@mmerterden/multi-agent-pipeline 12.5.0 → 12.7.0

package/pipeline/skills/shared/external/python-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: python-patterns
-description: "Modern Python 3.12+: type hints, dataclasses, Pydantic v2, async/await, context managers, generators, pattern matching"
+description: "Modern Python 3.12+: type hints, dataclasses, Pydantic v2, async/await, context managers, generators, pattern matching. Use when writing or reviewing modern Python: typing, dataclasses, Pydantic, async, generators."
 tags: [python, type-hints, pydantic, asyncio, dataclasses, backend]
 version: "2025.1"
 ---

package/pipeline/skills/shared/external/react-best-practices/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: react-best-practices
-description: "React 19+ best practices: Server Components, use() hook, Actions, hooks patterns, state management, and performance optimization"
+description: "React 19+ best practices: Server Components, use() hook, Actions, hooks patterns, state management, and performance optimization. Use when building or reviewing React work: components, hooks, state, Server Components, Actions."
 tags: [react, frontend, javascript, typescript, hooks, state-management]
 version: "2025.1"
 ---

package/pipeline/skills/shared/external/rest-api-design/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rest-api-design
-description: "REST API design: HTTP methods, status codes, pagination, versioning, rate limiting, caching headers, OpenAPI documentation"
+description: "REST API design: HTTP methods, status codes, pagination, versioning, rate limiting, caching headers, OpenAPI documentation. Use when a REST surface needs designing or reviewing: methods, status codes, pagination, versioning, caching."
 tags: [rest, api, http, openapi, pagination, backend]
 version: "2025.1"
 ---

package/pipeline/skills/shared/external/search-first/SKILL.md

@@ -71,6 +71,6 @@ person does not redo the search.
 ## Anti-patterns
 
 - **Jumping to code** before step 0-4.
-- **Silent skipping** — reporting no prior art when a channel was down or
+- **Silent skipping** - reporting no prior art when a channel was down or
   unchecked.
-- **Dependency reflex** — adding a package for a one-liner the repo already has.
+- **Dependency reflex** - adding a package for a one-liner the repo already has.

package/pipeline/skills/shared/external/skill-creator/SKILL.md

@@ -1,31 +1,31 @@
 ---
 name: skill-creator
 version: 1.0.0
-description: "Author and refine skills for a plugin/toolkit efficiently. Use when creating a new skill, trimming or splitting an existing one, writing a skill's description, or choosing skill vs command vs agent vs CLAUDE.md. Encodes the house rules — lean SKILL.md as an index, progressive disclosure into bundled files, the reference (descriptive) vs workflow (imperative) split, no-prefix naming, and growing a skill from observed failures. Bundles a template, a pre-ship checklist, and good/bad description examples."
+description: "Author and refine skills for a plugin/toolkit efficiently. Use when creating a new skill, trimming or splitting an existing one, writing a skill's description, or choosing skill vs command vs agent vs CLAUDE.md. Encodes the house rules - lean SKILL.md as an index, progressive disclosure into bundled files, the reference (descriptive) vs workflow (imperative) split, no-prefix naming, and growing a skill from observed failures. Bundles a template, a pre-ship checklist, and good/bad description examples."
 user-invocable: true
 argument-hint: [new | trim | description]
 allowed-tools: Read, Write, Edit, Glob
 ---
 
-# skill-creator — how to write skills here
+# skill-creator - how to write skills here
 
 > **Layer:** reference (knowledge)
 > **Use when:** creating/trimming a skill, writing a description, or choosing skill vs command/agent/CLAUDE.md.
 > **Bundled (read on demand):** [template.md](template.md) · [checklist.md](checklist.md) · [examples.md](examples.md) · [label-check.md](label-check.md) · [audit.md](audit.md)
 
 ## 1. Is a skill the right tool?
-- **CLAUDE.md** — broad facts/rules true *every* session.
-- **Skill** — on-demand procedure or knowledge for a recurring task.
-- **Subagent/agent** — needs independent reasoning + its own context/tools.
-- **MCP server** — structured integration with an external system's API.
+- **CLAUDE.md** - broad facts/rules true *every* session.
+- **Skill** - on-demand procedure or knowledge for a recurring task.
+- **Subagent/agent** - needs independent reasoning + its own context/tools.
+- **MCP server** - structured integration with an external system's API.
 
 ## 2. The description is discovery (the 90% lever)
 It's the *only* thing the model sees when deciding to load the skill. **Write it first.** Include **what + when + trigger words + one example trigger**, in third person. (Anthropic's data: vague→specific lifts activation ~20%→50%; adding examples ~72%→90%.) Good/bad pairs in [examples.md](examples.md).
 
