Conversation
Includes: - v1.24.0 across all publishable packages - Add packages/mcp + packages/api to bump-version.sh (were drifting) - Regenerate assets/tags/v1.24.0.svg, remove stale v1.23.0.svg - Bump agent count references from 45 to 46 (adds Hermes) - Update gen-tags.mjs (version + agent count) - Sync onboarding logo test expectation Release covers #114 (Hermes native support) + #117 (OpenClaw upstream paths).
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
📝 WalkthroughWalkthroughThis PR increments the monorepo version to 1.24.0, updates package manifests and generated tags, and changes documentation, metadata, and tests to reflect support for 46 agents (adding "Hermes") across docs, UI components, CLI help, and E2E/unit tests. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
|
|
||
| const COMPARISONS = [ | ||
| ['Agent Support', '1-17 agents', '45 agents'], | ||
| ['Agent Support', '1-17 agents', '46 agents'], |
There was a problem hiding this comment.
🟡 Incomplete 45→46 update: three remaining '45' references in docs/skillkit/components/Features.tsx
The PR updated some '45' references to '46' in docs/skillkit/components/Features.tsx (lines 39, 112) but missed three others in the same file: line 21 says auto-translate to 45 formats, line 114 says All 45 formats, and line 134 displays 45 as the stat counter. These are inconsistent with the rest of the PR's 45→46 update.
Prompt for agents
In docs/skillkit/components/Features.tsx, several '45' references were missed by the 45→46 update: line 21 says 'auto-translate to 45 formats' (should be 46), line 114 says 'All 45 formats' (should be 46), and line 134 displays the number '45' in the stats hero section (should be 46). Update all three to be consistent with the rest of the PR.
Was this helpful? React with 👍 or 👎 to provide feedback.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (3)
packages/core/src/translator/__tests__/registry.test.ts (1)
332-363:⚠️ Potential issue | 🟠 Major“all 46 agents” assertion is inaccurate and under-tests coverage.
The test title claims 46, but
allAgentsonly lists 29 agents, so this can pass while many agent mappings regress unnoticed. Please derive this list from the canonical agent source (or include all current agents explicitly).Proposed fix (derive from canonical agent enum)
- it('should support all 46 agents', () => { - const allAgents = [ - 'claude-code', - 'cursor', - 'codex', - 'gemini-cli', - 'opencode', - 'antigravity', - 'amp', - 'clawdbot', - 'droid', - 'github-copilot', - 'goose', - 'kilo', - 'kiro-cli', - 'roo', - 'trae', - 'windsurf', - 'universal', - 'devin', - 'aider', - 'sourcegraph-cody', - 'amazon-q', - 'augment-code', - 'replit-agent', - 'bolt', - 'lovable', - 'tabby', - 'tabnine', - 'codegpt', - 'playcode-agent', - ] as const; + it('should support all registered agents', () => { + const allAgents = AgentType.options;🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@packages/core/src/translator/__tests__/registry.test.ts` around lines 332 - 363, The test's hardcoded allAgents array is incomplete; replace it by importing the canonical agent enum/list used by the system (the source that defines the full set of agents) and derive the test list from that enum instead of manually listing values. In the test file where allAgents is defined (the variable named allAgents in registry.test.ts inside the 'should support all 46 agents' case), import the authoritative agent list/enum (the module that exports the runtime agent identifiers) and use its values to build the array, then assert against that derived list (and/or assert the expected length) so the test always covers every current agent mapping.e2e/onboarding-ui.e2e.test.ts (1)
47-96:⚠️ Potential issue | 🟠 MajorMake the onboarding E2E actually assert all 46 agents.
The expected list has 44 entries, so this test would still pass while missing newly supported agents. Add the missing entries and assert the expected list length.
Proposed test hardening
const agents = [ 'Claude Code', 'Cursor', @@ 'CodeGPT', 'PlayCode', + 'Hermes', + 'OpenClaw', ]; + + expect(agents).toHaveLength(46); for (const agent of agents) { expect(output.toLowerCase()).toContain(agent.toLowerCase()); }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@e2e/onboarding-ui.e2e.test.ts` around lines 47 - 96, The test "should display all 46 agents" currently defines the agents array with only 44 entries; update the agents array in the it block (the variable named agents) to include the two missing agent names so it truly contains 46 expected names, then add an explicit assertion that agents.length === 46 and assert the CLI output matches the full agents list (use the same runCli(['init', '--list']) result and compare parsed output to the agents array) to harden the e2e test.docs/fumadocs/src/components/Features.tsx (1)
86-87:⚠️ Potential issue | 🟡 MinorInconsistent agent count in the visual metric display.
