, listens actively                 |
+| Be Polymath Oriented       | Draws on diverse knowledge, makes unexpected connections                 |
+| Don't Lose Your Curiosity  | Asks good questions, explores alternatives, admits what they do not know |
 
 ## Behaviour maturity scale
 
@@ -59,7 +59,7 @@ from the transcript — "seemed strong" is not evidence.
 | Interview signal                                          | Implication                    |
 | --------------------------------------------------------- | ------------------------------ |
 | Needed guidance to structure their approach               | Level may be lower than est.   |
-| Self-directed; sound trade-offs independently             | Level estimate confirmed       |
+| Self-directed, made sound trade-offs independently        | Level estimate confirmed       |
 | Mentored or coached others during the exercise            | Level may be higher than est.  |
 | Struggled with complexity appropriate to the target level | Downgrade                      |
 | Interviewer explicitly suggested a different level        | Strong signal — weight heavily |

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

@@ -10,7 +10,7 @@ description: >
 # Hiring Decision
 
 Synthesize all available evidence for a candidate into a final hiring
-recommendation. This is the culmination of the hiring pipeline — every prior
+recommendation. This is the culmination of the hiring pipeline. Every prior
 assessment feeds in.
 
 This is **Stage 3** of the three-stage pipeline:
@@ -42,7 +42,7 @@ This is **Stage 3** of the three-stage pipeline:
   manager, domain lead). Check the `**Status:**` field to distinguish active
   from historical reqs.
 - `Knowledge/Priorities/*.md` — strategic context.
-- Other active candidates at the same level — relative positioning.
+- Other active candidates at the same level — relative position.
 
 ## Outputs
 
@@ -53,17 +53,20 @@ This is **Stage 3** of the three-stage pipeline:
 <do_confirm_checklist goal="Verify the recommendation is grounded and
 audit-ready">
 
-- [ ] Every skill rating traces to a specific evidence source (stage + detail).
-- [ ] Evidence hierarchy respected — interview evidence outranks CV.
-- [ ] Level recommendation grounded in standard progression criteria.
-- [ ] Track recommendation cites interview evidence, not just CV.
-- [ ] Decision rules applied strictly; match % and gap counts verified.
-- [ ] Risk assessment is honest — concerns not minimised to justify a hire.
-- [ ] "Do not hire" written with the same rigour as "Hire" (GDPR Article 15:
-      candidate may request access).
-- [ ] Brief updated with `[Hiring Recommendation](./recommendation.md)` and a
-      final pipeline entry.
-- [ ] Recommendation could be shown to the candidate without embarrassment.
+- [ ] Trace every skill rating to a specific evidence source (stage + detail).
+- [ ] Respect the evidence hierarchy. Interview evidence outranks CV.
+- [ ] Ground the level recommendation in standard progression criteria.
+- [ ] Cite interview evidence for the track recommendation. A CV alone is not
+      enough.
+- [ ] Apply the decision rules strictly. Verify the match % and the gap counts.
+- [ ] Keep the risk assessment honest. Do not minimise a concern to justify a
+      hire.
+- [ ] Write "Do not hire" with the same rigour as "Hire" (GDPR Article 15 lets
+      the candidate request access).
+- [ ] Update the brief with `[Hiring Recommendation](./recommendation.md)` and
+      a final pipeline entry.
+- [ ] Write a recommendation you could show to the candidate without
+      embarrassment.
 
 </do_confirm_checklist>
 
@@ -86,9 +89,10 @@ bunx fit-pathway job {discipline} {level} --track={track} --skills
 bunx fit-pathway progress {discipline} {level} --track={track}
 ```
 
-For each skill in the target job, pick the highest-fidelity evidence using the
-[evidence hierarchy](references/rubric.md#evidence-hierarchy). Record final
-rating, best evidence source, trajectory, confidence.
+For each skill in the target job, use the
+[evidence hierarchy](references/rubric.md#evidence-hierarchy) to pick the
+highest-fidelity evidence. Record final rating, best evidence source,
+trajectory, confidence.
 
 ### 3. Build the final behaviour profile
 
@@ -120,9 +124,8 @@ cat "Knowledge/Roles/{matching file}"
 ```
 
 Check the `**Status:**` field. Capture remaining positions, hiring manager,
-domain lead, goal alignment, other
-candidates on the same req, and channel (hr / vendor). Frame the recommendation
-in terms of strategic impact.
+domain lead, goal alignment, other candidates on the same req, and channel
+(hr / vendor). Frame the recommendation in terms of strategic impact.
 