 ## 3. Keep it lean (it stays in context every turn once loaded)
-- `SKILL.md` is an **index** — aim for ~1 page, hard cap ~500 lines.
-- Push detail into bundled files **one level deep** (reference, examples, scripts). They cost zero tokens until read; nested-deeper files get partially read — don't nest.
-- A **script executes without its source entering context** — prefer a script over asking the model to regenerate code.
+- `SKILL.md` is an **index** - aim for ~1 page, hard cap ~500 lines.
+- Push detail into bundled files **one level deep** (reference, examples, scripts). They cost zero tokens until read; nested-deeper files get partially read - don't nest.
+- A **script executes without its source entering context** - prefer a script over asking the model to regenerate code.
 - Challenge every line: *"would Claude err without this?"* If no, cut it.
 
 ## 4. Pick the right degree of freedom (= our layers)
@@ -34,9 +34,9 @@ It's the *only* thing the model sees when deciding to load the skill. **Write it
 - **tool skill → thin index over a script/CLI:** lean SKILL.md (when + the run command + sub-commands at a glance), heavy detail in a bundled `reference.md`; the script is the engine (e.g. `tools/figma-utility`).
 
 ## 5. Naming
-No platform prefix — the toolkit name + description already carry it. Reference = aspect noun (`navigation`); workflow = verb-phrase (`branch-and-pr`). Avoid vague/reserved (`helper`, `utils`, `claude-*`). For a name/title/strict-rule label that must carry its **whole intent**, validate it with the fresh-subagent inference test in [label-check.md](label-check.md) before committing.
+No platform prefix - the toolkit name + description already carry it. Reference = aspect noun (`navigation`); workflow = verb-phrase (`branch-and-pr`). Avoid vague/reserved (`helper`, `utils`, `claude-*`). For a name/title/strict-rule label that must carry its **whole intent**, validate it with the fresh-subagent inference test in [label-check.md](label-check.md) before committing.
 
-## 6. Grow it from real usage — don't pre-write
+## 6. Grow it from real usage - don't pre-write
 1. Do the task **without** a skill; note where Claude actually fails.
 2. Write the **minimum** that fixes those gaps.
 3. Watch Claude use it: move reused detail up into SKILL.md, cut detail it ignores, sharpen the description if it didn't trigger.
@@ -44,5 +44,5 @@ No platform prefix — the toolkit name + description already carry it. Referenc
 ## Before shipping
 Start from [template.md](template.md); run [checklist.md](checklist.md). For a new or
 substantially-changed skill that must be trusted, run the **multi-architect audit**
-([audit.md](audit.md)) — a panel of distinct-lens reviewers + synthesis, looped
+([audit.md](audit.md)) - a panel of distinct-lens reviewers + synthesis, looped
 fix → re-audit until no blockers/majors remain.

package/pipeline/skills/shared/external/skill-creator/audit.md

@@ -1,4 +1,4 @@
-# Multi-architect audit — adversarial quality gate for a skill
+# Multi-architect audit - adversarial quality gate for a skill
 
 The [checklist](checklist.md) is the self-review floor. This is the **high-confidence
 gate**: a panel of N independent reviewers, each a *distinct lens*, reads the skill
@@ -6,22 +6,22 @@ against the rubric + ground truth, then a synthesizer dedups and rules. You **lo
 fix → re-audit until it passes** (no blockers/majors). Run it before shipping a new
 or substantially-changed skill, or whenever a skill must be trusted.
 
-Use the [Workflow tool](scripts/audit-panel.js) to fan the panel out — it returns
+Use the [Workflow tool](scripts/audit-panel.js) to fan the panel out - it returns
 `{remaining, clearsBar, verdict}`.
 
 ## The loop (run to convergence)
-1. **Panel** — N agents, one lens each, read-only. Each returns specific findings
+1. **Panel** - N agents, one lens each, read-only. Each returns specific findings
    (severity · file:location · problem · concrete fix). Empty if its lens is clean.
-2. **Synthesize** — dedup overlaps; **drop false positives** (verify each against the
+2. **Synthesize** - dedup overlaps; **drop false positives** (verify each against the
    real files/repo before keeping); classify blocker / major / minor / nit;
    `clearsBar = no blockers and no majors remain`.
-3. **If not clean** — apply the do-now set (blockers + majors + cheap high-value
+3. **If not clean** - apply the do-now set (blockers + majors + cheap high-value
    minors), then run a **fresh** panel (see "Fresh each round") and repeat.
 4. **Stop** when `clearsBar` is true. The later/nit list is optional polish.
 