The hardcoded "45" in the metric display was not updated to "46", creating an inconsistency with the updated comparison table (line 67) and feature description (line 12) on the same page.
🔢 Proposed fix to update the metric display
- <div className="text-2xl sm:text-3xl font-bold text-white font-mono">45</div> + <div className="text-2xl sm:text-3xl font-bold text-white font-mono">46</div>🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/fumadocs/src/components/Features.tsx` around lines 86 - 87, Update the hardcoded metric text "45" inside the Features component so the visual metric display matches the rest of the page; locate the element with className "text-2xl sm:text-3xl font-bold text-white font-mono" in Features.tsx and replace the inner text "45" with "46" (ensure no other occurrences remain inconsistent).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/skillkit/components/Agents.tsx`:
- Line 432: The heading "Works with 46 AI Agents" is hard-coded while the AGENTS
array contains 44 items; update the Agents component to avoid this drift by
either adding the missing Hermes/OpenClaw entries to the AGENTS array (so it
truly has 46 items) or, better, derive the label dynamically from AGENTS.length
(e.g., use `${AGENTS.length}` in the heading). Locate the AGENTS array and the
heading text in Agents.tsx and change the static "46" to a computed value based
on AGENTS.length, or add the two missing agent objects (Hermes/OpenClaw) into
AGENTS if the list should be exhaustive.
In `@docs/skillkit/components/CompatibilityMatrix.tsx`:
- Line 249: The displayed “46 agents” is hardcoded and out of sync; update the
CompatibilityMatrix component to compute the agent count from the AGENTS array
(use AGENTS.length) instead of the literal 46, or alternatively add the missing
Hermes/OpenClaw entries and corresponding MATRIX coverage to bring AGENTS and
MATRIX up to 46; locate the label string in CompatibilityMatrix.tsx and replace
the hardcoded number with a derived value using the AGENTS symbol so the UI
remains correct as AGENTS changes.
In `@docs/skillkit/components/Features.tsx`:
- Line 112: Update the inconsistent agent-count text in the Features component:
find the feature entry containing the tuple that starts with 'Agent Support'
(the array item ['Agent Support', '1-17 agents', '46 agents']) and change the
third element from '46 agents' to '45 agents' so it matches the "At a Glance"
metric elsewhere in the component.
In `@packages/agents/README.md`:
- Line 14: Update the README's supported agents list to match the claimed count:
add "Hermes Agent" entry into the agents table and ensure the header count
"Supported Agents (46)" reflects the actual number of rows after insertion (or
adjust the number if you prefer to recalc); locate the header text "Supported
Agents (46)" and the agents table block in packages/agents/README.md and insert
the Hermes Agent row with the same format as other agents so the count and table
stay consistent.
In `@packages/cli/README.md`:
- Line 6: The README top-line agent count ("46 AI coding agents") is
inconsistent with the supported-agents table (6 named agents + " + 39 more" =
45); update the README so the totals match by either changing the header count
to 45 or adjusting the table's "+ 39 more" to "+ 40 more" (also update the
duplicate occurrence around the other mention at the later section referenced),
ensuring both the header and the supported-agents table use the same total.
In `@packages/core/README.md`:
- Line 17: The README has inconsistent agent counts: update the two inconsistent
occurrences— the "Cross-Agent Translation" bullet mentioning "46 agent formats"
and the later sentence that says "32 supported agents"—to the same correct
number; search the README for the phrases "Cross-Agent Translation" and
"supported agents" (or the exact numeric strings "46" and "32") and replace them
with the agreed-upon canonical count so all references in
packages/core/README.md match.