 ### 6. Assess against the active pipeline
 
@@ -146,8 +149,8 @@ Apply the [decision rules](references/rubric.md#decision-rules) and run the
 
 ### 8. Write the recommendation
 
-Save to `Knowledge/Candidates/{Name}/recommendation.md` using the template in
-[references/template.md](references/template.md). Carry the **advisory-only**
+Use the template in [references/template.md](references/template.md). Save to
+`Knowledge/Candidates/{Name}/recommendation.md`. Carry the **advisory-only**
 banner. Cite specific evidence in skill, behaviour, level, and track sections.
 
 ### 9. Update brief and insights
@@ -158,8 +161,8 @@ Update `brief.md`:
 - Append `- [Hiring Recommendation](./recommendation.md)`.
 - Add the final pipeline entry with date and outcome.
 
-Update `Knowledge/Candidates/Insights.md` only when there's a cross-candidate
-observation worth keeping (strongest at level, sourcing channel pattern,
-level-adjustment implications).
+Update `Knowledge/Candidates/Insights.md` only when a cross-candidate
+observation deserves a record (strongest at level, a pattern in the sourcing
+channel, level-adjustment implications).
 
-Use targeted Edit operations — never rewrite entire files.
+Use targeted Edit operations. Never rewrite entire files.

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

@@ -13,8 +13,9 @@ applies and use it as the source of the final rating.
    answers.
 3. **Interviewer observation** — an interviewer noted strength or concern.
 4. **CV evidence with quantification** — concrete metrics, named projects.
-5. **CV evidence without quantification** — described but vague.
-6. **Not evidenced** — never surfaced across any stage.
+5. **CV evidence without quantification** — the CV describes it but stays
+   vague.
+6. **Not evidenced** — no stage surfaced it.
 
 For each skill record: **final rating**, **best evidence source**,
 **trajectory** (↑ / ↓ / —), **confidence** (High = demonstrated live; Medium =
@@ -22,9 +23,9 @@ discussed well; Low = CV only or thin).
 
 ## Behaviour evidence
 
-Same hierarchy. Behaviours assessed in interviews carry far more weight than CV
-signals. For each: **final maturity**, **best evidence** (specific moment or
-pattern), **consistency** (once vs. throughout).
+Same hierarchy. A behaviour that an interview assessed carries far more weight
+than a CV signal. For each: **final maturity**, **best evidence** (specific
+moment or pattern), **consistency** (once vs. throughout).
 
 ## Level confirmation criteria
 
@@ -41,7 +42,7 @@ pattern), **consistency** (once vs. throughout).
 | Recommendation             | Criteria                                                                                  |
 | -------------------------- | ----------------------------------------------------------------------------------------- |
 | **Hire**                   | ≥ 70 % Strong match at the final level, no unresolved core-skill gaps, strong behaviours  |
-| **Hire at adjusted level** | Strong candidate; evidence supports a different level than originally targeted            |
+| **Hire at adjusted level** | Strong candidate. The evidence supports a level other than the original target            |
 | **Do not hire**            | Unresolved core-skill gaps, behaviour concerns, or insufficient evidence after interviews |
 
 ### Hire criteria check
@@ -50,14 +51,14 @@ pattern), **consistency** (once vs. throughout).
 - No core skill gaps remain unresolved (core = top-tier skills for the
   discipline/track combo).
 - All agent-aligned standard behaviours at or above expected maturity.
-- Level confirmed by interview evidence (not just CV).
-- Track fit confirmed by interview evidence.
+- Interview evidence confirms the level. The CV alone does not.
+- Interview evidence confirms the track fit.
 - No red flags from any interview stage.
 
 ## Pipeline context (Step 5)
 
-This is **not** a ranking exercise — it provides context. Note:
+This is **not** a ranking exercise. It gives context. Note:
 
 - Whether this candidate fills a gap in the current pipeline.
 - Whether stronger candidates exist for the same role.
-- Whether this candidate is better suited to a different open position.
+- Whether a different open position suits this candidate better.