 ## Rules that make it trustworthy
 - **Fresh panel each round.** After a fix, re-run the panel anew so agents read the
-  *current* files — do not reuse a prior run's cached results (they reflect the old
+  *current* files - do not reuse a prior run's cached results (they reflect the old
   state and will report fixed issues as open / miss regressions).
 - **Verify before keeping.** Every finding must be confirmed against the actual file
   or repo. The synthesizer drops anything it can't reproduce. Prefer findings that
@@ -29,31 +29,31 @@ Use the [Workflow tool](scripts/audit-panel.js) to fan the panel out — it retu
 - **Ground-truth, not vibes.** Give the panel the rubric ([SKILL.md](SKILL.md) +
   [checklist.md](checklist.md)), an exemplar skill, and the real source the skill
   describes (e.g. the iOS repo). Agents read; they don't assume.
-- **Watch for regressions.** A fix can break something — the red-team lens and the
+- **Watch for regressions.** A fix can break something - the red-team lens and the
   fresh re-audit exist to catch it (e.g. a broadened check that now false-positives).
 - **clearsBar gates the merge.** Don't merge with an open blocker/major.
 
-## Lenses — pick the set for the task
+## Lenses - pick the set for the task
 One distinct lens per agent (+ a synthesizer). Two ready-made sets:
 
-**General skill audit** — discovery · leanness · shape/layer · scripts · accuracy-vs-source · domain-correctness · wiring · boundaries · red-team → synthesis.
+**General skill audit** - discovery · leanness · shape/layer · scripts · accuracy-vs-source · domain-correctness · wiring · boundaries · red-team → synthesis.
 
-**Prompt-engineering audit** (when the concern is *prompt quality* — descriptions,
+**Prompt-engineering audit** (when the concern is *prompt quality* - descriptions,
 instructions, triggering):
-1. **description-as-discovery** — what + when + trigger words + example; would it activate on a real task?
-2. **disambiguation** — distinct from siblings; a reader can tell when to pick this vs a neighbor.
-3. **trigger coverage** — the real user phrasings (and synonyms) are covered.
-4. **instruction clarity** — steps are unambiguous, ordered, single-interpretation; no vague directives.
-5. **degrees of freedom / layer fit** — reference=descriptive (no numbered procedure), workflow=spine, tool=thin-index; freedom matches the task.
-6. **progressive disclosure / leanness** — SKILL.md is an index; detail bundled one level deep; no duplication.
-7. **token efficiency** — every line is load-bearing; nothing restates what the model already knows.
-8. **consistency** — terminology, naming, paths, cross-references, examples all agree.
-9. **anti-patterns / misfire** — would the model over-apply it, skip a gate, hallucinate a path, or follow it into a wrong output?
-10. **red-team** — adversarially try to make it not trigger, trigger wrongly, or produce broken output; hunt overclaims (says X, the script doesn't).
+1. **description-as-discovery** - what + when + trigger words + example; would it activate on a real task?
+2. **disambiguation** - distinct from siblings; a reader can tell when to pick this vs a neighbor.
+3. **trigger coverage** - the real user phrasings (and synonyms) are covered.
+4. **instruction clarity** - steps are unambiguous, ordered, single-interpretation; no vague directives.
+5. **degrees of freedom / layer fit** - reference=descriptive (no numbered procedure), workflow=spine, tool=thin-index; freedom matches the task.
+6. **progressive disclosure / leanness** - SKILL.md is an index; detail bundled one level deep; no duplication.
+7. **token efficiency** - every line is load-bearing; nothing restates what the model already knows.
+8. **consistency** - terminology, naming, paths, cross-references, examples all agree.
+9. **anti-patterns / misfire** - would the model over-apply it, skip a gate, hallucinate a path, or follow it into a wrong output?
+10. **red-team** - adversarially try to make it not trigger, trigger wrongly, or produce broken output; hunt overclaims (says X, the script doesn't).
 
 Scale the panel to risk: a quick check is ~3 lenses; a thorough gate is ~10.
 
 ## Scope of fixes per round
 Fix **blockers + majors** always; fold in **cheap, high-value minors** while you're
 in the file. Defer speculative nits and pre-existing/out-of-scope drift to the
-"later" list (and `log()`/note them — don't silently drop coverage).
+"later" list (and `log()`/note them - don't silently drop coverage).

package/pipeline/skills/shared/external/skill-creator/checklist.md

@@ -9,13 +9,13 @@ Run before considering a skill done.
 
 ## Leanness
 - [ ] `SKILL.md` reads like an index, ~1 page (hard cap ~500 lines).
-- [ ] Detail lives in bundled files **one level deep** — no nested-deeper references.
-- [ ] Every line survives "would Claude err without this?" — no over-explaining, no restating what the model knows.
+- [ ] Detail lives in bundled files **one level deep** - no nested-deeper references.
+- [ ] Every line survives "would Claude err without this?" - no over-explaining, no restating what the model knows.
 - [ ] Deterministic code is a **script**, not prose asking the model to regenerate it.
 
