Add Hermes Tweet plugin#582
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (3)
✅ Files skipped from review due to trivial changes (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughSummary by CodeRabbitRelease Notes
WalkthroughAdds a new Changeshermes-tweet Plugin Addition
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
docs/agent-skills.md (1)
390-390:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winUpdate stale skill count on line 390.
The introduction on line 3 correctly states 157 skills, but the specification compliance statement on line 390 refers to 156 skills — a leftover from the previous count. Update line 390 to match the new total.
🔧 Proposed fix
-All 156 skills follow the [Agent Skills Specification](https://agentskills.io/specification): +All 157 skills follow the [Agent Skills Specification](https://agentskills.io/specification):🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/agent-skills.md` at line 390, Update the skill count in the specification compliance statement from 156 to 157 to match the correct total stated in the document introduction. In the sentence starting with "All 156 skills follow the", change the number 156 to 157 to ensure consistency across the documentation.
🧹 Nitpick comments (1)
plugins/hermes-tweet/skills/hermes-tweet/SKILL.md (1)
65-79: ⚡ Quick winRewrite workflow prose to action-verb language in body sections.
The workflow/tool guidance is currently phrased in tool-name vocabulary (
tweet_explore,tweet_read,tweet_action) rather than action-first instructions. Rephrase the body text to action verbs and keep tool identifiers as secondary references/examples.As per coding guidelines, "Use action verbs in markdown body, not tool-name vocabulary: prefer 'open the file' over 'use the Read tool'."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@plugins/hermes-tweet/skills/hermes-tweet/SKILL.md` around lines 65 - 79, The workflow guidance items 1-3 in the SKILL.md file are currently phrased with tool names as the primary subject (starting with "Start with," "Use," "Use"). Rewrite items 1-3 to lead with action verbs instead, placing the tool identifiers (tweet_explore, tweet_read, tweet_action) as secondary references. For example, rephrase "Start with `tweet_explore` to find matching catalog routes" to "Search the bundled endpoint catalog with `tweet_explore` to find matching routes," and similarly rephrase items 2 and 3 to emphasize the action being performed (reading data, executing actions) with the tool name as supporting context rather than the directive itself. Items 4-6 already follow the action-verb pattern and do not require changes.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.claude-plugin/marketplace.json:
- Line 9: Remove all modifications to .claude-plugin/marketplace.json from this
PR, as registry edits must not be included in plugin PRs according to coding
guidelines. This includes the description change at line 9 and any other
registry modifications affecting lines 715-727. These registry updates should be
submitted separately through the appropriate registry update flow instead of
being included in plugin PRs.
In @.cursor-plugin/marketplace.json:
- Line 9: The marketplace.json file should not be hand-edited and instead must
be regenerated through the build system. Revert any manual changes made to the
description field and other affected areas in marketplace.json, then regenerate
the entire file by running the appropriate make generate command with the
correct HARNESS parameter as specified in the coding guidelines for
.cursor-plugin/ directory files.
In @.cursor-plugin/plugin.json:
- Line 5: The description field in the plugin.json manifest has been manually
edited, which violates the guideline that files under `.cursor-plugin/` should
only be generated through the automated flow. Revert the manual changes to the
description field in plugin.json and instead regenerate the entire manifest file
by running the appropriate make generate command with the correct HARNESS
parameter. Do not commit manual edits to this file; let the generation process
handle all manifest updates.
In @.cursor-plugin/plugins/hermes-tweet.json:
- Around line 1-12: The hermes-tweet.json file under .cursor-plugin/plugins/ is
being directly edited in this PR, but files under .cursor-plugin/ are
auto-generated artifacts and should not be manually modified. Revert all direct
edits to this file and instead regenerate it using the proper harness target by
running make generate HARNESS=<x> as appropriate for this plugin. Ensure the
file is not included as a direct edit in the PR.
---
Outside diff comments:
In `@docs/agent-skills.md`:
- Line 390: Update the skill count in the specification compliance statement
from 156 to 157 to match the correct total stated in the document introduction.
In the sentence starting with "All 156 skills follow the", change the number 156
to 157 to ensure consistency across the documentation.
