@forwardimpact/outpost 3.11.0 → 3.12.1

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

@@ -5,24 +5,23 @@ description: >
   hire. Uses WebFetch to read public APIs (HN Algolia, GitHub, dev.to).
   Writes prospect notes to Knowledge/Prospects/. Maintains
   cursor/dedup state in ~/.cache/fit/outpost/head-hunter/. Use when the
-  head-hunter agent is woken or when the user asks to scan for open candidates.
+  head-hunter agent wakes or when the user asks to scan for open candidates.
 ---
 
 # Scan Open Candidates
 
 Fetch and filter publicly available candidate posts from platforms where people
-**explicitly indicate** they are open for hire. This skill handles fetching,
-filtering, deduplication, benchmarking, prospect-note writing, and memory
-updates.
+**explicitly indicate** they are open for hire. This skill fetches, filters,
+deduplicates, benchmarks, writes prospect notes, and updates memory.
 
 ## Trigger
 
-- The head-hunter agent is woken by the scheduler.
+- The scheduler wakes the head-hunter agent.
 - The user asks to scan for open candidates or prospects.
 
 ## Prerequisites
 
-- `WebFetch` tool available (Claude Code built-in — no curl/wget).
+- `WebFetch` tool available (a Claude Code built-in, no curl/wget).
 - `fit-pathway` CLI available (`bunx fit-pathway`).
 - Memory directory `~/.cache/fit/outpost/head-hunter/`.
 
@@ -40,18 +39,18 @@ updates.
 
 <do_confirm_checklist goal="Verify the wake produced a clean, ethical scan">
 
-- [ ] Selected the least-recently-checked, non-suspended source.
-- [ ] Fetched via `WebFetch` (never curl/wget).
-- [ ] Applied all 5 filters in order; passed candidates have ≥ 2
+- [ ] Select the least-recently-checked source that is not suspended.
+- [ ] Fetch with `WebFetch` (never curl/wget).
+- [ ] Apply all 5 filters in order. Confirm each passed candidate has ≥ 2
       standard-relevant skills.
-- [ ] Deduplicated against `seen.tsv` before processing.
-- [ ] Benchmarked each prospect against a real `bunx fit-pathway job`.
-- [ ] Prospect notes follow the template (no fabricated names).
-- [ ] All state mutations went through `node scripts/state.mjs` — cursor, seen,
-      prospects, failures, log.
-- [ ] Triage report written to the state directory; alternative queries (if any)
-      logged.
-- [ ] Failures recorded; sources with ≥ 3 consecutive failures suspended.
+- [ ] Deduplicate against `seen.tsv` before you process a candidate.
+- [ ] Benchmark each prospect against a real `bunx fit-pathway job`.
+- [ ] Follow the template for every prospect note (no fabricated names).
+- [ ] Route every state mutation through `node scripts/state.mjs`: cursor,
+      seen, prospects, failures, log.
+- [ ] Write the triage report to the state directory. Log any alternative
+      queries.
+- [ ] Record every failure. Suspend a source at ≥ 3 consecutive failures.
 
 </do_confirm_checklist>
 
@@ -75,12 +74,12 @@ follow [references/filters.md](references/filters.md#failure-handling).
 ### 3. Filter
 
 Apply the 5-filter pipeline in
-[references/filters.md](references/filters.md#filter-pipeline) — signal, dedup,
+[references/filters.md](references/filters.md#filter-pipeline): signal, dedup,
 geographic, skill alignment, experience level.
 
 ### 3b. Fallback — zero new prospects
 
-If filtering eliminates every candidate, try up to **3 alternatives** per wake
+If the filters eliminate every candidate, try up to **3 alternatives** per wake
 from [references/fallbacks.md](references/fallbacks.md). Log every alternative
 in `log.md`.
 
@@ -99,7 +98,7 @@ Classify match strength:
 - **moderate** — some overlap, level roughly right, minor gaps.
 - **weak** — few matching signals, significant gaps.
 
