@event4u/agent-config 7.5.0 → 8.1.0

package/dist/agent-src/skills/html-deck/SKILL.md

@@ -0,0 +1,123 @@
+---
+model_tier: inherit
+name: html-deck
+description: "Build a slide presentation as one HTML file — fixed 1920×1080 canvas letterboxed to any viewport, layout-system-first, type floors. Use for deck, slides, presentation, or pitch requests."
+domain: product
+personas: []
+workspaces:
+  - engineering
+packs:
+  - frontend-design
+trust:
+  level: professional
+install:
+  removable: true
+execution:
+  type: manual
+---
+
+# HTML Deck
+
+Build a slide presentation as a single HTML file with fixed-size slides that
+letterbox to any viewport. A deck is fixed-canvas media (default 1920×1080,
+16:9) — a different medium from responsive UI and from static posters.
+
+## When to use
+
+- The user asks for a deck, presentation, slides, or a pitch as a web/HTML
+  deliverable.
+
+**When NOT to use:** static single-image visual art (poster, PNG/PDF
+one-off) → [`canvas-design`](../canvas-design/SKILL.md). Responsive product
+UI → [`fe-design`](../fe-design/SKILL.md) + stack executor. Multiple styled
+options of one screen → [`design-variations`](../design-variations/SKILL.md).
+
+## Procedure
+
+1. **Discovery.** Confirm: audience (engineers / executives / customers —
+   determines tone and density), aspect ratio (16:9 default), slide count vs
+   time budget (~1 slide/minute; most decks land at 8–15), tone, source
+   material (PRD/doc — read it before sketching), speaker notes (off unless
+   requested), and the brand / design system. No brand →
+   [`design-intelligence`](../design-intelligence/SKILL.md) direction first.
+   A fully specified ask ("5-slide deck for the all-hands from this PRD")
+   skips the question round.
+2. **Commit to a layout system before any slide.** 4–6 layout types (cover,
+   section header, content, quote/pull-out, comparison two-column, closing/
+   CTA); per layout: background, headline size/position, body area, footer
+   treatment. 1–2 background colors across the deck (section headers may
+   break to a third). Record the system as a comment block at the top of the
+   file.
+3. **Start from the deck-shell starter** (`templates/deck-shell.html`,
+   skill-local): fixed-canvas scaling + letterboxing, keyboard/tap
+   navigation, slide counter, `localStorage` slide-index persistence,
+   print-to-PDF CSS. Each slide is a direct child `<section>` with a
+   1-indexed `data-screen-label` ("01 Title") so the user can reference
+   slides by the counter they see.
+4. **Build slide-by-slide, reveal early.** Show the file at 1–2 slides —
+   don't perfect 15 in private. Per slide: one primary message; **type
+   floors on a 1080p canvas: body ≥24px (32px+ preferred), headlines
+   60–96px+**; tokens from the active brand/design system (precedence per
+   `brand-source-of-truth`, emission per
+   [`design-tokens`](../design-tokens/SKILL.md)); honest placeholders for
+   missing imagery (striped background + monospace size label — see
+   [`fe-design § Craft details`](../fe-design/SKILL.md)); cut filler slides
+   ("Why choose us?", "About this deck") and data that doesn't support the
+   slide's point.
+5. **Speaker notes only when requested** — as a toggleable overlay or
+   per-slide `<aside hidden>`, never printed.
+6. **Quality gate.** Run `lint_design_slop` over the file; honor the
+   outward-artifact hygiene floor (Q13 in
+   [`design-antipatterns.md`](../../../docs/guidelines/design-antipatterns.md))
+   — no workspace paths, skill/tool names, or generator traces in markup or
+   comments; final pass → [`design-review`](../design-review/SKILL.md).
+   Verify scaling + navigation + persistence once in a browser before
+   delivery.
+
+## Output format
+
+1. **One self-contained HTML file** built on the deck-shell: fixed-canvas
+   `<section>` slides with 1-indexed `data-screen-label`s, letterbox scaling,
+   keyboard/tap navigation, slide counter, `localStorage` persistence,
+   print-to-PDF CSS.
+2. **Layout-system comment block** at the top of the file naming the 4–6
+   layout types and the background-color budget.
+3. **Type-floor compliance** — body ≥24px, headlines 60–96px+ on the 1080p
+   canvas; deviations only with a stated reason.
+4. **Clean slop scan + Q13** — `lint_design_slop` findings resolved or
+   DESIGN.md-justified; no system internals in the artifact.
+
+## Do NOT
+
+- Do NOT hand-roll the scaling/navigation — start from the deck-shell
+  starter; re-derived viewport math drifts.
+- Do NOT use responsive units/breakpoints inside slides — a deck is
+  fixed-canvas; the shell scales the whole stage.
+- Do NOT drop body text below 24px on a 1080p canvas — projector legibility
+  is the floor, not a preference.
+- Do NOT pad with filler slides or invented stats — every slide earns its
+  place.
+- Do NOT introduce per-slide ad-hoc colors/spacing — the layout system from
+  step 2 is the budget.
+- Do NOT embed system internals (paths, skill/tool names, generator traces)
+  in the file — Q13.
+
+## Gotcha
+
+- `localStorage` persistence keys on `location.pathname` — two decks served
+  from the same path share a slide index; rename the file per deck or extend
+  the key when hosting several decks under one path.
+- Print-to-PDF uses the fixed canvas per page: browsers map it onto the
+  paper size — set the print dialog to landscape + "fit to page" or the
+  slides clip; test one print preview before shipping a PDF.
+- Emoji in slide headlines is the CP5 tell exactly as in product UI — the
+  deck medium doesn't exempt it.
+
+## See also
+
+- `templates/deck-shell.html` (skill-local) — the canonical shell; copy, don't re-derive.
+- [`canvas-design`](../canvas-design/SKILL.md) — static posters/one-frame art (not decks).
+- [`design-intelligence`](../design-intelligence/SKILL.md) — direction/palette/type grounding.
+- [`design-tokens`](../design-tokens/SKILL.md) / [`brand-to-tokens`](../brand-to-tokens/SKILL.md) — token precedence and emission.
+- [`design-review`](../design-review/SKILL.md) — final review gate.
+- [`docs/guidelines/design-antipatterns.md`](../../../docs/guidelines/design-antipatterns.md) — catalog, CP5, Q13.

