Code highlighting reused brand tokens (accent/text/border/muted), so it couldn't
be themed independently. Add syntax_string/number/keyword/comment skin keys →
syntax* theme tokens (defaulting to those brand tokens, so defaults are
unchanged) and point the highlighter at them. Documented in the element→key map.
Changing a single color kept wrecking the rest because the agent hand-authored a
new skin (often from `default`, which has no `background`, resetting the terminal
to black). Add `hermes skin set <key> <hex>`: edits the ACTIVE skin's one key in
place (a built-in is forked into an editable copy carrying its full palette), so
everything else — background included — is preserved. Plus `skin use` / `skin
list`. The skill now points tweaks at this command instead of hand-authoring.
Changing one color ("make the tool ● cyan") forked `default` — which has no
`background` — so applying it reset the terminal to its own (black) default and
dropped the active skin's palette. Teach the skill to edit the active skin's file
in place for a tweak (watcher repaints on the mtime bump), and to fork a built-in
only by carrying its full palette. Hard pitfall: never fork `default` for a tweak.
Theming was semantic-only: the gold tool `●` was `accent`, shared with
headings/links/chevrons, so "recolor tool calls" was impossible and the agent
had no key to point at. Add `ui_tool` (● + tool spinner) and `ui_thinking`
(reasoning body) tokens that fall back to accent/muted — defaults unchanged,
but now independently settable. Make diffs skinnable too (`diff_*`), which
fromSkin previously hardcoded. Document the full element→key map in the skill so
Hermes knows which knob turns what.
The TUI inherited the terminal's background; now a skin's `background` paints the
whole surface via OSC 11 when a skin is applied, and clears back to the terminal
default (OSC 111) on revert and on exit (ridden in through resetTerminalModes).
Opt-in: a skin with no `background` leaves the terminal untouched, and the
restore only fires if we actually painted. Desktop already themed its own bg;
this closes the loop so Hermes owns its background on every surface.
A skin Hermes activates (`hermes config set display.skin X`) or recolors in
place now goes live on every surface (CLI, TUI, desktop) within ~half a
second, on its own — no `/skin`, no tool-hook timing, no user action.
A gateway daemon polls the resolved skin signature `(name, active-file mtime)`
every 0.5s and broadcasts `skin.changed` on any real move — a name switch OR a
live color edit to the active skin. It routes through the SAME path `/skin`
uses, so all surfaces repaint identically. The watcher seeds its baseline at
gateway.ready (stdio + ws) so it only fires on a real change; the `/skin` RPC
seeds the baseline too so it never double-broadcasts.
Subsumes the desktop's post-turn `config.get skin` poll (its skin.changed
handler already applies).
The skill told the agent to `patch` display.skin into config.yaml; a stray indent
corrupts the file and breaks the live gateway (the reported "/ menu broke"), and
a raw file edit never live-applies in a running CLI/TUI ("nothing happened").
Route activation through the safe writer (`hermes config set display.skin`), and
state plainly that a tool call can't hot-switch a running CLI/TUI — the user runs
`/skin <name>` (desktop still auto-repaints on the next turn).
Make the Python skin engine the single source of truth for a canonical theme
shape consumed by every surface, so a skin authored in $HERMES_HOME/skins/*.yaml
(by a user or by Hermes from a prompt) themes the CLI, TUI, and desktop GUI at
once — the theme analogue of the plugin SDK.
- @hermes/shared: canonical `HermesSkin` token shape + `SKIN_COLOR_TOKENS` enum,
consumed by both TS surfaces (TUI `GatewaySkin` and desktop dedup onto it).
- Desktop: `skinToDesktopTheme` resolver (skin → CSS-var palette, VS Code-style
derive-from-seed) + `backend-sync` that registers backend skins into the theme
registry (Appearance/Cmd-K/`/skin`) and applies on a real change. Seeds on
gateway.ready (never stomps a persisted pick), applies on skin.changed and the
post-turn `config.get skin` poll (catch-all for agent-edited config.yaml).