---
Outside diff comments:
In `@docs/fumadocs/src/components/Features.tsx`:
- Around line 86-87: Update the hardcoded metric text "45" inside the Features
component so the visual metric display matches the rest of the page; locate the
element with className "text-2xl sm:text-3xl font-bold text-white font-mono" in
Features.tsx and replace the inner text "45" with "46" (ensure no other
occurrences remain inconsistent).
In `@e2e/onboarding-ui.e2e.test.ts`:
- Around line 47-96: The test "should display all 46 agents" currently defines
the agents array with only 44 entries; update the agents array in the it block
(the variable named agents) to include the two missing agent names so it truly
contains 46 expected names, then add an explicit assertion that agents.length
=== 46 and assert the CLI output matches the full agents list (use the same
runCli(['init', '--list']) result and compare parsed output to the agents array)
to harden the e2e test.
In `@packages/core/src/translator/__tests__/registry.test.ts`:
- Around line 332-363: The test's hardcoded allAgents array is incomplete;
replace it by importing the canonical agent enum/list used by the system (the
source that defines the full set of agents) and derive the test list from that
enum instead of manually listing values. In the test file where allAgents is
defined (the variable named allAgents in registry.test.ts inside the 'should
support all 46 agents' case), import the authoritative agent list/enum (the
module that exports the runtime agent identifiers) and use its values to build
the array, then assert against that derived list (and/or assert the expected
length) so the test always covers every current agent mapping.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 6256624e-f860-4dad-a587-071f13e89180
⛔ Files ignored due to path filters (2)
assets/tags/agents.svgis excluded by!**/*.svgassets/tags/v1.24.0.svgis excluded by!**/*.svg
📒 Files selected for processing (45)
README.mdapps/skillkit/README.mdapps/skillkit/package.jsondocs/fumadocs/package.jsondocs/fumadocs/src/components/Documentation.tsxdocs/fumadocs/src/components/Features.tsxdocs/skillkit/components/AdvancedFeatures.tsxdocs/skillkit/components/Agents.tsxdocs/skillkit/components/CompatibilityMatrix.tsxdocs/skillkit/components/Documentation.tsxdocs/skillkit/components/Features.tsxdocs/skillkit/components/Hero.tsxdocs/skillkit/components/UseCases.tsxdocs/skillkit/components/WhySkillKit.tsxdocs/skillkit/index.htmldocs/skillkit/metadata.jsondocs/skillkit/package.jsondocs/skillkit/public/openapi.jsone2e/onboarding-ui.e2e.test.tspackage.jsonpackages/agents/README.mdpackages/agents/package.jsonpackages/api/package.jsonpackages/api/src/routes/docs.tspackages/cli/README.mdpackages/cli/package.jsonpackages/cli/src/__tests__/onboarding.test.tspackages/cli/src/commands/primer.tspackages/core/README.mdpackages/core/package.jsonpackages/core/src/orchestrator/index.tspackages/core/src/translator/__tests__/registry.test.tspackages/extension/README.mdpackages/extension/src/manifest.jsonpackages/extension/store-assets/STORE_LISTING.mdpackages/mcp-memory/package.jsonpackages/mcp/package.jsonpackages/memory/package.jsonpackages/mesh/package.jsonpackages/messaging/package.jsonpackages/resources/package.jsonpackages/tui/README.mdpackages/tui/package.jsonscripts/bump-version.shscripts/gen-tags.mjs
| <div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8"> | ||
| <p className="text-zinc-500 font-mono text-[11px] uppercase tracking-widest mb-6 text-center"> | ||
| Works with 45 AI Agents | ||
| Works with 46 AI Agents |
There was a problem hiding this comment.
Avoid claiming 46 while rendering 44 agents.
The AGENTS array has 44 entries, so this heading can drift from the actual rendered set. Add the missing Hermes/OpenClaw entries if this carousel is exhaustive, or derive the label from AGENTS.length.