package/dist/agent-src/skills/html-deck/evals/triggers.json

@@ -0,0 +1,17 @@
+{
+  "skill": "html-deck",
+  "last_eval": "2026-07-06",
+  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers deck/slides/presentation/pitch builds in HTML. Should-not-trigger covers near-miss neighbors: canvas-design (posters/static art), fe-design (responsive UI), design-variations (options), PowerPoint-file requests, and content-only outline asks.",
+  "queries": [
+    {"q": "make a 10-slide deck for the investor pitch", "trigger": true},
+    {"q": "build a presentation from this PRD for the engineering all-hands", "trigger": true},
+    {"q": "turn these notes into HTML slides I can present tomorrow", "trigger": true},
+    {"q": "create a pitch deck with our brand colors, 16:9", "trigger": true},
+    {"q": "I need a slide presentation that also prints to PDF", "trigger": true},
+    {"q": "design a poster for the conference booth", "trigger": false, "note": "static one-frame art → canvas-design"},
+    {"q": "build the landing page hero section", "trigger": false, "note": "responsive UI → fe-design / stack executor"},
+    {"q": "show me 3 design options for this dashboard", "trigger": false, "note": "options → design-variations"},
+    {"q": "write an outline for my talk", "trigger": false, "note": "content-only ask, no HTML deliverable"},
+    {"q": "export our Google Slides to PowerPoint", "trigger": false, "note": "file conversion, not an HTML deck build"}
+  ]
+}