- TUI: `fromSkin` now maps the status bar + `background` keys it was dropping.
- Gateway: `config.get skin` also returns the full resolved palette (additive).
- Skill: `hermes-themes` teaches the agent to author + activate a skin.
Each surface keeps its own normalizing resolver (ansi for the TUI, CSS vars for
the desktop, prompt_toolkit/Rich for the CLI).
A full placement grid so the agent can put a widget where it asks — dock-top/
bottom and corner zones, with corners as reserved rails that take real space
instead of floating over content. A per-widget error boundary plus lenient
ShimmerRows means generated widget code can't crash the TUI.
Reusable render primitives the SDK exposes to widget authors: sparkline/gauge/
hbars chart helpers (dimension-stable so live updates never resize the card),
an Accordion for expand/collapse sections, animated shimmer loaders, and a
streams demo that no longer reserves a phantom icon column on unfocused titles.
Hermes can write its own widgets: a loader discovers $HERMES_HOME/tui-widgets/*.mjs,
fs.watch hot-loads them the moment they land (no restart), and a tui-widgets skill
teaches the agent the contract and the openWidget-at-register auto-open recipe.
Load/error/remove events announce themselves in the transcript; a lazy intro
skeleton covers the first paint.
Add an end-to-end developer guide for extending the native Hermes Desktop
app introduced in #60638: the HermesPlugin contract, PluginContext, every
contribution area (panes, routes, sidebar nav, status/title bar, palette,
keybinds, themes, composer, mount-scoped Contribute), the host API, the
React Query + nanostores data layer, the UI kit + theme variables, the
scoped ctx.rest/ctx.socket backend (plugin_api.py under /api/plugins/<id>)
and its separate enable gate, Settings/defaultEnabled/storage, bundled
plugins, the security model, pitfalls, and a full reference.
- Register the page in the sidebar under Extending -> Plugins.
- Disambiguate from the unrelated web-dashboard plugin SDK from both
directions, and add a map-table row + a desktop user-guide pointer.
- Fill the gaps in the agent-facing hermes-desktop-plugins skill
(ctx.rest/socket + backend, React Query, defaultEnabled, Contribute)
and point it at the new reference so agents know the SDK when writing
addons.
Hermes' computer_use wrapper dropped cua-driver's structured action verdicts,
exposed no delivery_mode, and injected background-only guidance — so the agent
reported unverified no-ops as success and concluded cua-driver 'cannot drive'
Electron/Chromium surfaces (observed live on tldraw offline). Fixes#67052.
Phase A — preserve the result contract:
- ActionResult carries verified/effect/escalation/path/degraded/code/delivery_mode
- CuaDriverBackend._action() reads structuredContent (was data-only); a helper
normalizes it, additive and None-safe on old drivers
- _text_response surfaces the fields additively (ok stays transport-only)
Phase B — bounded, model-reachable foreground:
- delivery_mode (background|foreground) + bring_to_front on the schema, dispatcher,
ABC, and all input methods
- foreground is capability-gated (input.delivery_mode); old drivers get a
structured foreground_unsupported refusal, never a silent background downgrade
- no automatic/hidden foreground retry — the model selects it from the signal
Phase C — guidance + isolation:
- system prompt (prompt_builder) and bundled skills/computer-use/SKILL.md go from
background-ONLY to background-FIRST, teaching the AX→PX→foreground ladder driven
by returned effect/escalation, not predicted from the app being Electron
- foreground approval scoped by (action, delivery_mode): a background approval
never silently authorizes foreground
- approval state keyed per session_id so concurrent gateway runs don't leak unlocks
Tests: tests/tools/test_computer_use_delivery_ladder.py (15) cover confirmed/
unverifiable/suspected_noop/degraded/old-driver verdicts, delivery_mode gating +
foreground_unsupported, and session-scoped foreground approval. Existing 265
computer_use tests still green.
Live E2E (real cua-driver 0.8.3 + tldraw offline on Linux/X11): a background click
returned effect='unverifiable'/path='ax' (no fabricated success), and a foreground
request returned code='foreground_unsupported' — correct on a driver that predates
the input.delivery_mode capability.