---
Nitpick comments:
In `@plugins/hermes-tweet/skills/hermes-tweet/SKILL.md`:
- Around line 65-79: The workflow guidance items 1-3 in the SKILL.md file are
currently phrased with tool names as the primary subject (starting with "Start
with," "Use," "Use"). Rewrite items 1-3 to lead with action verbs instead,
placing the tool identifiers (tweet_explore, tweet_read, tweet_action) as
secondary references. For example, rephrase "Start with `tweet_explore` to find
matching catalog routes" to "Search the bundled endpoint catalog with
`tweet_explore` to find matching routes," and similarly rephrase items 2 and 3
to emphasize the action being performed (reading data, executing actions) with
the tool name as supporting context rather than the directive itself. Items 4-6
already follow the action-verb pattern and do not require changes.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 0502a040-724e-4e7b-83e3-801d4255220d
📒 Files selected for processing (12)
.agents/plugins/marketplace.json.claude-plugin/marketplace.json.cursor-plugin/marketplace.json.cursor-plugin/plugin.json.cursor-plugin/plugins/hermes-tweet.jsonREADME.mddocs/agent-skills.mddocs/plugins.mdplugins/hermes-tweet/.claude-plugin/plugin.jsonplugins/hermes-tweet/.codex-plugin/plugin.jsonplugins/hermes-tweet/skills/hermes-tweet/SKILL.mdplugins/hermes-tweet/skills/hermes-tweet/references/workflows.md
📜 Review details
🧰 Additional context used
📓 Path-based instructions (6)
**/.cursor-plugin/**
📄 CodeRabbit inference engine (.cursor/rules/000-project-conventions.mdc)
Do not hand-edit anything under
.cursor-plugin/— regenerate viamake generate HARNESS=<x>
Files:
.cursor-plugin/plugin.json.cursor-plugin/plugins/hermes-tweet.json.cursor-plugin/marketplace.json
plugins/**/{.claude-plugin/plugin.json,agents/*.md,skills/*/SKILL.md,commands/*.md}
📄 CodeRabbit inference engine (.cursor/rules/000-project-conventions.mdc)
Plugin files follow the structure:
plugins/<name>/{.claude-plugin/plugin.json, agents/*.md, skills/<name>/SKILL.md, commands/*.md}and are auto-discovered
Files:
plugins/hermes-tweet/skills/hermes-tweet/SKILL.mdplugins/hermes-tweet/.claude-plugin/plugin.json
plugins/*/skills/*/SKILL.md
📄 CodeRabbit inference engine (.cursor/rules/020-agent-skill-authoring.mdc)
plugins/*/skills/*/SKILL.md: Skills frontmatter must include:name,description. Other Anthropic SKILL.md fields are optional and respected only on Claude Code
Cap skill body at approximately 8 KB. Push longer reference material intoskills/<name>/references/files, as Codex will hard-truncate at 8 KBPlugin frontmatter shapes must follow authoring standards defined in 'docs/authoring.md'
Files:
plugins/hermes-tweet/skills/hermes-tweet/SKILL.md
{plugins/*/agents/*.md,plugins/*/skills/*/SKILL.md,plugins/*/commands/*.md}
📄 CodeRabbit inference engine (.cursor/rules/020-agent-skill-authoring.mdc)
{plugins/*/agents/*.md,plugins/*/skills/*/SKILL.md,plugins/*/commands/*.md}: Use action verbs in markdown body, not tool-name vocabulary: prefer "open the file" over "use the Read tool". The adapter rewrites a conservative set, but unrewritten cases may bleed through
Do not referenceTodoWrite, theTaskspawn tool, or hooks as load-bearing — they don't exist in Codex or Cursor
Files:
plugins/hermes-tweet/skills/hermes-tweet/SKILL.md
{README.md,ARCHITECTURE.md}
📄 CodeRabbit inference engine (AGENTS.md)
Keep README/overview files short (~150 lines max) per OpenAI's harness-engineering practice; push procedural detail to docs/ and skill files
Files:
README.md
.claude-plugin/marketplace.json
📄 CodeRabbit inference engine (.cursor/rules/000-project-conventions.mdc)
Never modify
.claude-plugin/marketplace.jsonfrom inside a plugin PR — it's the registry
Files:
.claude-plugin/marketplace.json
🔇 Additional comments (3)
plugins/hermes-tweet/.claude-plugin/plugin.json (1)
1-12: LGTM!plugins/hermes-tweet/.codex-plugin/plugin.json (1)
1-18: LGTM!.agents/plugins/marketplace.json (1)
568-579: LGTM!
|
Update pushed in 74898a6. Validated:
The docs count and action-verb comments are fixed. The |
|
Addressed the registry/generated-file review items in 3d97775 by removing the .claude-plugin marketplace edit and .cursor-plugin generated-file changes from the PR. Validation run: jq on plugin manifests, claude plugin validate plugins/hermes-tweet, git diff --check. CodeRabbit is now passing. |
1 participant
Summary
Adds a source-native
hermes-tweetplugin for Hermes Agent X/Twitter research, read routes, and approval-gated action workflows.This is distinct from the existing
social-publishingplugin:social-publishingcovers broad multi-platform publishing, while Hermes Tweet focuses on the Hermes Agent runtime,tweet_explore,tweet_read, and guardedtweet_actionworkflows.Changes
plugins/hermes-tweetwith Claude and Codex plugin manifests.hermes-tweetskill plus workflow reference material.Validation
claude plugin validate plugins/hermes-tweetmake generate-allmake validatemake gardenreports 0 errors and 10 pre-existingSKILL_OVER_CODEX_CAPwarnings outside this pluginuv run --project plugins/plugin-eval plugin-eval score plugins/hermes-tweet/skills/hermes-tweet --depth quickgives 83.8/100 Gold with 0 anti-patternsTERM=xterm-256color make testgives 443 passed, 3 skipped