-Write notes for **strong** and **moderate** matches only, using the template in
+Write notes for **strong** and **moderate** matches only. Use the template in
 [references/template.md](references/template.md).
 
 ```bash
@@ -108,8 +107,8 @@ mkdir -p "Knowledge/Prospects"
 
 ### 5. Update state
 
-All state changes go through `node scripts/state.mjs` — full command reference:
-[references/state.md](references/state.md). Each wake:
+All state changes go through `node scripts/state.mjs`. The full command
+reference is [references/state.md](references/state.md). Each wake:
 
 1. Update the cursor (`cursor set`).
 2. Reset failure count on success or increment on failure.

package/templates/.claude/skills/req-scan/references/fallbacks.md

@@ -1,16 +1,16 @@
 # Fallback Strategies
 
 Reference for `req-scan` when a primary source query yields zero new prospects
-after filtering. Try at most **3 alternatives per wake** to stay within rate
-limits.
+after the filters run. Try at most **3 alternatives per wake** to stay within
+rate limits.
 
 ## Strategy 1 — alternative search terms
 
 ### HN
 
 - Check the **previous** month's "Who Wants to Be Hired?" thread.
-- Search for `"Who is hiring"` threads (candidates sometimes post in the wrong
-  thread; comments may link to candidate profiles).
+- Search for `"Who is hiring"` threads. (Candidates sometimes post in the wrong
+  thread. Comments may link to candidate profiles.)
 - Try
   `https://hn.algolia.com/api/v1/search?query=%22freelancer+available%22&tags=comment`.
 
@@ -47,9 +47,9 @@ WebFetch URL: https://dev.to/api/articles?tag=career&per_page=25
 If geography eliminated everyone, re-scan without the location filter. Mark
 unmatched-location prospects as "location unconfirmed" in the prospect note.
 
-If skill alignment filtered everyone out: lower the bar from 2 standard skills
-to 1; consider transferable skills (strong Python ⇒ likely data integration
-capability); accept adjacent indicators ("machine learning" implies data
+If skill alignment filtered everyone out, lower the bar from 2 standard skills
+to 1. Consider transferable skills (strong Python ⇒ likely data integration
+capability). Accept adjacent indicators ("machine learning" implies data
 skills).
 
 ## Strategy 3 — cross-reference
@@ -57,11 +57,11 @@ skills).
 When a source yields very few results, enrich what you do find:
 
 - A GitHub profile that links to a blog/portfolio → WebFetch it for more detail
-  before deciding skill fit.
+  before you decide skill fit.
 - An HN post that mentions a GitHub username → fetch their GitHub profile for
   richer signal.
 
-## Logging alternatives
+## Log the alternatives
 
 Log every alternative in `log.md`:
 

package/templates/.claude/skills/req-scan/references/filters.md

@@ -11,7 +11,7 @@ Apply in order. Stop at the first that excludes the candidate.
 - HN "Who Wants to Be Hired?" → **auto-pass** (thread is opt-in).
 - GitHub → must have `hireable: true` **or** bio contains an open-to-work
   phrase.
-- dev.to → must be tagged `opentowork` or `lookingforwork`.
+- dev.to → the post must carry the tag `opentowork` or `lookingforwork`.
 
 ### 2. Deduplication
 
@@ -31,8 +31,8 @@ Prefer or accept candidates in or open to:
 - **Remote / Anywhere / Global**.
 
 Skip candidates explicitly locked to incompatible regions ("San Francisco only",
-"APAC only"). When location is ambiguous or unstated, include the candidate —
-let the user decide.
+"APAC only"). When location is ambiguous or unstated, include the candidate.
+Let the user decide.
 
 ### 4. Skill alignment
 
@@ -46,8 +46,8 @@ non-traditional path (law, policy, academia → tech), AI/ML tool proficiency
 **Platform:** infrastructure / cloud / DevOps, architecture and system design,
 API design and shared services, performance / scalability / reliability.
 
-**Minimum bar:** at least 2 standard-relevant skills must be identifiable from
-the post. Skip candidates with purely non-technical profiles.
+**Minimum bar:** the post must show at least 2 standard-relevant skills. Skip
+candidates with purely non-technical profiles.
 
 ### 5. Experience level
 
@@ -68,16 +68,16 @@ block page):
 1. Increment the failure count:
    `node scripts/state.mjs failure increment {source}`.
 2. **Do not retry** the same source in this wake cycle.
-3. Suspend after 3 consecutive failures — skip during source selection. Retry
-   suspended sources once every 7 days to detect recovery.
+3. Suspend after 3 consecutive failures. Skip a suspended source during source
+   selection. Retry suspended sources once every 7 days to detect recovery.
 4. Log the failure in `log.md` with HTTP status and error.
 5. Reset on success: `node scripts/state.mjs failure reset {source}`.
 
 ### Common failure patterns
 
-| Symptom                  | Likely cause                                           |
-| ------------------------ | ------------------------------------------------------ |
-| 503 with HTML redirect   | Corporate proxy blocking the domain (won't recover)    |
-| 403 Forbidden            | Auth required or automated requests blocked            |
-| 429 Too Many Requests    | Rate limited — will recover; don't suspend permanently |
-| Empty response / timeout | Transient — likely recovers next wake                  |
+| Symptom                  | Likely cause                                             |
+| ------------------------ | -------------------------------------------------------- |
+| 503 with HTML redirect   | A corporate proxy blocks the domain. It will not recover |
+| 403 Forbidden            | The site needs auth, or it blocks automated requests     |
+| 429 Too Many Requests    | Rate limited. It recovers. Do not suspend permanently    |
+| Empty response / timeout | Transient. It likely recovers next wake                  |

package/templates/.claude/skills/req-scan/references/sources.md

@@ -4,31 +4,31 @@ Reference for `req-scan` Step 2 (fetch & scan). One source per wake cycle.
 
 ## 1. Hacker News "Who Wants to Be Hired?"
 
-Monthly thread, posted on the 1st.
+A monthly thread that appears on the 1st.
 