Add an optional skill for connecting OAuth-gated remote MCP servers
(Better Stack, Linear, Cloudflare, Datadog, Stripe, etc.) when Hermes
runs as a remote gateway, where the built-in browser OAuth flow cannot
capture the 127.0.0.1 callback.
Covers the manual RFC 7591 DCR + RFC 7636 PKCE + authorization_code
flow, writing tokens in Hermes' HermesTokenStorage schema, the
dashboard-first escalation path, and a diagnostic script + pitfalls
for refresh/session-revocation recovery.
Disable address reuse so an existing family-specific listener cannot silently split traffic with the webhook server. Normalize wildcard bind hosts for local CLI URLs and align setup documentation with the dual-stack default.
Add patterns 30-34: forced metaphors/figurative overwriting, dramatic fragmentation and punchy kickers, rhetorical questions answered immediately, sentence-opener tics, and reassurance kickers. These cover structural/rhythm tells the existing 29 patterns miss (short subjectless dramatic fragments, cutesy aphorisms, rhetorical Q-and-A).
Add a 'marketing and blog cliches' list to pattern 7 for the business/LinkedIn register (game-changer, circle back, deep dive, moving forward, ...) that the Wikipedia-derived vocabulary list does not catch.
Edit the skill's own instructional prose to follow its own guidance: remove em dashes and negative parallelism from the narration so the skill models the writing it asks for. Before/After examples are left intact so the demonstrations still show the tells.
Update the pattern count (29 -> 34) and the attribution note to mark 30-34 and the pattern-7 additions as Hermes additions beyond the blader/humanizer source.
Follow-up to #60944 (webhook payload filters and route scripts):
- reference/cli-commands.md (en+zh): document the new --script option on
'hermes webhook subscribe'
- zh-Hans user-guide webhooks.md: mirror the Payload Filters and Script
Filters/Transforms sections plus the filters/script route properties
(the salvage shipped English-only docs)
- hermes-agent skill webhooks reference: teach the agent the filters/
script surface so agent-driven subscriptions can use them
Address all 5 review points against actual delegate_task behavior:
- child toolsets are subject to delegate restrictions (leaf strips
delegate_task/clarify/memory/send_message/execute_code), not 'full'
- durable work has lighter options than kanban (cron one-shot,
managed background terminal) for simpler cases
- unique per-run /tmp/wf_<name>_<uuid> dir + freshness/count check so
a stale interrupted run isn't read as success
- note that one delegate_task batch is capped by
delegation.max_concurrent_children; large fan-out needs bounded waves
- delegate_task exposes no per-task model/profile field (per-task keys
are goal/context/toolsets/role); model/profile-scoped runs go via
delegation config, cron, kanban, or separate process
Adapts Claude Code's research-preview dynamic workflows (plan-in-code
fan-out, hundreds of subagents per session) to Hermes invariants.
The ported mechanic is plan/loop/intermediate-state-out-of-context, not
more subagents. Documents the two real orchestration layers and the hard
capability boundary between them:
- Layer A (execute_code): deterministic fan-out, SANDBOX_ALLOWED_TOOLS
only, cannot call delegate_task
- Layer B (delegate_task batch): LLM-judgment fan-out
Plus the synchronous trap (delegate_task is turn-scoped, cancelled on new
message; durable/resumable = kanban swarm) and the genuinely-new piece:
the adversarial-convergence verification recipe (N independent attempts
with varied framings + M refuters, keep only located claims that survive
refutation, iterate to convergence).
Self-contained: inlines the load-bearing fan-out hygiene rather than
hard-depending on local-only skills; references the shipped kanban swarm
subsystem for the durable path.
ruff check --fix --select F541 . on current main. Pure prefix removals;
adjacent-string concatenations keep the f only on interpolating fragments.
No string content or live placeholder altered.