 ## Shape
 - [ ] Layer is explicit (reference or workflow) and matches the content.
-- [ ] **Reference** skill has **no numbered procedures** — heuristics + pointers only.
+- [ ] **Reference** skill has **no numbered procedures** - heuristics + pointers only.
 - [ ] **Workflow** skill's numbered steps are **only** the deterministic/irreversible spine, and it has a **verification gate**.
 - [ ] Conventions **point to canonical files** rather than pasting code that will rot.
 

package/pipeline/skills/shared/external/skill-creator/examples.md

@@ -1,22 +1,22 @@
-# Examples — descriptions & shape
+# Examples - descriptions & shape
 
 ## Descriptions: the discovery lever
 
-**Bad (vague — rarely triggers):**
+**Bad (vague - rarely triggers):**
 ```yaml
 description: Helps with navigation
 ```
-Why it fails: no "when", no trigger words, no platform — the router can't tell what task this matches.
+Why it fails: no "when", no trigger words, no platform - the router can't tell what task this matches.
 
 **Good (what + when + triggers + platform):**
 ```yaml
-description: "In-app navigation for a SwiftUI iOS app — the coordinator-per-domain pattern, the tab shell, cross-domain navigation, deep links, and modals. Reach for this when adding a screen, a tab, a deep link, or a modal, or deciding how one screen reaches another."
+description: "In-app navigation for a SwiftUI iOS app - the coordinator-per-domain pattern, the tab shell, cross-domain navigation, deep links, and modals. Reach for this when adding a screen, a tab, a deep link, or a modal, or deciding how one screen reaches another."
 ```
 Why it works: states the domain, lists concrete triggers ("adding a screen, a tab, a deep link"), names the platform, and implies the boundary.
 
 **Workflow example (action + when to run):**
 ```yaml
-description: "Branch, commit, push, and open a PR for this repo. Owns the git/PR spine and house guardrails — type-first branch names, no AI attribution, no force-push, correct base branch. Reach for this whenever a change is ready to ship."
+description: "Branch, commit, push, and open a PR for this repo. Owns the git/PR spine and house guardrails - type-first branch names, no AI attribution, no force-push, correct base branch. Reach for this whenever a change is ready to ship."
 ```
 
 ### Recipe
@@ -26,7 +26,7 @@ description: "Branch, commit, push, and open a PR for this repo. Owns the git/PR
 
 ## Shape: reference vs workflow
 
-**Wrong — a reference skill drifting into a procedure:**
+**Wrong - a reference skill drifting into a procedure:**
 ```markdown
 ## Procedures
 1. Open the file
@@ -36,7 +36,7 @@ description: "Branch, commit, push, and open a PR for this repo. Owns the git/PR
 ```
 A reference (knowledge) skill should describe *the rule and where the canonical example lives*, not script the keystrokes.
 
-**Right — reference stays descriptive:**
+**Right - reference stays descriptive:**
 ```markdown
 ## Decision rules
 - New screen in a domain → add `<Name>Screen` under its Presentation layer,
@@ -44,14 +44,14 @@ A reference (knowledge) skill should describe *the rule and where the canonical
   Canonical: `<repo>/Features/Profile/ProfileScreen.swift`.
 ```
 
-**Right — workflow earns its numbered steps** (deterministic/irreversible spine):
+**Right - workflow earns its numbered steps** (deterministic/irreversible spine):
 ```markdown
 ## Procedures
 1. Pre-flight: `git status` clean? on base branch?
 2. Branch: `git checkout -b <type>/<scope>/<desc>`
 3. Commit: stage; conventional message; strip any AI co-author trailer.
 4. Push; never force-push a protected branch.
-5. PR: `gh pr create --base <base> …` (no AI footer).
+5. PR: `gh pr create --base <base> ...` (no AI footer).
 ## Verification
 - `git log -1` shows clean message, no AI trailer, correct author.
 ```
@@ -60,6 +60,6 @@ A reference (knowledge) skill should describe *the rule and where the canonical
 
 ## Leanness: cut what the model already knows
 
-**Bloat:** "PDF files are documents that contain text and images. To read them you first need a library that can parse the binary format…"
+**Bloat:** "PDF files are documents that contain text and images. To read them you first need a library that can parse the binary format..."
 
 **Lean:** "Extract text from PDFs with `pdfplumber`."

package/pipeline/skills/shared/external/skill-creator/label-check.md

@@ -1,35 +1,35 @@
-# Label intent check — does a title carry its own meaning?
+# Label intent check - does a title carry its own meaning?
 