Suggested drift-proof label
- Works with 46 AI Agents
+ Works with {AGENTS.length} AI Agents📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| Works with 46 AI Agents | |
| Works with {AGENTS.length} AI Agents |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/skillkit/components/Agents.tsx` at line 432, The heading "Works with 46
AI Agents" is hard-coded while the AGENTS array contains 44 items; update the
Agents component to avoid this drift by either adding the missing
Hermes/OpenClaw entries to the AGENTS array (so it truly has 46 items) or,
better, derive the label dynamically from AGENTS.length (e.g., use
`${AGENTS.length}` in the heading). Locate the AGENTS array and the heading text
in Agents.tsx and change the static "46" to a computed value based on
AGENTS.length, or add the two missing agent objects (Hermes/OpenClaw) into
AGENTS if the list should be exhaustive.
| <h2 className="text-lg sm:text-xl font-bold text-white mb-1 font-mono">Compatibility Matrix</h2> | ||
| <p className="text-zinc-500 font-mono text-[10px] sm:text-xs"> | ||
| Skill support across all 45 agents and {CATEGORIES.length} categories. | ||
| Skill support across all 46 agents and {CATEGORIES.length} categories. |
There was a problem hiding this comment.
Keep the displayed count in sync with the matrix data.
Line 249 now claims “46 agents”, but AGENTS currently contains 44 entries and does not include Hermes/OpenClaw. Either add the missing agent definitions and MATRIX coverage, or derive this label from AGENTS.length until the table is complete.
Suggested guard against future drift
- Skill support across all 46 agents and {CATEGORIES.length} categories.
+ Skill support across all {AGENTS.length} agents and {CATEGORIES.length} categories.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| Skill support across all 46 agents and {CATEGORIES.length} categories. | |
| Skill support across all {AGENTS.length} agents and {CATEGORIES.length} categories. |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/skillkit/components/CompatibilityMatrix.tsx` at line 249, The displayed
“46 agents” is hardcoded and out of sync; update the CompatibilityMatrix
component to compute the agent count from the AGENTS array (use AGENTS.length)
instead of the literal 46, or alternatively add the missing Hermes/OpenClaw
entries and corresponding MATRIX coverage to bring AGENTS and MATRIX up to 46;
locate the label string in CompatibilityMatrix.tsx and replace the hardcoded
number with a derived value using the AGENTS symbol so the UI remains correct as
AGENTS changes.
|
|
||
| const COMPARISONS = [ | ||
| ['Agent Support', '1-17 agents', '45 agents'], | ||
| ['Agent Support', '1-17 agents', '46 agents'], |
There was a problem hiding this comment.
Agent-count copy is still inconsistent within this component.
Line 112 says 46 agents, but the “At a Glance” metric still shows 45 (Line 134). Please update that stat to avoid conflicting UI numbers.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/skillkit/components/Features.tsx` at line 112, Update the inconsistent
agent-count text in the Features component: find the feature entry containing
the tuple that starts with 'Agent Support' (the array item ['Agent Support',
'1-17 agents', '46 agents']) and change the third element from '46 agents' to
'45 agents' so it matches the "At a Glance" metric elsewhere in the component.
| ``` | ||
|
|
||
| ## Supported Agents (45) | ||
| ## Supported Agents (46) |
There was a problem hiding this comment.
Supported-agents count and table content are out of sync.
Line 14 says 46 supported agents, but the table does not list Hermes Agent. Please add Hermes Agent to keep this README internally consistent with the release claim.
🛠️ Suggested doc fix
| OpenClaw | SKILL.md | `.openclaw/skills/` | `~/.openclaw/workspace/skills/` |
+| Hermes Agent | SKILL.md | `.hermes/skills/` | - |
| Cline | SKILL.md | `.cline/skills/` | - |🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/agents/README.md` at line 14, Update the README's supported agents
list to match the claimed count: add "Hermes Agent" entry into the agents table
and ensure the header count "Supported Agents (46)" reflects the actual number
of rows after insertion (or adjust the number if you prefer to recalc); locate
the header text "Supported Agents (46)" and the agents table block in
packages/agents/README.md and insert the Hermes Agent row with the same format
as other agents so the count and table stay consistent.
| [](https://opensource.org/licenses/Apache-2.0) | ||
|
|
||
| **Command-line interface for SkillKit** - install, manage, translate, and sync skills across 45 AI coding agents. | ||
| **Command-line interface for SkillKit** - install, manage, translate, and sync skills across 46 AI coding agents. |
There was a problem hiding this comment.
Update the supported-agents table to match the new total.
Line 6 says 46 agents, but the table still shows 6 named agents plus “+ 39 more” — 45 total.