The model could pass `toolsets` (top-level and per-task) to delegate_task,
letting it choose which toolsets a subagent got. Toolset selection is a
capability-scoping decision the model should not control; subagents inherit
the parent's enabled toolsets, period.
- Remove `toolsets` from the delegate_task() signature, the registry handler,
the top-level + per-task JSON schema, and the live dispatch path
(run_agent._dispatch_delegate_task — this forwarded it on every model call).
- Single-task and per-task child builds now pass toolsets=None so
_build_child_agent resolves to pure parent inheritance.
- Drop the now-dead _SUBAGENT_TOOLSETS / _TOOLSET_LIST_STR schema-hint block.
- _build_child_agent keeps its internal toolsets param + intersection helpers
(internal API; fed the inherited value only).
- Tests: schema assertions flipped to assertNotIn; added a regression test
proving the dispatch path never forwards a smuggled model `toolsets`.
- Docs: update delegate_task signature refs in the autonomous-ai-agents skill.
Port the two genuinely-novel ideas from Command Code's /design skill into
our existing claude-design skill (skill-only, zero model-tool footprint):
- Surface-First: commit to one of 7 surface archetypes (Monitor/Operate/
Compare/Configure/Decide/Explore/Command) before any visual tokens. Most
AI design slop is compositional, not cosmetic — conditioning generation on
a surface choice collapses entropy the way a CoT step does. Workflow step 3.
- Slop Diagnostic: the ~10 tells that account for ~90% of the 'this is AI'
signal, as a score-out-of-10 self-audit. Diagnose-then-treat: the report is
context not a to-do list; repair only what fired, matched to the tell
(re-layout vs recolor vs de-decorate). Workflow step 7 (Verify).
Did NOT clone /design's 16-mode CLI, proprietary reference corpus, or make it
a core tool. Docs page regenerated via generate-skill-docs.py.
Refresh the hermes-agent skill against the last 5 major releases and the
current codebase, and cut verbose prose.
Coverage added (v0.13.0–v0.17.0):
- New gateway platforms: iMessage (Photon), Teams, LINE, SimpleX, ntfy,
Google Chat, Raft, official WhatsApp Business Cloud API (now 20+).
- New surfaces section: desktop app, web dashboard admin panel,
hermes proxy (OpenAI-compatible OAuth proxy), Automation Blueprints.
- delegate_task(background=true) async subagents; memory-tool atomic
batch operations; session_search three-mode shape; x_search/video_analyze
toolsets; image_gen image-to-image; xAI Grok via SuperGrok OAuth.
- display.interface (cli/tui), curator.consolidate opt-in, PyPI install.
Accuracy fixes:
- Adding-a-Tool is two files (auto-discovery), not three.
- Testing uses scripts/run_tests.sh (canonical runner), not bare pytest.
- Dropped change-detector test count and a dangling references/ pointer.
- Refreshed overview (Windows-native, 20+ providers, many surfaces).
Conciseness: trimmed over-explained Windows keybinding/sandbox/test prose
and deep prompt-builder internals to pointers.
* feat(moa): expose MoA presets as selectable virtual models
Reconstructed onto current main (PR #46081's base had diverged with no common
ancestor, marking the PR dirty so CI never dispatched). MoA is now a virtual
provider: each named preset is a selectable model under provider 'moa', and the
preset's aggregator is the acting model that answers and calls tools.
Reference models fan out in parallel via a bounded ThreadPoolExecutor (the same
batch pattern delegate_task uses) — all references dispatched at once, collected
when every one finishes, then handed to the aggregator. Output order is
preserved, failures and the MoA-recursion guard stay isolated per reference.
- Removed the old mixture_of_agents model tool and moa toolset.
- Added moa as a virtual provider in the provider/model inventory.
- /moa is shortcut behavior over model selection (default preset / named preset
/ one-shot prompt).
- Dashboard + Desktop manage named presets; presets appear in model pickers.
- Parallel reference fan-out in agent/moa_loop.py with regression test.