package/dist/agent-src/skills/html-deck/templates/deck-shell.html

@@ -0,0 +1,77 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>Deck</title>
+<style>
+  /* Deck shell — fixed-canvas slides (default 1920×1080) letterboxed to any
+     viewport. Slides are direct children <section> of <main class="deck">. */
+  :root { --deck-w: 1920; --deck-h: 1080; }
+  * { margin: 0; padding: 0; box-sizing: border-box; }
+  html, body { height: 100%; background: #111; overflow: hidden; }
+  .deck { position: absolute; top: 50%; left: 50%; width: calc(var(--deck-w) * 1px); height: calc(var(--deck-h) * 1px); transform-origin: center center; }
+  .deck > section { position: absolute; inset: 0; display: none; overflow: hidden; background: #fafafa; color: #1a1a1a; }
+  .deck > section.active { display: block; }
+  .deck-counter { position: fixed; right: 16px; bottom: 12px; font: 14px/1 monospace; color: #888; z-index: 10; }
+  @media print {
+    html, body { height: auto; overflow: visible; background: none; }
+    .deck { position: static; transform: none !important; width: auto; height: auto; }
+    .deck > section { position: relative; display: block; width: calc(var(--deck-w) * 1px); height: calc(var(--deck-h) * 1px); page-break-after: always; }
+    .deck-counter { display: none; }
+  }
+</style>
+</head>
+<body>
+<main class="deck">
+  <!-- Each slide: <section data-screen-label="01 Title">…</section> (1-indexed
+       labels match the counter the viewer sees). Replace the samples. -->
+  <section data-screen-label="01 Title">
+    <h1 style="font-size:96px;padding:120px">Deck title</h1>
+  </section>
+  <section data-screen-label="02 Content">
+    <h2 style="font-size:64px;padding:120px 120px 40px">Section</h2>
+    <p style="font-size:32px;padding:0 120px">Body text on a 1080p canvas stays at 24px minimum; 32px preferred.</p>
+  </section>
+</main>
+<div class="deck-counter" aria-hidden="true"></div>
+<script>
+(() => {
+  const deck = document.querySelector(".deck");
+  const slides = Array.from(deck.querySelectorAll(":scope > section"));
+  const counter = document.querySelector(".deck-counter");
+  const KEY = "deck-slide:" + location.pathname;
+  let i = Math.min(parseInt(localStorage.getItem(KEY) || "0", 10) || 0, slides.length - 1);
+
+  function show(n) {
+    i = Math.max(0, Math.min(n, slides.length - 1));
+    slides.forEach((s, k) => s.classList.toggle("active", k === i));
+    counter.textContent = (i + 1) + " / " + slides.length;
+    localStorage.setItem(KEY, String(i));
+  }
+
+  function fit() {
+    const w = parseFloat(getComputedStyle(document.documentElement).getPropertyValue("--deck-w"));
+    const h = parseFloat(getComputedStyle(document.documentElement).getPropertyValue("--deck-h"));
+    const scale = Math.min(innerWidth / w, innerHeight / h);
+    deck.style.transform = "translate(-50%, -50%) scale(" + scale + ")";
+  }
+
+  addEventListener("keydown", (e) => {
+    if (e.key === "ArrowRight" || e.key === "PageDown" || e.key === " ") show(i + 1);
+    else if (e.key === "ArrowLeft" || e.key === "PageUp") show(i - 1);
+    else if (e.key === "Home") show(0);
+    else if (e.key === "End") show(slides.length - 1);
+  });
+  // Tap/click navigation: right two-thirds advances, left third goes back.
+  addEventListener("click", (e) => {
+    if (e.target.closest("a, button, input, textarea, select, [contenteditable]")) return;
+    show(e.clientX < innerWidth / 3 ? i - 1 : i + 1);
+  });
+  addEventListener("resize", fit);
+  fit();
+  show(i);
+})();
+</script>
+</body>
+</html>

package/dist/agent-src/skills/judge-code-quality/SKILL.md

@@ -3,6 +3,7 @@ model_tier: high
 name: judge-code-quality
 description: "Use when a diff needs a readability review — naming, single-responsibility, DRY, dead code, mismatch with codebase conventions — dispatched by /review-changes, /do-and-judge, /judge."
 domain: quality
+parallelizable: files
 workspaces:
   - agent-config-maintainer
 packs:

package/dist/agent-src/skills/laravel/SKILL.md

@@ -1,7 +1,6 @@
 ---
 model_tier: medium
 name: laravel
-source: package
 description: "Writes Laravel PHP — Eloquent, Artisan controllers, FormRequests, jobs, events, policies, providers. For Symfony / Doctrine use `symfony-workflow`. For framework-free PHP use `php-coder`."
 domain: engineering
 workspaces:

package/dist/agent-src/skills/learning-to-rule-or-skill/SKILL.md

@@ -233,6 +233,26 @@ before handing to `upstream-contribute`. The
 gate is hard: non-zero exit = the proposal does not move
 to stage `gated`.
 