Proposed README fix
-| + 39 more | SKILL.md |
+| + 40 more | SKILL.md |Also applies to: 267-267
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/cli/README.md` at line 6, The README top-line agent count ("46 AI
coding agents") is inconsistent with the supported-agents table (6 named agents
+ " + 39 more" = 45); update the README so the totals match by either changing
the header count to 45 or adjusting the table's "+ 39 more" to "+ 40 more" (also
update the duplicate occurrence around the other mention at the later section
referenced), ensuring both the header and the supported-agents table use the
same total.
|
|
||
| - **Skill Discovery**: Find and parse SKILL.md files from any source | ||
| - **Cross-Agent Translation**: Convert skills between 45 agent formats (Claude Code, Cursor, Windsurf, etc.) | ||
| - **Cross-Agent Translation**: Convert skills between 46 agent formats (Claude Code, Cursor, Windsurf, etc.) |
There was a problem hiding this comment.
Agent-count docs are now internally inconsistent.
Line 17 says 46 formats, but Line 281 still says 32 supported agents in the same README. Please align these values to avoid contradictory docs.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/core/README.md` at line 17, The README has inconsistent agent
counts: update the two inconsistent occurrences— the "Cross-Agent Translation"
bullet mentioning "46 agent formats" and the later sentence that says "32
supported agents"—to the same correct number; search the README for the phrases
"Cross-Agent Translation" and "supported agents" (or the exact numeric strings
"46" and "32") and replace them with the agreed-upon canonical count so all
references in packages/core/README.md match.
Test arrays were renamed to '46 agents' but still listed 45: - packages/core/src/translator/__tests__/registry.test.ts: add 'hermes' - e2e/onboarding-ui.e2e.test.ts: add 'Hermes' - e2e/skill-translator.e2e.test.ts: add 'hermes' + update comment - e2e/translation.e2e.test.ts: add 'hermes' + update comment docs/fumadocs Features.tsx: stat counter 45 -> 46 (line 86) Banner refresh (docs/img/banner.svg): - Title: 'One Skill. 44 Agents.' -> 'One skill. 46 agents.' with blue gradient accent on '46' - Subtitle: sharper one-liner on scope - Version badge under SKILLKIT lockup - Install command: npm i -g skillkit (canonical path) - Chip row: colored dots per status (skills/rewrites/license) - Agent list: +Hermes +OpenCode, count math now correct (10+36=46) - Palette: Zinc/Tailwind neutrals for cleaner dark mode
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
e2e/translation.e2e.test.ts (1)
5-5:⚠️ Potential issue | 🟡 MinorUpdate the stale supported-agent count in the file header.
Line 5 still says this validates 45 agents, while Line 19 and the fixture now reflect 46.
📝 Proposed fix
- * Validates translation to all 45 supported agents + * Validates translation to all 46 supported agentsAlso applies to: 19-19
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@e2e/translation.e2e.test.ts` at line 5, Update the stale header comment that says "Validates translation to all 45 supported agents" to the correct count "46" in the e2e/translation.e2e.test.ts header and any other inline comment (the one referenced near line 19) so the comment matches the fixture and test assertions that expect 46 agents.