* fix(moa): thread moa_config through _run_agent to _run_agent_inner
The reconstructed gateway MoA wiring declared moa_config on _run_agent (the
profile-scoping wrapper) and used it inside _run_agent_inner, but the wrapper
never forwarded it — _run_agent_inner had no such parameter, so the runtime hit
NameError: name 'moa_config' is not defined on the compression-failure session
sync path. Add moa_config to _run_agent_inner's signature and forward it from
both wrapper call sites (multiplex and non-multiplex). Caught by
tests/gateway/test_compression_failure_session_sync.py on CI shard test(4).
* fix(moa): classify moa as a virtual provider in the catalog
The moa virtual provider has no PROVIDER_REGISTRY/ProviderProfile entry, so
provider_catalog() fell through to the default auth_type="api_key" with no
env vars — tripping two catalog invariants:
- test_provider_catalog: api_key providers must expose a credential env var
- test_provider_parity: every hermes-model provider must be desktop-configurable
moa already declares auth_type="virtual" in HERMES_OVERLAYS; consult that
overlay as an auth_type fallback so the catalog reports moa as virtual (no real
credential, no network endpoint). Exempt virtual providers from the desktop
parity union check the same way 'custom' is exempt — derived from the catalog,
not a hardcoded slug, so future virtual providers are covered too.
Make the computer_use toolset platform-agnostic by driving cua-driver on
macOS, Windows, and Linux. Consumes the 8 cua-driver decoupling surfaces
(capability discovery, structuredContent AX tree, opaque element_token,
click button enum, explicit mimeType, machine-readable manifest,
structured list_windows, structured health_report), each degrading
gracefully on older drivers.
Adds `hermes computer-use doctor` (drives cua-driver health_report with a
per-OS check matrix and an exit 0/1/2 ok/degraded/blocked contract), full
typed wrappers for the previously-uncovered cua-driver tools plus a generic
call_tool escape hatch, per-session agent-cursor lifecycle, platform-aware
system-prompt guidance (host-deterministic, cache-safe), and honors
HERMES_CUA_DRIVER_CMD end-to-end.
Replaces the macOS-only skills/apple/macos-computer-use skill with a
cross-platform skills/computer-use skill, and refreshes the EN + zh-Hans
docs.
Supersedes #44221 (Windows-enablement salvage of #30660).
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
* feat(providers): remove google-gemini-cli + google-antigravity OAuth providers
Google now actively bans accounts for third-party tools that piggyback on
Gemini CLI / Antigravity / Code Assist OAuth, and because abuse prevention
sits at a backend layer the ban can extend to the entire Google account
(Gmail/Drive), with a second violation being permanent.
Ref: https://github.com/google-gemini/gemini-cli/discussions/20632
Removes both OAuth inference providers entirely (modules, provider profiles,
auth/runtime/config/models wiring, the /gquota Code Assist quota command,
the antigravity-cli optional skill, desktop + docs surface in en + zh-Hans).
The API-key 'gemini' provider (GOOGLE_API_KEY/GEMINI_API_KEY against
generativelanguage.googleapis.com) is unaffected and stays fully supported.
* fix(skills): keep the antigravity-cli skill — only the OAuth provider is removed
The antigravity-cli optional skill orchestrates the external `agy` binary as
a coding-agent tool via the terminal tool — it does NOT wrap Hermes inference
through the banned google-antigravity OAuth provider, so it carries none of
the account-ban risk that motivated removing that provider. Restore the skill,
its docs page, the sidebar entry, and the optional-skills catalog row. The
google-antigravity / google-gemini-cli inference providers stay fully removed.
The kanban-worker and kanban-orchestrator bundled skills existed only to
be force-loaded into dispatcher-spawned workers, gated by
environments:[kanban] so they wouldn't leak into normal CLI listings.
That gating was fragile (the leak that #50443 patched) and the
--skills auto-load was already best-effort — most workers ran without it
because the bundled skill isn't present in profile-scoped skills dirs.