+### 9. Degrade the source to a pointer (when promoted from a knowledge page)
+
+If the learning came from an `agents/knowledge/procedures/skill-candidates.md`
+entry or any other `agents/knowledge/` page (see § "Knowledge-candidate
+learnings" below), promotion is **not complete** until the source is
+degraded to a pointer — this prevents double-maintenance between the
+knowledge page and the new artifact:
+
+```bash
+./scripts-run src/scripts/degrade_to_pointer \
+    --source "agents/knowledge/procedures/skill-candidates.md#<topic>" \
+    --artifact "<promoted-artifact-path>" \
+    --date "<YYYY-MM-DD>"
+```
+
+This rewrites the source entry to `Promoted to <artifact> on <date>; see
+<path>.` and regenerates `agents/knowledge/INDEX.md`. Skip when the
+learning's source was NOT a knowledge page (direct user request,
+audit-log pattern, one-off observation).
+
 ## Output format
 
 For the **decision step** (what this skill prints to the user):
@@ -332,6 +352,32 @@ mining `agents/runtime/state/audit/<YYYY-MM>.jsonl`
    and link the mining-script run id, so the human reviewer can
    reproduce the pattern from the raw audit log.
 
+## Knowledge-candidate learnings (optional source)
+
+When the input is an entry from `agents/knowledge/procedures/skill-candidates.md`
+that reached candidate status (≥ 3 mentions across distinct sessions —
+see `update_skill_candidates.ts` and the
+[`memory-consolidation`](../memory-consolidation/SKILL.md) recurrence
+step):
+
+1. Treat the candidate's topic as the **State the learning** step
+   input (§1). The repetition gate (§0) is already satisfied by the
+   ≥ 3-mention threshold — skip straight to §3 (decide the target).
+   Overlap check (§4) and proposal draft (§8) remain mandatory.
+2. **Ground the draft in the original session logs, never the
+   consolidated summary alone.** The candidate entry's `Sessions:`
+   list names the chat-history session ids the topic recurred in —
+   pull those via [`/chat-history import`](../../../commands/chat-history/import.md)
+   (select by id) or the host's native transcript view before
+   drafting. A skill written purely from the recurrence-counter
+   summary tends to be plausible but wrong; the original transcripts
+   carry the detail the summary dropped.
+3. Set `source_learning` to the knowledge-candidate entry
+   (`agents/knowledge/procedures/skill-candidates.md#<topic>`).
+4. **§9 (degrade the source) is mandatory for this source type** —
+   the whole point of the candidate counter is that it stops counting
+   once promoted.
+
 ## Environment notes
 
 Prefer updating existing rule/skill when possible.

package/dist/agent-src/skills/lint-skills/SKILL.md

@@ -9,8 +9,8 @@ execution:
   timeout_seconds: 120
   allowed_tools: []
   command:
-    - python3
-    - src/scripts/skill_linter.ts
+    - ./scripts-run
+    - src/scripts/skill_linter
     - "--all"
 workspaces:
   - agent-config-maintainer
@@ -39,8 +39,8 @@ Do NOT use when:
 
 ### 1. Inspect the environment
 
-Confirm `python3` is available and the working directory is the agent-config
-repository root — the linter expects to find `.agent-src.uncondensed/skills/`
+Confirm `./scripts-run` is executable and the working directory is the agent-config
+repository root — the linter expects to find `src/skills/`
 and related directories relative to `cwd`.
 