-A label (rule title, section header, principle/constraint name) is the handle a reader grasps *before* the body. If the handle leaks the wrong shape — ambiguous, one-sided, or off-topic — the reader forms the wrong model and the body has to fight it. This is a cheap test that catches that early: have **fresh subagents infer the rule from the label alone**, then compare against your intended meaning. Convergence = the label is self-carrying.
+A label (rule title, section header, principle/constraint name) is the handle a reader grasps *before* the body. If the handle leaks the wrong shape - ambiguous, one-sided, or off-topic - the reader forms the wrong model and the body has to fight it. This is a cheap test that catches that early: have **fresh subagents infer the rule from the label alone**, then compare against your intended meaning. Convergence = the label is self-carrying.
 
 ## When to run it
 - Naming a **strict rule** or constraint inside a skill (the kind a reader must obey).
 - A **section header** that gates non-trivial content (phase/principle/constraint names).
-- Any label meant to convey the **whole intent** of its body (not a summary — the intent).
-- Skip it for purely organizational labels ("Examples", "See also") — they carry no intent.
+- Any label meant to convey the **whole intent** of its body (not a summary - the intent).
+- Skip it for purely organizational labels ("Examples", "See also") - they carry no intent.
 
 ## Inputs (collect first)
-1. **Candidate label** — the exact string under test.
-2. **Surrounding context** — one paragraph: which skill/doc, what adjacent labels cover, the domain concepts in play.
-3. **Intended meaning** — 1–3 sentences of ground truth (what the body says / what the reader should walk away believing). **Not** shown to the inference agents. If you can't state it in 3 sentences, the body is unclear — fix that first.
+1. **Candidate label** - the exact string under test.
+2. **Surrounding context** - one paragraph: which skill/doc, what adjacent labels cover, the domain concepts in play.
+3. **Intended meaning** - 1-3 sentences of ground truth (what the body says / what the reader should walk away believing). **Not** shown to the inference agents. If you can't state it in 3 sentences, the body is unclear - fix that first.
 
 ## Procedure
 **One iteration = 5 parallel subagents**, each given ONLY the label + context (never the body), each forced to commit:
 ```
-Context: <surrounding context — 1 paragraph>.
+Context: <surrounding context - 1 paragraph>.
 The label under test is: **"<candidate label>"**
 You have NOT seen the body. From ONLY this label + context, what do you infer it
-enforces / requires / means? 1–2 concrete sentences, under 80 words. Commit — no
+enforces / requires / means? 1-2 concrete sentences, under 80 words. Commit - no
 hedging, no clarifying questions.
 ```
 Launch all 5 in the **same** message (parallel) so they're independent by construction.
 
 **Convergence (per iteration), comparing the 5 inferences to the intended meaning:**
-- **PASS** — ≥4/5 cover *all* key intent beats (including the bidirectional / edge / scope beat, if the intent has one). Wording drift is fine.
-- **PARTIAL** — they consistently catch one side of a bidirectional rule but miss the other, or over-extend into an adjacent concern. Revise the label, re-run.
-- **FAIL** — inferences diverge wildly or miss the core beat. Revise, re-run.
+- **PASS** - ≥4/5 cover *all* key intent beats (including the bidirectional / edge / scope beat, if the intent has one). Wording drift is fine.
+- **PARTIAL** - they consistently catch one side of a bidirectional rule but miss the other, or over-extend into an adjacent concern. Revise the label, re-run.
+- **FAIL** - inferences diverge wildly or miss the core beat. Revise, re-run.
 
-**Idempotency (after a PASS):** run **2 more rounds**, 5 fresh agents each (3×5 = 15 inferences), same prompt. Require **all 3 rounds PASS** with no new systematic miss — confirms the PASS wasn't luck. A regression in round 2/3 → treat as PARTIAL and iterate.
+**Idempotency (after a PASS):** run **2 more rounds**, 5 fresh agents each (3×5 = 15 inferences), same prompt. Require **all 3 rounds PASS** with no new systematic miss - confirms the PASS wasn't luck. A regression in round 2/3 → treat as PARTIAL and iterate.
 
 **Termination:** converged (3/3 PASS) → apply the label. 3 iterations without a PASS → stop, hand back the best candidate + the persistent miss; don't force a label that won't stick.
 
@@ -37,7 +37,7 @@ Launch all 5 in the **same** message (parallel) so they're independent by constr
 5 agents/round · 3 rounds · 80-word inference cap · max 3 iterations before handing back. High-stakes labels (top-level skill names, protocol names) → 7 agents × 3 rounds; throwaway section headers → 3 × 2.
 