🧹 Nitpick comments (1)
e2e/skill-translator.e2e.test.ts (1)
77-77: Add Hermes-specific path/config assertions to lock the new contract.The generic loop only proves Hermes returns non-empty values. Since this release promises
.hermes/skills,AGENTS.md, and XML-style config behavior, add explicit assertions so a wrong fallback mapping does not pass.🧪 Proposed test additions
it('should return correct paths for major agents', () => { expect(getAgentSkillsDir('claude-code')).toBe('.claude/skills'); expect(getAgentSkillsDir('cursor')).toBe('.cursor/skills'); expect(getAgentSkillsDir('windsurf')).toBe('.windsurf/skills'); expect(getAgentSkillsDir('github-copilot')).toBe('.github/skills'); expect(getAgentSkillsDir('codex')).toBe('.codex/skills'); + expect(getAgentSkillsDir('hermes')).toBe('.hermes/skills'); }); @@ it('should return correct config files for major agents', () => { expect(getAgentConfigFile('claude-code')).toBe('CLAUDE.md'); expect(getAgentConfigFile('cursor')).toBe('.cursor/rules/skills.mdc'); expect(getAgentConfigFile('windsurf')).toBe('.windsurf/rules/skills.md'); expect(getAgentConfigFile('github-copilot')).toBe('.github/copilot-instructions.md'); + expect(getAgentConfigFile('hermes')).toBe('AGENTS.md'); }); @@ expect(AGENT_SKILL_FORMATS['github-copilot'].configFormat).toBe('markdown'); expect(AGENT_SKILL_FORMATS.trae.configFormat).toBe('markdown'); expect(AGENT_SKILL_FORMATS.roo.configFormat).toBe('xml'); + expect(AGENT_SKILL_FORMATS.hermes.configFormat).toBe('xml'); });🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@e2e/skill-translator.e2e.test.ts` at line 77, The test currently only checks non-empty values for all agents (including the 'hermes' entry); update the e2e/skill-translator.e2e.test.ts test loop to add Hermes-specific assertions: when the agent identifier equals 'hermes' (the array element 'hermes'), assert that returned skill paths include a path segment '.hermes/skills' (or exact '.hermes/skills' entry), assert that an AGENTS.md file is present in the result set, and assert the config content follows XML-style shape (e.g., contains XML tags like '<skill' or starts with '<' and ends with '>') rather than just non-empty; implement these checks inside the existing test case (the loop that enumerates agents) so Hermes fails if a wrong fallback mapping is returned.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@e2e/translation.e2e.test.ts`:
- Line 5: Update the stale header comment that says "Validates translation to
all 45 supported agents" to the correct count "46" in the
e2e/translation.e2e.test.ts header and any other inline comment (the one
referenced near line 19) so the comment matches the fixture and test assertions
that expect 46 agents.
---
Nitpick comments:
In `@e2e/skill-translator.e2e.test.ts`:
- Line 77: The test currently only checks non-empty values for all agents
(including the 'hermes' entry); update the e2e/skill-translator.e2e.test.ts test
loop to add Hermes-specific assertions: when the agent identifier equals
'hermes' (the array element 'hermes'), assert that returned skill paths include
a path segment '.hermes/skills' (or exact '.hermes/skills' entry), assert that
an AGENTS.md file is present in the result set, and assert the config content
follows XML-style shape (e.g., contains XML tags like '<skill' or starts with
'<' and ends with '>') rather than just non-empty; implement these checks inside
the existing test case (the loop that enumerates agents) so Hermes fails if a
wrong fallback mapping is returned.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 6be58874-a67e-4ef7-9f80-ff5a4a8d62f8
⛔ Files ignored due to path filters (1)
docs/img/banner.svgis excluded by!**/*.svg
📒 Files selected for processing (5)
docs/fumadocs/src/components/Features.tsxe2e/onboarding-ui.e2e.test.tse2e/skill-translator.e2e.test.tse2e/translation.e2e.test.tspackages/core/src/translator/__tests__/registry.test.ts
✅ Files skipped from review due to trivial changes (2)
- e2e/onboarding-ui.e2e.test.ts
- docs/fumadocs/src/components/Features.tsx
🚧 Files skipped from review as they are similar to previous changes (1)
- packages/core/src/translator/tests/registry.test.ts
| <div className="mx-auto max-w-5xl px-4 sm:px-6 lg:px-8"> | ||
| <p className="text-zinc-500 font-mono text-[11px] uppercase tracking-widest mb-6 text-center"> | ||
| Works with 45 AI Agents | ||
| Works with 46 AI Agents |
There was a problem hiding this comment.
🟡 Agents carousel claims 46 agents but AGENTS array doesn't include Hermes
The heading at docs/skillkit/components/Agents.tsx:432 was updated to say "Works with 46 AI Agents", but the AGENTS array (defined starting at line 6) that powers the scrolling agent carousel was not updated to include a Hermes entry. The carousel will display only 45 agents while claiming 46.
Prompt for agents
In docs/skillkit/components/Agents.tsx, the AGENTS array (starting around line 6) needs a new entry for Hermes Agent to match the '46 AI Agents' claim at line 432. Add an object like { name: 'Hermes', url: 'https://...', icon: (...svg...) } to the AGENTS array, following the same pattern as other entries.
