aiblueprint-cli 1.4.108 → 1.4.109

package/agents-config/skills/test-audit/LICENSE

@@ -0,0 +1,23 @@
+Adapted from https://github.com/openclaw/openclaw/tree/main/.agents/skills/test-audit
+
+MIT License
+
+Copyright (c) 2026 OpenClaw Foundation
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/agents-config/skills/test-audit/SKILL.md

@@ -0,0 +1,169 @@
+---
+name: test-audit
+description: "Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand."
+---
+
+# Test Audit
+
+Three modes, one value bar. Authoring mode gates every new or changed test at
+write time. Audit mode runs focused sweeps of tests that re-assert source,
+duplicate stronger proof, couple behavior to implementation, or keep test-only
+production seams alive. Continue broad audits as separate coherent follow-up
+PRs; optimize for confidence, not deletion count. Campaign mode prunes one
+whole subsystem's test surface (every test file a package, plugin, or core area
+owns); before starting one, read [CAMPAIGN.md](CAMPAIGN.md).
+
+## Authoring gate
+
+Before adding any test, answer four questions; a missing answer means do not
+add it yet:
+
+1. What observable behavior, invariant, or independent contract does it protect?
+2. What credible regression makes it fail?
+3. Why does existing coverage not already catch that failure? Each contract has
+   one primary test owner at the strongest boundary; another layer needs its
+   own distinct risk, such as a transport or lifecycle failure the owner cannot
+   reach. Prefer extending a table-driven case or shared fixture over a
+   near-duplicate test; consolidate duplicated setup in the same change.
+4. Does it need a production seam (export, flag, wrapper, injection hook) that no
+   production caller needs? If yes, move the test to the real boundary instead.
+
+Then check the test against every [junk pattern](#junk-patterns); a match fails
+the gate unless the [retention bar](#retention-bar) names the contract it
+independently guards. A test that would break under behavior-preserving
+refactoring is asserting implementation, not behavior; rewrite it at the
+owning boundary before landing it.
+
+Bug regression tests must fail on the pre-fix code for the intended reason and
+pass after the owner-boundary repair. A regression test that never demonstrably
+failed proves the mock, not the fix. One regression at the owner boundary
+covers the bug; do not replay the same scenario at every layer it crosses.
+
+## Junk patterns
+
+The shared checklist for both modes: the authoring gate rejects a new test that
+matches one, and audits hunt for existing tests that do.
+
+- assertion-free coverage probes;
+- self-comparisons and identity copiers;
+- copied fixtures, inventories, manifests, or export lists;
+- exact source, import, or string greps;
+- private predicate or call-shape tests duplicated at real boundaries;
+- duplicate invocations of the same contract;
+- provider-local replays of shared helpers;
+- tests whose only purpose is preserving test-only exports, globals, or wrappers;
+- dead production code whose only callers are tests;
+- expected values produced by the helper or renderer under test;
+- mocks that implement the asserted behavior, or one identical mock standing in
+  for different APIs;
+- fixtures that supply the receipt, admission, or callback ordering the owner
+  should produce, or persistence asserted against a store the path never writes;
+- capability tests that restate declared flags instead of exercising the
+  delivery or acknowledgement the flag promises;
+- negative controls that pass for an unrelated reason, such as a denial from a
+  different guard or a rejection the production path never reaches;
+- names or fixtures that promise more than the input exercises, such as a
+  "retires the window" test asserting the window was not cleared.
+
+## Value bar
+
+Tests justify their maintenance cost by protecting behavior, a credible
+regression, or an independently meaningful contract. In an audit, an existing
+test that must change for behavior-preserving source reorganization is suspect,
+not automatically deletable; the authoring gate still rejects new ones.
+
+Before judging a candidate, read the complete test and production owner, its
+entry point, callers, callees, sibling implementations, overlapping tests, CI
+routing, and relevant history. Read root and scoped `AGENTS.md` files first.
+When the test claims dependency-backed behavior, inspect the dependency source
+or types directly.
+
+## Discovery
+
+Keep discovery read-only and report evidence before editing. For broad scope,
+run parallel discovery lanes when available:
+
+- core source and packages;
+- plugins, extensions, or integrations;
+- UI, apps, scripts, and tooling;
+- a cross-cutting pattern sweep.
+
+Outside campaign mode, prefer a few high-confidence candidates over a large
+speculative inventory. Hunt for the [junk patterns](#junk-patterns).
+
+## Retention bar
+
+Keep a test when it independently enforces a public API, SDK, protocol, config,
+migration, storage, security, platform, default, generated-output, package,
+release, or architecture contract. Also keep:
+
+- call ordering when order is observable behavior;
+- regressions with a credible failure mode;
+- source inspection when it is the cheapest independent guard: it fails when
+  the contract changes (the user-facing key, byte, or path) and survives an
+  identifier-only refactor;
+- a retained test that fails on the baseline: treat it as a possible product
+  bug, reproduce it, and repair the owner rather than deleting it.
+
+Static or slow is not a deletion reason. A test that resembles implementation
+may still be the independent contract; prove otherwise before removing it.
+
+## Candidate evidence
+
+Record every field below before editing. A missing field means the candidate is
+not ready for deletion:
+
+- exact test name and location;
+- what failure it can actually detect;
+- non-test callers of the covered production or support seam;
+- stronger remaining owner-boundary proof, or why no proof is needed;
+- relevant history and the reason the test or seam exists;
+- production or test-support deletion unlocked;
+- risk and the focused validation command.
+
+## Edit shape
+
+Choose one coherent owner-boundary batch. Delete obsolete test-only exports,
+globals, wrappers, and dead production paths instead of preserving aliases.
+Move retained regressions to their canonical owners. Consolidate repeated
+package or dependency assertions into one generic contract.
+
+Prefer net-negative production LOC. Do not add replacement tests that restate
+the same implementation, and do not convert uncertain candidates into cleanup
+to increase deletion counts.
+
+## Validation
+
+Never edit source or tests while a test watcher is running in the checkout. Use
+the test commands documented in the repository's `AGENTS.md`, `CLAUDE.md`, or
+package scripts.
+
+1. Run the smallest owner and sibling tests with the repository's test runner,
+   filtered to the affected paths.
+2. For removed source greps or plan assertions, run the executable script or
+   dry-run that owns the real contract.
+3. Run targeted formatting, then `git diff --check`.
+4. Run the changed-files gate required by repository policy (lint, typecheck,
+   and the CI checks those paths trigger).
+5. Inspect `git diff --numstat`; report production/tooling separately from
+   tests and test support.
+6. After final audit edits, get an independent review of the deleted coverage
+   against the remaining keepers.
+
+## Landing and continuation
+
+Commit, push, open a PR, or land only when authorized. Follow the repository's
+PR flow. Land one coherent PR at a time; after landing, refresh from current
+`main` and rerun read-only discovery for the next high-confidence batch.
+
+## Handoff
+
+Report:
+
+- root cause and removed low-value categories;
+- production owner simplifications;
+- retained false positives and why they remain valuable;
+- focused and full proof actually run;
+- production versus test LOC;
+- PR and merge state;
+- named follow-ups.