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

@@ -4,17 +4,18 @@ description: >
   Process GDPR Article 17 data erasure requests. Finds and removes all personal
   data related to a named individual from the knowledge base, cached data, and
   agent state files. Use when the user receives a right-to-be-forgotten
-  request, asks to delete all data about a person, or needs to comply with a
+  request, asks to delete all data about a person, or must comply with a
   data erasure obligation.
 compatibility: Requires macOS filesystem access
 ---
 
 # Right to Be Forgotten
 
-Process data erasure requests under GDPR Article 17. Given a person's name,
-systematically find and remove all personal data from the knowledge base, cached
-synced data, and agent state files. Produces an **erasure report** documenting
-what was found, deleted, and redacted — the compliance audit trail.
+Process data erasure requests under GDPR Article 17. Work from the person's
+name. Systematically find and remove all personal data from the knowledge base,
+the cached synced data, and the agent state files. Produces an **erasure
+report** that records what you found, deleted, and redacted. The report is the
+compliance audit trail.
 
 ## Trigger
 
@@ -43,16 +44,16 @@ what was found, deleted, and redacted — the compliance audit trail.
 <do_confirm_checklist goal="Verify erasure is complete and the audit trail is
 sound">
 
-- [ ] User confirmed intent before any deletion.
-- [ ] All discovery recipes ran; inventory covers knowledge, cache, state,
-      drafts.
-- [ ] All dedicated files and directories deleted.
-- [ ] All mentions and backlinks redacted from other notes.
-- [ ] Cached email threads, attachments, and calendar entries handled.
-- [ ] Agent state and `graph_processed` cleaned.
-- [ ] Erasure report saved; contains **no** personal data beyond the name and
-      actions taken.
-- [ ] Final `rg` search shows only the erasure report as a match.
+- [ ] Get the user's confirmation before any deletion.
+- [ ] Run every discovery recipe. Cover knowledge, cache, state, and drafts in
+      the inventory.
+- [ ] Delete all dedicated files and directories.
+- [ ] Redact all mentions and backlinks from other notes.
+- [ ] Handle cached email threads, attachments, and calendar entries.
+- [ ] Clean the agent state and `graph_processed`.
+- [ ] Save the erasure report. Keep **no** personal data in it beyond the name
+      and the actions taken.
+- [ ] Run a final `rg` search. Confirm the erasure report is the only match.
 
 </do_confirm_checklist>
 
@@ -70,9 +71,9 @@ State to the user:
 > - Cached email threads and attachments
 > - Agent state and triage files
 >
-> This action cannot be undone. Proceed?
+> You cannot undo this action. Proceed?
 
-**Wait for explicit confirmation before continuing.**
+**Wait for explicit confirmation before you continue.**
 