 ### 2. Dispatch via the runtime layer
@@ -53,7 +53,7 @@ this skill's frontmatter governs the call:
 ```
 
 The dispatcher resolves the request, the shell handler runs
-`python3 src/scripts/skill_linter.ts --all`, captures stdout/stderr, and returns
+`./scripts-run src/scripts/skill_linter --all`, captures stdout/stderr, and returns
 a typed `ExecutionResult`.
 
 ### 3. Verify the result
@@ -64,7 +64,7 @@ Check the returned `ExecutionResult`:
 - `exit_code: 1` → warnings only — review `stdout` for the listed warnings
 - `exit_code: 2` → errors present — fix the flagged files before continuing
 - `status: timeout` → the linter exceeded `timeout_seconds` — investigate
-- `status: error` → the interpreter could not launch — check that `python3`
+- `status: error` → the runner could not launch — check that `./scripts-run`
   is on `PATH` and the repository root is the current working directory
 
 ## Output format

package/dist/agent-src/skills/md-language-check/SKILL.md

@@ -9,8 +9,8 @@ execution:
   timeout_seconds: 30
   allowed_tools: []
   command:
-    - python3
-    - scripts/check_md_language.py
+    - ./scripts-run
+    - src/scripts/check_md_language
 workspaces:
   - agent-config-maintainer
 packs:
@@ -114,7 +114,7 @@ proceeds on exit `0`.
 ## Do NOT
 
 - Do NOT silence the checker by deleting trigger words from
-  `scripts/check_md_language.py`; extend the allow-list (anchor
+  `src/scripts/check_md_language.ts`; extend the allow-list (anchor
   blocks, ignore marker) instead
 - Do NOT add the ignore marker to body prose just to push a save
   through; the marker is for meta-documentation that quotes tokens,

package/dist/agent-src/skills/memory-consolidation/SKILL.md

@@ -101,9 +101,35 @@ miner is too loose; tighten patterns and re-run before promoting.
    curated YAML (next phase) become team-shared (committed).
 3. Default to `--preview` mode: render the JSONL block to stdout and
    stop. Only `--commit-intake` writes the file.
+4. **Triage each fact NOT already promoted to curated YAML** against
+   `agents/knowledge/{concepts,procedures}/` before treating it as
+   brand new:
+
+   | Triage | Condition | Action |
+   |---|---|---|
+   | `NEW` | No existing knowledge page covers this topic | Candidate for a new page (via `/team-knowledge consolidate`, not this skill) |
+   | `EXTEND` | An existing page covers the topic but is missing this detail | Note the target page in the report; do not edit mid-cycle |
+   | `CONFIRM` | An existing page already states this exactly | Discard — no duplicate entry |
+   | `CONFLICT` | An existing page states the opposite or a stale variant | Record **both** positions verbatim in the report with a `contested: true` recommendation for that page — never silently overwrite; resolution is always human |
+
+5. **Track cross-cycle recurrence toward skill-candidacy.** For each
+   `NEW` fact, run:
+
+   ```bash
+   ./scripts-run src/scripts/update_skill_candidates --topic "<stable-slug>" --session "<session-id>" --date "<YYYY-MM-DD>"
+   ```
+
+   This increments a durable per-topic counter in
+   `agents/knowledge/procedures/skill-candidates.md` — a fact that
+   recurs unpromoted across ≥ 3 consolidation cycles becomes a live
+   candidate the exit report surfaces for
+   [`learning-to-rule-or-skill`](../learning-to-rule-or-skill/SKILL.md)
+   to pick up. This script only counts; it never proposes or writes
+   the skill/rule itself. Regenerate `agents/knowledge/INDEX.md`
+   (`generate_knowledge_index.ts`) after any candidate update.
 
 **Exit gate:** every fact carries ≥ 1 tag and a JSONL-shape that
-validates against the contract.
+validates against the contract; every fact has a triage verdict.
 
 ### Phase 4 — PRUNE & INDEX
 
@@ -143,6 +169,15 @@ skills — github.com/ViktorAxelsen/MemSkill, Apache-2.0, commit `9907c35f8cc7`)
   reusable facts, not transcripts or one-off chatter.
 - **One durable fact per entry.** No narrative blobs — each entry is a single
   PATTERN / CONVENTION / INVARIANT / GOTCHA the next agent can act on.
+- **"Don't relitigate" memories carry scope + `revisit-if`.** A memory that
+  locks a question as settled — an honest-null verdict, a council convergence,