package/agents-config/skills/test-audit/agents/openai.yaml

@@ -0,0 +1,10 @@
+interface:
+  display_name: "Test Audit"
+  short_description: "Gate new tests and prune low-value ones"
+  icon_small: "./assets/codex-icon.svg"
+  icon_large: "./assets/codex-icon.svg"
+  brand_color: "#737373"
+  default_prompt: "Use $test-audit to gate these tests or audit low-value ones."
+
+policy:
+  allow_implicit_invocation: true

package/agents-config/skills/test-audit/assets/codex-icon.svg

@@ -0,0 +1 @@
+<svg role="img" aria-label="test-audit skill icon" xmlns="http://www.w3.org/2000/svg" width="128" height="128" viewBox="0 0 24 24" fill="none" stroke="#F5F5F5" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M9 2v6.5L4.5 17A3 3 0 0 0 7.2 21h9.6a3 3 0 0 0 2.7-4L15 8.5V2"/><path d="M8 2h8"/><path d="M7 15h10"/></svg>

package/agents-config/skills/use-style/SKILL.md

@@ -1,58 +1,18 @@
 ---
 name: use-style
 description: Apply named visual style guides to landing pages, app shells, and UI. Use for $use-style, /useskill, list styles, or styles like ios-app, grid, vercel, black-grid, stripe, linear, raycast, gumroad, dusk, or luma.
+disable-model-invocation: true
+user-invocable: true
 ---
 
-Load and apply a named style before designing or implementing any UI.
+Load a named style before designing or implementing UI. Parse the name from `$ARGUMENTS` or the message. Aliases: `ios`/`iphone`/`nowstack-mobile`/`ink & spark` → `ios-app`; `use-vercel`/`geist` → `vercel`; `old vercel`/`black grid` → `black-grid`; `testsprite`/`test sprite` → `testspirite`; `lu.ma`/`luma.com` → `luma`; `super simple`/`SUPER_SIMPLE` → `super-simple`.
 