Remove the skills entirely and promote their load-bearing content
(workspace kinds, deliverable artifacts, created-card integrity, profile
discovery) into KANBAN_GUIDANCE, which is already injected into every
kanban worker's system prompt. Net result: every worker reliably gets
the guidance, nothing can leak into a CLI/blank-slate session, and the
gating machinery is gone.
- agent/prompt_builder.py: promote the 4 load-bearing rules into KANBAN_GUIDANCE
- hermes_cli/kanban_db.py: drop --skills kanban-worker auto-injection + _kanban_worker_skill_available probe
- hermes_cli/kanban_swarm.py: drop skills=[kanban-orchestrator] on the root card
- hermes_cli/kanban.py: drop kanban-init skill seeding; fix help text
- delete skills/devops/kanban-{worker,orchestrator}
- docs: delete the two skill pages (EN+zh), fix sidebars/catalog/kanban.md/kanban-worker-lanes.md and the video-orchestrator + codex-lane references
- tests: update spawn-argv expectations; re-bound the guidance-size guard
Supersedes the skill-leak half of #50443 (credit @helix4u for flagging the area).
Adds a new 'Project Context Files' section to the hermes-agent skill
explaining the priority order and discovery rules for .hermes.md,
AGENTS.md, CLAUDE.md, and .cursorrules. Specifically clarifies:
- .hermes.md walks parents up to the git root (good for monorepos)
- AGENTS.md / agents.md is cwd-only (portable to other agents)
- The 20K cap and head+tail truncation strategy
- The threat-pattern scanner behavior (blocks content, not file)
- What --ignore-rules actually skips (everything)
Also fixes an inaccurate docstring in agent/agent_init.py for
skip_context_files — the previous text only mentioned SOUL.md,
AGENTS.md, and .cursorrules, but the actual behavior (per
build_context_files_prompt and the --ignore-rules CLI flag) skips
all of them plus .hermes.md and CLAUDE.md.
Refs: https://github.com/NousResearch/hermes-agent/issues/46775
Closes#48835
The bundled himalaya skill and its website docs documented command
syntax that does not match Himalaya CLI v1.2.0.
Verified against pimalaya/himalaya v1.2.0 source:
- message move: MessageMoveCommand declares target_folder BEFORE
envelopes (src/email/message/command/move.rs) -> usage is
'<TARGET> <ID>...', so 'move 42 "Archive"' is wrong; correct is
'move "Archive" 42'.
- message copy: same ordering in copy.rs.
- attachment download: AttachmentDownloadCommand exposes the flag as
'-d, --downloads-dir <PATH>' (src/email/message/attachment/command/
download.rs), not '--dir'.
Fixed in all three surfaces that carried the wrong examples:
- skills/email/himalaya/SKILL.md
- website/docs/.../email-himalaya.md
- website/i18n/zh-Hans/.../email-himalaya.md
The kanban-worker skill taught kanban_complete with three full examples but
never mentioned the artifacts=[...] parameter added in #27813 — so a worker
reading the skill had no way to learn it can ship a chart/PDF/image as a
native upload to the subscriber's chat.
Adds a 'Shipping deliverables' section covering absolute-path rules, the
inline-vs-file extension behavior, and the trap that the notifier reads the
top-level artifacts list (NOT metadata.*).
Five targeted enhancements to the upstream simplify-code skill:
1. Risk-tiered application (SAFE/CAREFUL/RISKY) — safe changes auto-applied,
careful changes verified per-file, risky changes flagged for human review.
Prevents auto-applying N+1 restructures and public API renames.
2. Chesterton's Fence — before flagging anything for removal, reviewers run
'git blame' to understand why it exists. Low-confidence findings are
escalated rather than guessed.
3. AI slop detection — Quality reviewer now catches: extra comments restating
obvious code, unnecessary defensive null-checks on validated inputs, 'as any'
casts, and patterns inconsistent with the rest of the file.
4. Silent failure detection — Efficiency reviewer now catches: empty catch
blocks, ignored error returns, except:pass, .catch(()=>{}) with no handling,
and error propagation gaps.