+  a maintainer call — is not a permanent law; it is a decision under the
+  conditions that held when it was written. Record what exactly is settled
+  (narrow enough that a different-but-similar proposal is not silently
+  covered) and at least one concrete condition that reopens it. Tag whether
+  it is **settled-by-evidence** (an eval ran) or **settled-by-decision** (a
+  maintainer call) — the latter is cheaper to reopen. See
+  [`decision-revisit-gate`](../../rules/decision-revisit-gate.md).
 
 This is **meta-memory**: the skill of *how to remember* (what to extract,
 keep, forget) — distinct from the remembered content. The store stays simple
@@ -151,6 +186,36 @@ INSERT/UPDATE/DELETE/NOOP operation machinery (append-only JSONL + curated
 YAML need no such ops) and do **not** import any retrieval / decay / trust
 engine.
 
+## Applying recalled memories
+
+How memories are *written* is covered above; this section covers how
+recalled content is *used* once retrieved.
+
+- **Apply selectively and contextually.** A recalled fact surfaces only
+  when it's relevant to the current turn — not as a demonstration that
+  memory exists.
+- **Never narrate the retrieval mechanism.** Forbidden phrases: "I
+  remember", "based on your memories", "according to your profile/data",
+  "I can see from memory". Recalled facts surface as normal working
+  knowledge, indistinguishable in tone from anything else the agent knows.
+- **Sensitivity floor.** Recalled content about sensitive topics
+  (personal difficulties, conflicts, health) is never surfaced
+  unprompted — only when the user raises the topic first, this session.
+  Bringing up a sensitive memory unprompted is not just unhelpful, it is
+  actively harmful.
+- **Staleness still applies.** A recalled memory reflects what was true
+  when it was written — verify referenced files/flags/state still hold
+  before treating it as current (see the memory-and-other-persistence
+  guidance this skill's callers already carry).
+
+### Retrieval-trigger linguistics
+
+Before answering from scratch, treat these as signals to consult memory
+first: possessives ("my/our X"), definite references to unnamed prior
+work ("that bug", "the migration"), and past-time cues ("last week",
+"back then"). These phrasings imply the user expects continuity with
+something already known, not a first-time explanation.
+
 ## TranscriptAdapter contract
 
 The miner is host-agnostic by design. A `TranscriptAdapter` for host

package/dist/agent-src/skills/migration-architect/SKILL.md

@@ -5,6 +5,7 @@ description: "Use when shaping a non-trivial migration — rollout phases, dual-
 personas:
   - backend-architect
   - senior-engineer
+  - data-integrity
 domain: process
 workspaces:
   - engineering

package/dist/agent-src/skills/module-detect-on-the-fly/SKILL.md

@@ -67,8 +67,8 @@ Confirm both flags via `get_modules_config()` before running detection.
 
    - **Option 1** — build the payload (matches `propose_modules_config.py
      --json` shape, includes `detection_acknowledged: true`), pipe into
-     `python3 scripts/apply_modules_config.py --project <root>`.
-   - **Option 2** — run `python3 scripts/apply_modules_config.py
+     `./scripts-run src/scripts/apply_modules_config --project <root>`.
+   - **Option 2** — run `./scripts-run src/scripts/apply_modules_config
      --project <root> --acknowledge-only`. Flips only the ack flag;
      every other `modules.*` key stays untouched.
    - **Option 3** — list candidates, then loop back to step 3.

package/dist/agent-src/skills/performance-analysis/SKILL.md

@@ -2,6 +2,8 @@
 model_tier: high
 name: performance-analysis
 description: "ONLY when user explicitly requests: performance audit, bottleneck analysis, or N+1 query detection. NOT for regular feature work."
+personas:
+  - performance-engineer
 domain: discovery
 workspaces:
   - engineering

package/dist/agent-src/skills/prediction-pool-optimizer/SKILL.md

@@ -145,9 +145,9 @@ Don't hand-pick a scoreline. Run the executed grid optimiser — builds the full
 Poisson score grid, returns the EV-max tip under the step-1 point tiers:
 