Was this helpful? React with 👍 or 👎 to provide feedback.
| <h2 className="text-lg sm:text-xl font-bold text-white mb-1 font-mono">Compatibility Matrix</h2> | ||
| <p className="text-zinc-500 font-mono text-[10px] sm:text-xs"> | ||
| Skill support across all 45 agents and {CATEGORIES.length} categories. | ||
| Skill support across all 46 agents and {CATEGORIES.length} categories. |
There was a problem hiding this comment.
🟡 CompatibilityMatrix claims 46 agents but matrix data doesn't include Hermes
The text at docs/skillkit/components/CompatibilityMatrix.tsx:249 was updated to say "46 agents" but the AGENTS array and MATRIX data used to render the compatibility table were not updated to include Hermes. The table will show only the original agents while the header claims 46.
Prompt for agents
In docs/skillkit/components/CompatibilityMatrix.tsx, the AGENTS array and MATRIX data need Hermes entries added to match the '46 agents' claim at line 249. Add a Hermes entry to the AGENTS array (with id, name, icon, and group), and add 'hermes' support levels to each category in the MATRIX object.
Was this helpful? React with 👍 or 👎 to provide feedback.
| <div className="space-y-4"> | ||
| <p className="text-zinc-300"> | ||
| SkillKit supports 45 AI coding agents with automatic format translation: | ||
| SkillKit supports 46 AI coding agents with automatic format translation: |
There was a problem hiding this comment.
🟡 skillkit docs Documentation.tsx claims 46 agents but agent table doesn't list Hermes
At docs/skillkit/components/Documentation.tsx:160, the text was updated to "SkillKit supports 46 AI coding agents" but the <Table> component rendered just below (lines 163-198) lists only the original agents without a Hermes row. The table shows 31 rows while the text claims 46 agents, and Hermes is not among the listed entries.
Prompt for agents
In docs/skillkit/components/Documentation.tsx, the agent table starting at line 165 needs a row for Hermes Agent added, e.g. ['Hermes Agent', '.hermes/skills/', 'SKILL.md']. This applies to the 'agents' section's Table component rows array.
Was this helpful? React with 👍 or 👎 to provide feedback.
| <div className="space-y-4"> | ||
| <p className="text-zinc-300"> | ||
| SkillKit supports 45 AI coding agents with automatic format translation: | ||
| SkillKit supports 46 AI coding agents with automatic format translation: |
There was a problem hiding this comment.
🟡 fumadocs Documentation.tsx claims 46 agents but agent table doesn't list Hermes
At docs/fumadocs/src/components/Documentation.tsx:161, the text was updated to "SkillKit supports 46 AI coding agents" but the <Table> rows below (lines 166-211) don't include a Hermes entry. Same issue as the skillkit docs — the agent count was bumped but the backing data wasn't updated.
Prompt for agents
In docs/fumadocs/src/components/Documentation.tsx, the agent table (rows array starting at line 166) needs a Hermes Agent row added, e.g. ['Hermes Agent', '.hermes/skills/', 'SKILL.md']. This should be inserted in alphabetical order among the agent entries.
Was this helpful? React with 👍 or 👎 to provide feedback.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Highlights
.hermes/skills/discovery, AGENTS.md config, translate/sync/commands/primer all wired. (feat: add Hermes agent adapter (Native Hermes Support) #114, RUFFY-369)skillsDir→.openclaw/skills,configFile→AGENTS.md,globalSkillsDir→~/.openclaw/workspace/skills. AddsaltConfigFilesschema so detection picks upopenclaw.json. (fix(openclaw): align paths with upstream openclaw/openclaw conventions #117)Internals
getSearchDirs()now prefersglobalSkillsDirfor home path instead of deriving fromskillsDirSKILL_DISCOVERY_PATHSincludes.hermes/skillsand.openclaw/skillsAGENT_DIR_MAPwired for both agents including.openclaw/workspace/skillsbump-version.shnow includespackages/mcp+packages/api(were drifting)Validation
@skillkit/core: 1035/1035 tests@skillkit/agents: 192/192 tests@skillkit/cli: 41/41 testsUpgrade
Summary by CodeRabbit
New Features
Chores
Tests