5. Structured reviewer output with confidence+risk tags — reviewers report in
'file:line → problem → fix | confidence: H/M/L | risk: SAFE/CAREFUL/RISKY'
format, enabling the orchestrator to tier the application.
Plus 3 new pitfalls: over-trusting dead code tools, public contract awareness,
and preserving intentional error handling.
Total: +45/-8 lines. Keeps the 212-line compact spirit.
Ref: #379
* feat(skills): add html-artifact skill, fold in sketch + architecture-diagram + concept-diagrams
Adds a unified `html-artifact` creative skill that produces self-contained,
single-file HTML artifacts — concept explainers, implementation plans,
status/incident reports, code-review walkthroughs, technical + educational
SVG diagrams, multi-variant design comparisons, and throwaway editors that
export their state back to the clipboard. Grounded in Anthropic's
html-effectiveness gallery (MIT); the house style (token block, serif/sans/
mono split, hand-rolled diffs, inline-SVG diagrams, graceful degradation) is
distilled from reading all 20 reference files.
Supersedes and removes three overlapping skills, folding their unique value in:
- sketch -> the fidelity dial (throwaway vs presentation) + the
multi-variant comparison layouts + the browser-vision
verify loop (references/fidelity-and-verify.md)
- architecture-diagram-> the dark "infra" token variant + double-rect masking +
semantic component palette (references/dark-tech.md,
templates/diagram.html infra mode)
- concept-diagrams -> the 9-ramp educational color system + the concept
archetype library (references/concept-archetypes.md,
the light design system in templates/diagram.html)
Structure:
- SKILL.md (description exactly 60 chars), 6 references, 3 templates
- templates verified by headless-Chrome render + vision inspection
- editor export logic (file://-safe clipboard, Promise-normalized) verified in node
Cross-references updated in claude-design (new disambiguation table row drawing
the design-taste vs information-artifact boundary), design-md, pretext, spike,
and kanban-video-orchestrator. Website skill docs + catalogs regenerated;
stale EN/zh-Hans per-skill pages pruned and i18n cross-refs fixed.
Not folded (intentionally orthogonal): excalidraw (.excalidraw JSON), p5js
(generative canvas), claude-design / popular-web-designs / design-md (visual
design taste / brand vocab / token spec).
* feat(skills): ship html-effectiveness gallery as fetched reference examples
Add scripts/fetch-examples.sh (idempotent clone/pull of Anthropic's MIT
html-effectiveness gallery) + references/examples.md mapping each of the 20
example files to a mode so the agent reads the right worked example. The clone
lands in references/examples/ and is gitignored (it's a 384KB upstream repo,
not vendored). SKILL.md workflow + reference list now point at it; falls back to
the distilled pattern references when offline.
* feat(skills): make reading a gallery example a required authoring step
Reading the matching html-effectiveness example is now workflow step 2 (was an
optional aside in step 3): fetch the gallery, read_file the file for your mode,
mirror its structure. Models skip optional steps; the examples are the ground
truth, so consulting one is mandatory. Added an 'Example' column to the
mode->build quick-reference table and a 'don't skip the example' pitfall.
Also dogfooded the skill: read 03-code-review-pr.html and 13-flowchart-diagram.html
raw and reconciled the distilled references against source — aligned diff-row tint
opacity to the source's 0.15 (was 0.18) and added the .ctx/.hunk rows in
house-style.md + base.html so they match 03-code-review-pr.html verbatim.
* docs(skills): explain the consolidation + bundled-vs-optional rationale
The supersession note only stated *what* was folded, not *why* the prune is
sound. Expand SKILL.md's intro into a 'Why this skill exists' section: the three
former skills emitted the same artifact and overlapped, so consolidating removes
which-one-do-I-load ambiguity; and the optional->bundled promotion of
concept-diagrams is footprint-safe because this skill has zero deps (only cost is
the 60-char description; everything else is progressive-disclosure). States the
bundling dividing line explicitly: zero install cost + broadly useful gets
bundled, real install cost (hyperframes: Node+FFmpeg+Chromium) stays optional.
Regenerated website per-skill page to match.