-## Invocation
+Defaults: NowStack / Expo / NativeWind → `ios-app`. Codelynx product landings → `grid`. Vercel / Geist infrastructure marketing → `vercel`. Austere monochrome tools → `black-grid`. Linear / issue tracker shell → `linear`. Newspaper / magazine → `new-york-times`. Anthropic / Claude cream lab → `anthropic`. Neo-brutalist yellow/pink → `gumroad`. Glossy dark glow marketing → `raycast`. Attio twilight CRM → `dusk`. TestSprite paper dashboard → `testspirite`. Luma / events / RSVP → `luma`.
 
-- Explicit: `$use-style ios-app`, `$use-style vercel`, `$use-style black-grid`, `/useskill list`, or "use the grid style"
-- Implicit: user references NowStack Mobile, Ink & Spark, an iOS app shell, Expo / React Native / NativeWind app UI, `/aiblueprint`, `/agents`, `/aibuilder`, "grid theme", Vercel, Geist, a minimalist dark tool UI, Stripe / fintech / checkout / dashboard UI, Linear / issue tracker / app-shell sidebar UI, NYT / newspaper / editorial / broadsheet / magazine layouts, Anthropic / Claude / warm cream AI-lab pages, Gumroad / neo-brutalist / loud commerce / bold yellow-pink pages, Raycast / glossy dark / glow gradients / floating glass nav / premium product marketing, Dusk / Attio / dark CRM dashboard floating on a twilight backdrop / blue data viz / colorful category pills, Luma / lu.ma / event timeline / calendar / RSVP / discover / a dark consumer events-and-calendar app with photo-led cards, a top teal aurora, and a white pill button, or TestSprite / TestSpirite / calm light dev-tool dashboard / warm paper canvas with one forest-green accent / grouped sidebar + promo rail / isometric line-art empty states
-
-Parse the style name from `$ARGUMENTS` or the message. Treat `ios`, `ios app`, `ios-app`, `iphone app`, `nowstack-mobile`, `nowstack mobile`, and `ink & spark` as `ios-app`. Treat `use-vercel`, `vercel style`, and `current vercel` as `vercel`. Treat `vercel-simple`, `old vercel`, `black grid`, and `black-grid` as `black-grid`. Treat `testsprite`, `test-sprite`, and `test sprite` as `testspirite`. Treat `luma`, `lu.ma`, and `luma.com` as `luma`. Treat `list`, `styles`, `available styles`, and missing style names with no implicit match as a request to list available styles and ask the user to choose before designing. Default to `ios-app` when the user references NowStack Mobile, Ink & Spark, an iOS app shell, Expo, React Native, NativeWind, or OS-native tabs. Default to `grid` for Codelynx product landings. Default to `vercel` when the user references Vercel, the Vercel dashboard, Geist, Vercel's changelog, or black infrastructure marketing with large editorial whitespace. Default to `black-grid` for austere monochrome developer tools, calculators, indexes, or line-driven data products. Default to `linear` when the user references Linear, an issue tracker, or a dense sidebar + list + detail app shell. Default to `new-york-times` when the user references a newspaper, broadsheet, magazine, or serif editorial layout. Default to `anthropic` when the user references Anthropic, Claude, or a warm cream + serif AI-lab aesthetic. Default to `gumroad` when the user references Gumroad, neo-brutalism, hard offset shadows, or a loud yellow/pink bordered look. Default to `raycast` when the user references Raycast, a glossy dark page with glow gradients, a floating glass nav, or premium dark product marketing. Default to `dusk` when the user references Attio, a dark CRM/data dashboard floating on a twilight/aurora backdrop, vivid-blue charts, or colorful category pills. Default to `testspirite` when the user references TestSprite, a calm light dev-tool dashboard, a warm paper canvas with a single forest-green accent, a grouped sidebar with a free-trial/upgrade promo rail, or isometric line-art empty states. Default to `luma` when the user references Luma, lu.ma, an event timeline/feed, a calendar or RSVP/invite app, a discover page, or a dark consumer events UI with photo-led cards, a top teal aurora, and a white pill button.
-
-If the parsed style is `list`, or if no style can be inferred, do not load a style file. Reply with the available styles table below, add one short line asking which style to use, and stop until the user chooses.
-
-## Workflow
+If the name is `list` or nothing matches, list the styles in `styles/` and stop until the user chooses.
 