 ## Anti-patterns
-- **Giving agents the body** — defeats the test (you're checking the label's *self-carrying* power).
-- **Running sequentially** — they'd anchor on each other; must be parallel.
-- **Tweaking one word on a FAIL** — step back and rethink the concept the label names, don't polish a wrong handle.
-- **Accepting "mostly right"** — a label that reliably misses a beat misleads every reader the same way. Fix it, or accept the rule is one-sided and split the body.
+- **Giving agents the body** - defeats the test (you're checking the label's *self-carrying* power).
+- **Running sequentially** - they'd anchor on each other; must be parallel.
+- **Tweaking one word on a FAIL** - step back and rethink the concept the label names, don't polish a wrong handle.
+- **Accepting "mostly right"** - a label that reliably misses a beat misleads every reader the same way. Fix it, or accept the rule is one-sided and split the body.

package/pipeline/skills/shared/external/skill-creator/scripts/audit-panel.js

@@ -1,42 +1,57 @@
-// audit-panel.js — Workflow template for the multi-architect skill audit.
+// audit-panel.js - Workflow template for the multi-architect skill audit.
 //
 // Run with the Workflow tool. Edit the CONFIG block for your target, then launch.
 // Returns { remaining, clearsBar, verdict }. If clearsBar is false, apply the
-// `remaining` blockers/majors, then RE-RUN A FRESH copy (do NOT resume — agents
+// `remaining` blockers/majors, then RE-RUN A FRESH copy (do NOT resume - agents
 // must read the current files). Loop until clearsBar. See ../audit.md.
 
 export const meta = {
-  name: 'skill-audit-panel',
-  description: 'Adversarial N-architect audit of a skill against the skill-creator rubric',
-  phases: [{ title: 'Audit' }, { title: 'Synthesis' }],
-}
+  name: "skill-audit-panel",
+  description: "Adversarial N-architect audit of a skill against the skill-creator rubric",
+  phases: [{ title: "Audit" }, { title: "Synthesis" }],
+};
 
-// ── CONFIG — edit these ──────────────────────────────────────────────────────
+// ── CONFIG - edit these ──────────────────────────────────────────────────────
 const TARGET = `
 - <abs path to SKILL.md>
 - <abs path to each bundled file / script>
-`
-const RUBRIC = `<abs path to reference/skill-creator/SKILL.md> + checklist.md`
-const EXEMPLAR = `<abs path to a known-good skill of the same layer>`
-const GROUND_TRUTH = `<abs path to the real source the skill describes (e.g. the iOS repo), with key facts>`
+`;
+const RUBRIC = `<abs path to reference/skill-creator/SKILL.md> + checklist.md`;
+const EXEMPLAR = `<abs path to a known-good skill of the same layer>`;
+const GROUND_TRUTH = `<abs path to the real source the skill describes (e.g. the iOS repo), with key facts>`;
 // Pick a lens set from audit.md (general or prompt-engineering). [label, brief] pairs:
 const LENSES = [
-  ['discovery', 'description-as-discovery: what+when+trigger words+example; would it activate on a real task?'],
-  ['disambiguation', 'distinct from sibling skills; a reader can tell when to pick this vs a neighbor.'],
-  ['triggers', 'real user phrasings + synonyms are covered.'],
-  ['clarity', 'instructions unambiguous, ordered, single-interpretation; no vague directives.'],
-  ['layer', 'degrees of freedom match the layer (reference=descriptive / workflow=spine / tool=thin-index).'],
-  ['leanness', 'SKILL.md is an index; detail bundled one level deep; no duplication or bloat.'],
-  ['tokens', 'every line load-bearing; nothing restates what the model already knows.'],
-  ['consistency', 'terminology, naming, paths, cross-refs, examples all agree.'],
-  ['misfire', 'would the model over-apply, skip a gate, hallucinate a path, or follow it to a wrong output?'],
-  ['redteam', 'adversarially make it not trigger / trigger wrongly / produce broken output; hunt overclaims (says X, script does not).'],
-]
+  [
+    "discovery",
+    "description-as-discovery: what+when+trigger words+example; would it activate on a real task?",
+  ],
+  [
+    "disambiguation",
+    "distinct from sibling skills; a reader can tell when to pick this vs a neighbor.",
+  ],
+  ["triggers", "real user phrasings + synonyms are covered."],
+  ["clarity", "instructions unambiguous, ordered, single-interpretation; no vague directives."],
+  [
+    "layer",
+    "degrees of freedom match the layer (reference=descriptive / workflow=spine / tool=thin-index).",
+  ],
+  ["leanness", "SKILL.md is an index; detail bundled one level deep; no duplication or bloat."],
+  ["tokens", "every line load-bearing; nothing restates what the model already knows."],
+  ["consistency", "terminology, naming, paths, cross-refs, examples all agree."],
+  [
+    "misfire",
+    "would the model over-apply, skip a gate, hallucinate a path, or follow it to a wrong output?",
+  ],
+  [
+    "redteam",
+    "adversarially make it not trigger / trigger wrongly / produce broken output; hunt overclaims (says X, script does not).",
+  ],
+];
 // ─────────────────────────────────────────────────────────────────────────────
 
 const COMMON = `
 You are auditing a skill. Read the CURRENT files and report ONLY genuine, specific,
-reproducible findings for YOUR lens. Verify against the rubric + ground truth — do
+reproducible findings for YOUR lens. Verify against the rubric + ground truth - do
 not assume. Read-only; do NOT edit. If your lens is clean, return an empty array.
 