 ```text
 WebFetch URL: https://hn.algolia.com/api/v1/search?query=%22Who+wants+to+be+hired%22&tags=ask_hn&hitsPerPage=5
 ```
 
-The first hit whose title matches "Who wants to be hired?" with `created_at` in
-the current or previous month is the target thread.
+The target thread is the first hit whose title matches "Who wants to be hired?"
+and whose `created_at` falls in the current or previous month.
 
 ```text
 WebFetch URL: https://hn.algolia.com/api/v1/items/{objectID}
 ```
 
-`children[]` contains top-level comments — each is one candidate. Parse the
-`text` field for:
+`children[]` contains top-level comments. Each comment is one candidate. Parse
+the `text` field for:
 
 - **Location** ("Location: New York", "NYC / Remote").
 - **Remote** ("Remote: Yes", "Open to remote").
 - **Skills** — tech stack, language/standard mentions.
 - **Experience** — years, role titles, past companies.
-- **Contact** — email (often obfuscated: "name [at] domain [dot] com").
+- **Contact** — email, often obfuscated as "name [at] domain [dot] com".
 - **Resume / CV** — links to personal sites, GitHub, LinkedIn.
 
 **Cursor:** thread `objectID` plus the ID of the last processed child comment.
-**Rate:** no strict limit; one fetch per wake cycle.
+**Rate:** no strict limit. One fetch per wake cycle.
 
 ## 2. GitHub Open to Work
 

package/templates/.claude/skills/req-scan/references/state.md

@@ -40,7 +40,7 @@ node scripts/state.mjs failure increment mastodon_hachyderm
 node scripts/state.mjs failure reset github_open_to_work
 ```
 