 ### 1. Discovery
 
@@ -97,12 +98,12 @@ rm -f "Knowledge/People/{Name}.md"
 find ~/.cache/fit/outpost/apple_mail/attachments/ -iname "*{Name}*" -delete
 ```
 
-**3b. Redact mentions in other notes:** read each file, remove the specific
+**3b. Redact mentions in other notes:** Read each file. Remove the specific
 lines/bullets/sections per the rules in
-[references/classify.md](references/classify.md#redaction-rules), remove broken
-`[[backlinks]]` to deleted notes, write the file back.
+[references/classify.md](references/classify.md#redaction-rules). Remove broken
+`[[backlinks]]` to deleted notes. Write the file back.
 
-**3c. Email threads:** delete sole-subject threads; redact paragraphs only in
+**3c. Email threads:** Delete sole-subject threads. Redact paragraphs only in
 multi-person threads.
 
 **3d. Agent state files:**
@@ -126,9 +127,10 @@ rg -v "{deleted_path}" ~/.cache/fit/outpost/state/graph_processed \
 
 ### 4. Write the erasure report
 
-Save to `Knowledge/Erasure/{Name}--{YYYY-MM-DD}.md` using the template in
-[references/report-template.md](references/report-template.md). Record **only**
-what was deleted — never CV content, skills, or assessments.
+Use the template in
+[references/report-template.md](references/report-template.md). Save to
+`Knowledge/Erasure/{Name}--{YYYY-MM-DD}.md`. Record **only** what you deleted.
+Never record CV content, skills, or assessments.
 
 ### 5. Verify
 
@@ -148,7 +150,7 @@ them and update the report.
 - Recruitment threads (known agency domains)
 - `recruiter_triage.md`
 
-Leaves `Knowledge/People/{Name}.md` and the wider graph intact — the person may
-be a colleague or non-recruitment contact.
+It leaves `Knowledge/People/{Name}.md` and the wider graph intact. The person
+may be a colleague or a non-recruitment contact.
 
 **`all`** (default): full erasure across knowledge base, cache, and state.

package/templates/.claude/skills/req-forget/references/classify.md

@@ -3,21 +3,21 @@
 Reference for `req-forget` Step 2. For every match in the inventory, pick the
 action below.
 
-| Reference Type                     | Action                                      | Example                                         |
-| ---------------------------------- | ------------------------------------------- | ----------------------------------------------- |
-| **Dedicated note** (sole subject)  | Delete entire file                          | `Knowledge/People/{Name}.md`                    |
-| **Dedicated directory**            | Delete entire directory                     | `Knowledge/Candidates/{Name}/`                  |
-| **Mention in another note**        | Redact: remove lines referencing the person | Backlink in `Knowledge/Organizations/Agency.md` |
-| **Email thread** (sole subject)    | Delete file                                 | `~/.cache/fit/outpost/apple_mail/thread.md`     |
-| **Email thread** (multiple people) | Redact: remove paragraphs about the person  | Thread discussing multiple candidates           |
-| **Attachment** (their CV, etc.)    | Delete file                                 | `attachments/{thread}/CV.pdf`                   |
-| **Triage/state file**              | Redact: remove lines mentioning them        | `recruiter_triage.md`                           |
-| **Insights file**                  | Redact: remove bullets mentioning them      | `Knowledge/Candidates/Insights.md`              |
+| Reference Type                     | Action                                         | Example                                         |
+| ---------------------------------- | ---------------------------------------------- | ----------------------------------------------- |
+| **Dedicated note** (sole subject)  | Delete the entire file                         | `Knowledge/People/{Name}.md`                    |
+| **Dedicated directory**            | Delete the entire directory                    | `Knowledge/Candidates/{Name}/`                  |
+| **Mention in another note**        | Redact: remove the lines that name the person  | Backlink in `Knowledge/Organizations/Agency.md` |
+| **Email thread** (sole subject)    | Delete the file                                | `~/.cache/fit/outpost/apple_mail/thread.md`     |
+| **Email thread** (multiple people) | Redact: remove the paragraphs about the person | A thread about multiple candidates              |
+| **Attachment** (their CV, etc.)    | Delete the file                                | `attachments/{thread}/CV.pdf`                   |
+| **Triage/state file**              | Redact: remove the lines that mention them     | `recruiter_triage.md`                           |
+| **Insights file**                  | Redact: remove the bullets that mention them   | `Knowledge/Candidates/Insights.md`              |
 
 ## Redaction rules
 
 - Remove entire bullet points that mention the person by name.
-- Remove table rows containing the person's name.
-- Remove `## Connected to` entries linking to deleted notes.
+- Remove the table rows that contain the person's name.
+- Remove the `## Connected to` entries that link to deleted notes.
 - If a section becomes empty after redaction, remove its header too.
-- Do **not** remove surrounding context that doesn't identify the person.
+- Do **not** remove nearby context that does not identify the person.

package/templates/.claude/skills/req-forget/references/locations.md

@@ -1,7 +1,7 @@
 # Discovery Search Recipes
 
-Reference for `req-forget` Step 1. Run every recipe; record every match into the
-inventory.
+Reference for `req-forget` Step 1. Run every recipe. Record every match into
+the inventory.
 
 ## Knowledge base — direct notes
 

package/templates/.claude/skills/req-forget/references/report-template.md

@@ -5,7 +5,7 @@ Audit trail for `req-forget` Step 4. Save to
 
 **The report itself must not contain personal data** beyond the subject's name
 and the actions taken. Do not copy CV content, skills, or assessments into the
-report — record only what was deleted, not what it contained.
+report. Record only what you deleted. Do not record what it contained.
 
 ````markdown
 # Data Erasure Report — {Full Name}