 TARGET (the skill under audit):${TARGET}
@@ -45,39 +60,60 @@ EXEMPLAR (known-good of this layer): ${EXEMPLAR}
 GROUND TRUTH (what the skill describes): ${GROUND_TRUTH}
 
 Each finding: severity (blocker|major|minor|nit), file:location, the problem, the concrete fix.
-`
+`;
 
 const FINDING = {
-  type: 'object', additionalProperties: false,
+  type: "object",
+  additionalProperties: false,
   properties: {
-    severity: { type: 'string', enum: ['blocker', 'major', 'minor', 'nit'] },
-    location: { type: 'string' }, problem: { type: 'string' }, fix: { type: 'string' },
-  }, required: ['severity', 'location', 'problem', 'fix'],
-}
+    severity: { type: "string", enum: ["blocker", "major", "minor", "nit"] },
+    location: { type: "string" },
+    problem: { type: "string" },
+    fix: { type: "string" },
+  },
+  required: ["severity", "location", "problem", "fix"],
+};
 const LENS_SCHEMA = {
-  type: 'object', additionalProperties: false,
-  properties: { lens: { type: 'string' }, findings: { type: 'array', items: FINDING } },
-  required: ['lens', 'findings'],
-}
+  type: "object",
+  additionalProperties: false,
+  properties: { lens: { type: "string" }, findings: { type: "array", items: FINDING } },
+  required: ["lens", "findings"],
+};
 
-phase('Audit')
-const results = await parallel(LENSES.map(([lens, brief]) => () =>
-  agent(`${COMMON}\n\nYOUR LENS — ${lens}: ${brief}`, { label: `audit:${lens}`, phase: 'Audit', schema: LENS_SCHEMA })
-))
-const all = results.filter(Boolean).flatMap(r => r.findings.map(f => ({ ...f, lens: r.lens })))
+phase("Audit");
+const results = await parallel(
+  LENSES.map(
+    ([lens, brief]) =>
+      () =>
+        agent(`${COMMON}\n\nYOUR LENS - ${lens}: ${brief}`, {
+          label: `audit:${lens}`,
+          phase: "Audit",
+          schema: LENS_SCHEMA,
+        }),
+  ),
+);
+const all = results.filter(Boolean).flatMap((r) => r.findings.map((f) => ({ ...f, lens: r.lens })));
 
-phase('Synthesis')
+phase("Synthesis");
 const SYNTH = {
-  type: 'object', additionalProperties: false,
+  type: "object",
+  additionalProperties: false,
   properties: {
-    remaining: { type: 'array', items: { type: 'object', additionalProperties: false,
-      properties: { ...FINDING.properties, lenses: { type: 'string' } },
-      required: [...FINDING.required, 'lenses'] } },
-    clearsBar: { type: 'boolean' },
-    verdict: { type: 'string' },
-  }, required: ['remaining', 'clearsBar', 'verdict'],
-}
+    remaining: {
+      type: "array",
+      items: {
+        type: "object",
+        additionalProperties: false,
+        properties: { ...FINDING.properties, lenses: { type: "string" } },
+        required: [...FINDING.required, "lenses"],
+      },
+    },
+    clearsBar: { type: "boolean" },
+    verdict: { type: "string" },
+  },
+  required: ["remaining", "clearsBar", "verdict"],
+};
 return await agent(
-  `${COMMON}\n\nYou are the SYNTHESIS architect. Below are ${all.length} raw findings from ${LENSES.length} lenses. Dedup overlaps (note which lenses raised each). DROP false positives — verify against the files before keeping; if you cannot reproduce it, drop it. Classify each survivor; set clearsBar=true ONLY if no blockers and no majors remain. One-paragraph verdict.\n\nRAW:\n${JSON.stringify(all, null, 2)}`,
-  { label: 'synthesis', phase: 'Synthesis', schema: SYNTH }
-)
+  `${COMMON}\n\nYou are the SYNTHESIS architect. Below are ${all.length} raw findings from ${LENSES.length} lenses. Dedup overlaps (note which lenses raised each). DROP false positives - verify against the files before keeping; if you cannot reproduce it, drop it. Classify each survivor; set clearsBar=true ONLY if no blockers and no majors remain. One-paragraph verdict.\n\nRAW:\n${JSON.stringify(all, null, 2)}`,
+  { label: "synthesis", phase: "Synthesis", schema: SYNTH },
+);

package/pipeline/skills/shared/external/skill-creator/template.md

@@ -1,30 +1,30 @@
 # Skill skeletons
 
-Two skeletons — pick by layer. Both stay lean; push detail into one-level-deep bundled files.
+Two skeletons - pick by layer. Both stay lean; push detail into one-level-deep bundled files.
 