-## Logging
+## Logs
 
 ```bash
 node scripts/state.mjs log-wake github_open_to_work "Primary query: 'open to work' location:UK — 30 results, 2 new prospects"

package/templates/.claude/skills/req-scan/scripts/state.mjs

@@ -2,7 +2,8 @@
 /**
  * Manage head-hunter agent state files.
  *
- * Provides atomic operations on the 5 state files used by the head-hunter agent:
+ * The script provides atomic operations on the 5 state files that the
+ * head-hunter agent uses:
  *   cursor.tsv   — source rotation state (source, last_checked, position)
  *   seen.tsv     — deduplication index (source, id, date)
  *   prospects.tsv — prospect index (name, source, date, strength, level)
@@ -82,7 +83,7 @@ State dir: ~/.cache/fit/outpost/head-hunter/`);
   process.exit(0);
 }
 
-// --- Ensure state directory exists ---
+// --- Make sure the state directory exists ---
 
 mkdirSync(STATE_DIR, { recursive: true });
 

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

@@ -2,28 +2,29 @@
 name: req-screen
 description: >
   Screen candidate CVs against the agent-aligned engineering standard to decide
-  whether to invest interview time. Produces a structured screening assessment
-  with interview/pass recommendation and suggested interview focus areas.
-  Use when the user asks to evaluate a CV or when a new CV is detected.
+  whether to invest interview time. It produces a structured screening
+  assessment with an interview/pass recommendation and suggested interview
+  focus areas. Use when the user asks to evaluate a CV, or when you find a new
+  CV.
 ---
 
 # Screen CV
 
 Screen a candidate's CV against the agent-aligned engineering standard defined
-in `fit-pathway`. The single question this skill answers: **is this candidate
-worth interviewing?** Every assessment is grounded in the standard — no
-subjective impressions.
+in `fit-pathway`. This skill answers one question. **Is this candidate worth an
+interview?** Ground every assessment in the standard. Never use subjective
+impressions.
 
 This is **Stage 1** of a three-stage hiring pipeline:
 
 1. **Screen CV** (this skill) — CV arrives → interview or pass.
 2. `req-assess` — interview transcript arrives → updated evidence.
-3. `req-decide` — all stages complete → hire / don't hire.
+3. `req-decide` — all stages complete → hire / do not hire.
 
 ## Trigger
 
-- A new CV is added to `Knowledge/Candidates/{Name}/`.
-- A CV appears in `~/Downloads/` and is associated with a candidate.
+- A new CV appears in `Knowledge/Candidates/{Name}/`.
+- A CV appears in `~/Downloads/` and matches a candidate.
 - The user asks to screen, evaluate, or assess a CV.
 - The user asks "is this person worth interviewing?".
 
@@ -38,9 +39,9 @@ This is **Stage 1** of a three-stage hiring pipeline:
 - CV file path (e.g. `Knowledge/Candidates/{Name}/CV.pdf`).
 - Target role (optional).
 - Existing `Knowledge/Candidates/{Name}/brief.md`, if any.
-- `Knowledge/Roles/*.md` matching the candidate's `Req` (provides `Level`,
-  `Discipline`, `Hiring manager`, `Domain lead`, and the `**Status:**` field).
-  Look up by Req number or filename substring.
+- `Knowledge/Roles/*.md` that matches the candidate's `Req`. It provides
+  `Level`, `Discipline`, `Hiring manager`, `Domain lead`, and the `**Status:**`
+  field. Look up by Req number or filename substring.
 
 ## Outputs
 
@@ -51,15 +52,15 @@ This is **Stage 1** of a three-stage hiring pipeline:
 decision-rule-compliant">
 
 - [ ] Every claim cites CV evidence or marks "Not evidenced".
-- [ ] Two-level scepticism applied; vague phrases didn't earn levels.
-- [ ] "Not evidenced" skills are counted as gaps in the recommendation.
-- [ ] Recommendation follows the decision rules and threshold rule — match % and
-      gap count verified before picking a tier.
+- [ ] Two-level scepticism applied. Vague phrases did not earn levels.
+- [ ] "Not evidenced" skills count as gaps in the recommendation.
+- [ ] Recommendation follows the decision rules and the threshold rule. Match %
+      and gap count verified before you pick a tier.
 - [ ] "Interview with focus areas" used only for strong candidates with a named
-      concern — not as a soft "maybe".
-- [ ] Output file is exactly `screening.md`; any misnamed prior file deleted.
-- [ ] `brief.md` links the screening as `[CV Screening](./screening.md)` and
-      Skills/Summary updated via targeted edits.
+      concern. Never used as a soft "maybe".
+- [ ] Output file is exactly `screening.md`. Any misnamed prior file deleted.
+- [ ] `brief.md` links the screening as `[CV Screening](./screening.md)`.
+      Targeted edits updated Skills and Summary.
 - [ ] Gender set only from explicit pronouns/titles.
 - [ ] Recommendation header carries the advisory-only banner.
 
@@ -74,7 +75,7 @@ Extract the fields listed in
 
 ### 2. Anchor the target role
 
-If `brief.md` carries a `Req`, look up the matching Role file:
+If `brief.md` carries a `Req`, look up the Role file that matches it:
 
 ```bash
 ls Knowledge/Roles/ | grep "{req_number}"
@@ -83,10 +84,10 @@ cat "Knowledge/Roles/{matching file}"
 
 Use the Role's `Level` and `Discipline` as the target unless the user specified
 a different target. Capture `Hiring manager` and `Domain lead` for the screening
-header. Note the `**Status:**` field, but don't let historical (`closed`) roles
-block screening of still-active candidates.
+header. Note the `**Status:**` field. Screen a still-active candidate even when
+the role is `closed`.
 