 1. Read `styles/<name>.md` from this skill directory.
-2. Check for project overrides and prefer them over the portable spec:
-   - `.agents/styles/<name>.md`
-   - `.agents/styles/<name>-theme.md`
-   - `.agents/styles/<name>-theme-migration.md` (migration playbooks only)
-3. Treat the loaded style as hard constraints for layout, typography, color, borders, motion, and component choice.
-4. Reuse existing primitives. In Codelynx repos, import `GridTheme*` components from `grid-theme-primitives.tsx` instead of reinventing patterns.
-
-## Available styles
-
-| Style | File | Vibe |
-|-------|------|------|
-| `ios-app` | `styles/ios-app.md` | NowStack Mobile Ink & Spark. iOS/Expo app UI with monochrome ink/paper, one yellow `#FFE040` spark, NativeWind tokens, OS-native tabs, flat hairline cards. |
-| `grid` | `styles/grid.md` | Blueprint landing. Square geometry, 1px borders, mono data, condensed display type. |
-| `vercel` | `styles/vercel.md` | Current Vercel product language. Black canvas, Geist Sans, hairline dashboard structure, dense deployment lists, vast editorial marketing space, restrained semantic color. |
-| `black-grid` | `styles/black-grid.md` | Austere monochrome developer tools. Black canvas, Geist + mono, sharp line-defined indexes and calculators, no decoration. |
-| `stripe` | `styles/stripe.md` | Stripe fintech UI. Pale `#f6f9fc` canvas, white cards on soft shadows, blurple `#635BFF` accent, green CTA, rounded geometry. |
-| `linear` | `styles/linear.md` | Linear app shell. Near-black `#08090a` canvas, dense aligned sidebar + list + detail panes, indigo `#5e6ad2` accent, Inter Display headings, quiet line-defined chrome. |
-| `new-york-times` | `styles/new-york-times.md` | Print-newspaper editorial. Paper-white, serif headlines (Cheltenham/Georgia), Franklin sans kickers, blackletter masthead, hairline rules, multi-column grid, red/blue accents only. |
-| `anthropic` | `styles/anthropic.md` | Warm AI-lab. Cream `#f0efe9` paper, bold grotesque sans display + reading serif, clay-coral `#cc785c` accent, big soft-rounded dark panels, pill buttons. Light marketing + dark Claude app surfaces. |
-| `gumroad` | `styles/gumroad.md` | Loud neo-brutalist commerce. Yellow `#ffc900` + pink `#ff90e8`, thick black borders, hard offset shadows `4px 4px 0 #000`, flat fills, bold geometric sans, pill buttons. Light marketplace + dark dashboard surfaces. |
-| `raycast` | `styles/raycast.md` | Glossy dark product marketing. Near-black `#0a0a0a` + red `#ff6363` glow, floating glass nav (`backdrop-blur`), oversized bold pricing, large-radius `rounded-3xl` cards, soft glow over hard shadows. |
-| `dusk` | `styles/dusk.md` | Refined dark data app (Attio-style). Rounded near-black window floating on a twilight gradient backdrop, vivid sky-blue `#38bdf8` charts, `#3b6eff` primary, colorful category pills, Inter + mono numbers. |
-| `luma` | `styles/luma.md` | Dark consumer events + calendar app (Luma/lu.ma). Near-black `#0a0a0b` canvas with one soft teal aurora at the top, near-borderless `rounded-2xl` photo-led cards, white pill primary buttons, blue `#2f6bff` status pills, gold `#f5b13d` event times, centered timeline column. |
-| `testspirite` | `styles/testspirite.md` | Calm light dev-tool app shell (TestSprite). Warm paper-white `#f7f7f3` canvas, one forest-green `#3d7c4e` accent, grouped sidebar + promo rail, soft `rounded-xl` cards on quiet borders, pale-green `#eaf3ea` status pills, isometric line-art empty states. |
-
-Add new styles as `styles/<name>.md` and register them here.
-
-## Output rules
-
-- Match the style vibe precisely. Do not blend with generic SaaS aesthetics.
-- Honor the anti-patterns section in the style file.
-- When a project spec lists concrete tokens or components, use those over prose approximations.
-- For landing pages, scaffold the page shell from the style first, then fill sections.
-
-## Related skills
+2. Prefer project overrides: `.agents/styles/<name>.md`, `<name>-theme.md`, `<name>-theme-migration.md`.
+3. Treat the loaded style as hard constraints. Reuse existing primitives (Codelynx: `GridTheme*` from `grid-theme-primitives.tsx`).
 
-- `frontend-design` / `frontend-skill`: general UI craft. Defer to `use-style` when a named style is requested.
-- `use-feature`: reusable feature and UX implementation patterns that are not visual styles.
-- `impeccable`: polish pass after the style is applied.
+Match the vibe exactly. Honor the style file's anti-patterns. Scaffold the shell first on landing pages. `impeccable` is the polish pass after the style is applied.