 ```bash
-python3 scripts/prediction-pool/score_ev.py --lh <home-xg> --la <away-xg> \
+./scripts-run src/scripts/prediction-pool/score_ev --lh <home-xg> --la <away-xg> \
     --tendency <t> --diff <d> --exact <e>          # one match
-python3 scripts/prediction-pool/score_ev.py matches.json \
+./scripts-run src/scripts/prediction-pool/score_ev matches.json \
     --tendency <t> --diff <d> --exact <e>          # batch, prints a ranked table
 ```
 
@@ -176,7 +176,7 @@ of the field)**; pure EV-max converges with the crowd, can't open a gap.
 Measure it with the executed field simulator, not a "rough Kelly" hand-wave:
 
 ```bash
-python3 scripts/prediction-pool/pool_winsim.py pool.json --runs 4000 --max-flips 4
+./scripts-run src/scripts/prediction-pool/pool_winsim pool.json --runs 4000 --max-flips 4
 ```
 
 Models the field as softmax-EV tippers, reports `P(win)` for EV-max-everywhere,
@@ -204,7 +204,7 @@ question type — full taxonomy + per-type method in
   winner") aggregated per step 2, **or** the executed Poisson simulator:
 
   ```bash
-  python3 scripts/prediction-pool/poisson_sim.py <teams-xg.json> --runs 20000
+  ./scripts-run src/scripts/prediction-pool/poisson_sim <teams-xg.json> --runs 20000
   ```
 
   It plays the bracket from per-team expected goals and prints empirical

package/dist/agent-src/skills/premortem/SKILL.md

@@ -1,18 +1,15 @@
 ---
 name: premortem
 description: "Use before committing to a heavy or irreversible plan — imagine it's 6 months later and this failed; enumerate why, score each mode, derive early-warning signals and preventive guardrails."
-source: package
 domain: quality
 model_tier: high
 workspaces:
   - engineering
 packs:
   - analysis-workbench
-lifecycle: active
 trust:
   level: professional
   confidence: medium
-  human_review_required: false
 install:
   default: false
   removable: true

package/dist/agent-src/skills/project-analysis-core/SKILL.md

@@ -129,6 +129,22 @@ Check:
 6. Known uncertainties
 7. Recommended next specialist skill
 
+## Knowledge capture (`convention_detected` events)
+
+An architecture-map or stack finding that recurs (naming convention,
+module boundary, layering rule) is worth persisting for the team.
+Append to the knowledge intake instead of leaving it in the one-off
+analysis output — applies to every `project-analysis-*` specialist
+this skill hands off to:
+
+```bash
+./scripts-run src/scripts/emit_knowledge_event --type convention_detected \
+    --pattern "<pattern>" --evidence "file:line" --sample-size <N> --scope project
+```
+
+`/team-knowledge consolidate` turns accumulated events into
+`agents/knowledge/concepts/` pages as a reviewed batch.
+
 ## Gotcha
 
 * If versions are guessed, the whole analysis becomes unreliable.

package/dist/agent-src/skills/reasoning-orchestrator/SKILL.md

@@ -71,7 +71,9 @@ coordinates.
 Each link **delegates** to the artifact that owns it (no duplication):
 
 1. **ground** — close constraints/tools/info-gaps before designing
-   ([`think-before-action` § Environment grounding](../../rules/think-before-action.md)).
+   ([`think-before-action` § Environment grounding](../../rules/think-before-action.md));
+   seed the read from the **repo** slot of the
+   [context-spine](../../../docs/contracts/context-spine.md) when present.
 2. **intent** — state the inferred goal + one recommendation, standard host only
    ([`improve-before-implement` § Intent inference](../../rules/improve-before-implement.md)).
 3. **notes** — hypotheses/predictions/decisions/uncertainty to the notes file, not