-If no target is available, estimate one using the level heuristics in
+If no target is available, estimate one with the level heuristics in
 [references/rubric.md](references/rubric.md#level-estimation-heuristics).
 
 ### 3. Load the standard
@@ -111,7 +112,7 @@ mapping and the scepticism rule in
 bunx fit-pathway behaviour --list
 ```
 
-Map CV evidence using the behaviour signals in
+Map CV evidence with the behaviour signals in
 [references/rubric.md](references/rubric.md#behaviour-signals).
 
 ### 6. Classify gaps and strengths
@@ -124,12 +125,12 @@ bunx fit-pathway progress {discipline} {level} --track={track}
 
 Classify each skill per
 [references/rubric.md](references/rubric.md#skill-alignment-classification).
-Pick the recommendation using the decision rules and threshold rule in
+Pick the recommendation with the decision rules and threshold rule in
 [references/rubric.md](references/rubric.md#recommendation-decision-rules).
 
 ### 7. Write the screening
 
-Save to `Knowledge/Candidates/{Name}/screening.md` using the template in
+Save to `Knowledge/Candidates/{Name}/screening.md` with the template in
 [references/template.md](references/template.md). Include the **Suggested
 Interview Questions** when the recommendation is "Interview" or "Interview with
 focus areas":
@@ -138,7 +139,7 @@ focus areas":
 bunx fit-pathway interview {discipline} {level} --track={track}
 ```
 
-Pick 3–5 questions most relevant to the gaps; note which gap each targets.
+Pick 3–5 questions most relevant to the gaps. Note which gap each one targets.
 
 ### 8. Enrich the brief
 
@@ -146,7 +147,8 @@ If `brief.md` exists, apply targeted edits:
 
 - Add or update `## Skills` with agent-aligned standard skill IDs.
 - Update `## Summary` if the CV provides better context.
-- Set `**Gender:**` only when explicitly stated and not already set.
+- Set `**Gender:**` only when the CV states it explicitly and the field is
+  empty.
 - Append `- [CV Screening](./screening.md)` if missing.
 
 If no brief exists, tell the user to run `req-track` first to build the

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

@@ -14,7 +14,7 @@ Reference data for `req-screen` Steps 1, 3, 4, 5, and 6 (recommendation).
 | **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   |
+| **Gender**              | Pronouns or gendered titles only. Never infer it from a name   |
 
 ## Level estimation heuristics
 
@@ -40,21 +40,21 @@ Reference data for `req-screen` Steps 1, 3, 4, 5, and 6 (recommendation).
 
 ## 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    |
+| 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 that use 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.
+CVs inflate. Default **two levels below** what the CV implies. Make an
+exception when 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 that appears only in a
+"Skills" section with no project context is `awareness` at most.
 
 ## Behaviour signals
 
@@ -73,8 +73,8 @@ project context is `awareness` at most.
 - **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.
+- **Not evidenced** — the CV does not mention this skill area. **Treat it as a
+  gap.** Absence of evidence is not evidence of skill.
 
 ## Recommendation decision rules
 
@@ -82,7 +82,7 @@ project context is `awareness` at most.
 | ------------------------------ | ------------------------------------------------------------------------ |
 | **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                                |
+| **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
@@ -90,5 +90,5 @@ Gap or Not evidenced, the candidate cannot receive "Interview." If more than
 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.
+should be rare. Use it for a strong candidate with a specific, named concern.
+Do not use it for a marginal candidate.

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

@@ -1,10 +1,10 @@
 # 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.
+`Knowledge/Candidates/{Name}/screening.md`. The filename **must** be
+`screening.md`. Do not use `assessment.md`, `cv-screening.md`, or any variant.
+Look in the folder for a misnamed screening file with `# CV Screening` in the
+header. If one exists, delete it after you write the new one.
 
 ```markdown
 # CV Screening — {Full Name}