 Frontmatter fields used in this toolkit: `name`, `description` (required-quality), `user-invocable`, `argument-hint` (optional), `allowed-tools`.
 
 ---
 
-## Reference skill (descriptive — knowledge)
+## Reference skill (descriptive - knowledge)
 
 No numbered procedures. Principles + pointers + heuristics.
 
 ```markdown
 ---
-name: <aspect-noun>          # e.g. navigation — NO platform prefix
+name: <aspect-noun>          # e.g. navigation - NO platform prefix
 description: <what it covers + when to reach for it + trigger words. Say "iOS/SwiftUI" so the router can disambiguate.>
 user-invocable: true
 allowed-tools: Read, Grep, Glob, Bash, Edit, Write
 ---
 
-# <name> — <short title>
+# <name> - <short title>
 
 > **Layer:** reference (knowledge)
 > **Use when:** <trigger>   **Hand off to:** <sibling skill>
 
 ## Scope
-In / out, 1–2 lines.
+In / out, 1-2 lines.
 
 ## Invariants            <!-- non-negotiables + the why -->
 ## Conventions & golden paths   <!-- point to canonical files; don't paste code -->
@@ -35,7 +35,7 @@ In / out, 1–2 lines.
 
 ---
 
-## Workflow skill (imperative — action)
+## Workflow skill (imperative - action)
 
 Has a numbered procedure, but only for the deterministic/irreversible spine. Cite reference skills for judgment. Always include a verification gate.
 
@@ -48,17 +48,17 @@ argument-hint: [<step> | ...]
 allowed-tools: Bash, Read
 ---
 
-# <name> — <short title>
+# <name> - <short title>
 
 > **Layer:** workflow (action)
 > **Use when:** <trigger>   **Don't use when:** <hand off>
 
 ## Scope
-In / out, 1–2 lines.
+In / out, 1-2 lines.
 
 ## Invariants            <!-- hard rules / guardrails -->
 ## Conventions & golden paths   <!-- base branch, auth, canonical commands -->
-## Decision rules        <!-- branch when…, escalate when… -->
+## Decision rules        <!-- branch when..., escalate when... -->
 ## Procedures            <!-- IMPERATIVE: only deterministic/irreversible steps -->
 1. ...
 ## Verification          <!-- IMPERATIVE: prove it worked (build/run/test) -->

package/pipeline/skills/shared/external/swift-concurrency-expert/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: swift-concurrency-expert
-description: Review and fix Swift concurrency issues such as actor isolation and Sendable violations.
+description: "Review and fix Swift concurrency issues such as actor isolation and Sendable violations. Use when a Swift concurrency problem needs diagnosing, such as actor isolation or a Sendable violation."
 risk: safe
 source: "Dimillian/Skills (MIT)"
 date_added: "2026-03-25"

package/pipeline/skills/shared/external/swiftui-performance-audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: swiftui-performance-audit
-description: Audit SwiftUI performance issues from code review and profiling evidence.
+description: "Audit SwiftUI performance issues from code review and profiling evidence. Use when a SwiftUI view is slow and the cause has to be found from code and profiling evidence."
 risk: safe
 source: "Dimillian/Skills (MIT)"
 date_added: "2026-03-25"

package/pipeline/skills/shared/external/swiftui-ui-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: swiftui-ui-patterns
-description: Apply proven SwiftUI UI patterns for navigation, sheets, async state, and reusable screens.
+description: "Apply proven SwiftUI UI patterns for navigation, sheets, async state, and reusable screens. Use when a SwiftUI screen needs a proven pattern for navigation, sheets, async state or reuse."
 risk: safe
 source: "Dimillian/Skills (MIT)"
 date_added: "2026-03-25"

package/pipeline/skills/shared/external/swiftui-view-refactor/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: swiftui-view-refactor
-description: Refactor SwiftUI views into smaller components with stable, explicit data flow.
+description: "Refactor SwiftUI views into smaller components with stable, explicit data flow. Use when a SwiftUI view has grown too large and needs splitting with clear data flow."
 risk: safe
 source: "Dimillian/Skills (MIT)"
 date_added: "2026-03-25"

package/pipeline/skills/shared/external/tailwind-css/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: tailwind-css
-description: "Tailwind CSS v4: utility-first styling, responsive design, dark mode, custom themes, component patterns, and cn() utility"
+description: "Tailwind CSS v4: utility-first styling, responsive design, dark mode, custom themes, component patterns, and cn() utility. Use when styling or reviewing UI with Tailwind: utilities, responsive design, dark mode, theming."
 tags: [tailwind, css, styling, responsive, dark-mode, frontend]
 version: "2025.1"
 ---