feat(plugin): skill-forge-essentials - 3 novel behavioral skills#577
feat(plugin): skill-forge-essentials - 3 novel behavioral skills#577Adit-Jain-srm wants to merge 4 commits into
Conversation
Focused subset per wshobson#570 feedback: only genuinely novel skills, markdown-first, no executable components.
📝 WalkthroughSummary by CodeRabbit
WalkthroughThis PR adds a new ChangesSkill-Forge Essentials Plugin
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 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.
🧹 Nitpick comments (2)
plugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.md (1)
40-40: 💤 Low valueMinor style suggestion: Replace "very" with more specific alternative.
Per LanguageTool, "very" is an over-used intensifier. Consider replacing with a more precise descriptor (e.g., "extremely large," "exceptionally large," or a concrete bound like "multi-GB input").
🤖 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/skill-forge-essentials/skills/ai-debt-detector/SKILL.md` at line 40, Update the phrase "Very large input?" in the question list in SKILL.md to use a more specific descriptor—replace "Very large input?" with a concrete alternative such as "Extremely large input?" or better yet a bounded example like "Multi-GB input?" (or "Exceptionally large input?") so the symptom is clearer; locate the line containing the list item "Empty array/string? null/undefined? Very large input? Unicode? Concurrent calls?" and substitute the improved wording.Source: Linters/SAST tools
plugins/skill-forge-essentials/skills/session-guard/SKILL.md (1)
15-15: 💤 Low valueMinor style suggestion: "without warning" is wordy; consider a shorter alternative.
Per LanguageTool, "without warning" may be simplified (e.g., "silently," "unannounced," or "unexpectedly"). Current phrasing is clear, but a tighter version would improve conciseness.
🤖 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/skill-forge-essentials/skills/session-guard/SKILL.md` at line 15, The phrase "without warning" in the SKILL.md sentence "Context compaction drops instructions without warning." is wordy; replace it with a tighter alternative (e.g., "silently," "unannounced," or "unexpectedly") — e.g., change the sentence to "Context compaction drops instructions silently." to improve conciseness while preserving meaning.Source: Linters/SAST tools
🤖 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.
Nitpick comments:
In `@plugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.md`:
- Line 40: Update the phrase "Very large input?" in the question list in
SKILL.md to use a more specific descriptor—replace "Very large input?" with a
concrete alternative such as "Extremely large input?" or better yet a bounded
example like "Multi-GB input?" (or "Exceptionally large input?") so the symptom
is clearer; locate the line containing the list item "Empty array/string?
null/undefined? Very large input? Unicode? Concurrent calls?" and substitute the
improved wording.
In `@plugins/skill-forge-essentials/skills/session-guard/SKILL.md`:
- Line 15: The phrase "without warning" in the SKILL.md sentence "Context
compaction drops instructions without warning." is wordy; replace it with a
tighter alternative (e.g., "silently," "unannounced," or "unexpectedly") — e.g.,
change the sentence to "Context compaction drops instructions silently." to
improve conciseness while preserving meaning.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 7c5f2704-7e72-4113-9ab1-6a3d7783889c
📒 Files selected for processing (5)
plugins/skill-forge-essentials/.claude-plugin/plugin.jsonplugins/skill-forge-essentials/.codex-plugin/plugin.jsonplugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.mdplugins/skill-forge-essentials/skills/design-mode/SKILL.mdplugins/skill-forge-essentials/skills/session-guard/SKILL.md
📜 Review details
🧰 Additional context used
📓 Path-based instructions (3)
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/skill-forge-essentials/.claude-plugin/plugin.jsonplugins/skill-forge-essentials/skills/design-mode/SKILL.mdplugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.mdplugins/skill-forge-essentials/skills/session-guard/SKILL.md
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/skill-forge-essentials/skills/design-mode/SKILL.mdplugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.mdplugins/skill-forge-essentials/skills/session-guard/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/skill-forge-essentials/skills/design-mode/SKILL.mdplugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.mdplugins/skill-forge-essentials/skills/session-guard/SKILL.md
🪛 LanguageTool
plugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.md
[style] ~40-~40: As an alternative to the over-used intensifier ‘very’, consider replacing this phrase.
Context: ... - Empty array/string? null/undefined? Very large input? Unicode? Concurrent calls? - ...
(EN_WEAK_ADJECTIVE)
plugins/skill-forge-essentials/skills/session-guard/SKILL.md
[style] ~15-~15: ‘without warning’ might be wordy. Consider a shorter alternative.
Context: .... Context compaction drops instructions without warning. Hooks don't fix it (confirmed by multi...
(EN_WORDINESS_PREMIUM_WITHOUT_WARNING)
🪛 SkillSpector (2.1.1)
plugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.md
[warning] 65: [EA2] Autonomous Decision Making: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Remediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
(Excessive Agency (EA2))
🔇 Additional comments (5)
plugins/skill-forge-essentials/.claude-plugin/plugin.json (1)
1-11: LGTM!plugins/skill-forge-essentials/.codex-plugin/plugin.json (1)
1-11: LGTM!plugins/skill-forge-essentials/skills/ai-debt-detector/SKILL.md (1)
53-68: Clarify the SkillSpector EA2 warning: autonomous decision-making without human verification.SkillSpector flagged this skill for enabling autonomous high-impact decisions without explicit user confirmation. However, upon review, this skill is a checklist-based audit skill, not an autonomous executor. It guides human review of AI-generated code; it does not autonomously delete, modify, or execute destructive operations. The red flags section (line 53) explicitly names patterns and calls for stopping—"stop and fix immediately"—which requires human decision.
Request verification: Does SkillSpector's EA2 warning apply to audit/checklist-only skills that guide human verification, or only to skills that execute autonomous operations? If the warning is intended to flag autonomous destructive commands, this skill should not trigger it.
Source: Linters/SAST tools
plugins/skill-forge-essentials/skills/design-mode/SKILL.md (1)
1-104: LGTM!plugins/skill-forge-essentials/skills/session-guard/SKILL.md (1)
1-85: LGTM!
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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:
- Around line 1150-1162: Remove the marketplace registry change that adds the
"skill-forge-essentials" entry in .claude-plugin/marketplace.json: revert or
delete the JSON object that registers the plugin (the block with "name":
"skill-forge-essentials", "source": "./plugins/skill-forge-essentials", etc.) so
the PR only contains the plugin directory and manifests, not edits to
marketplace.json; leave the plugin files intact and ensure no other edits to
.claude-plugin/marketplace.json remain in the diff so registry additions are
made through the separate registry process.
🪄 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: 051af0d6-1c86-41e1-8324-6c5088c5d83c
📒 Files selected for processing (1)
.claude-plugin/marketplace.json
📜 Review details
🧰 Additional context used
📓 Path-based instructions (1)
.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
This reverts commit 528f7f3.
|
Reverted the marketplace.json change - understood, registry is managed separately. Plugin directory only now. |
|
@coderabbitai resolve |
✅ Action performedComments resolved and changes approved. |
1 participant
Adds
skill-forge-essentials- three focused behavioral skills that address gaps not currently covered by the marketplace.What's included
What's NOT included (per #570 feedback)
Structure
plugins/skill-forge-essentials/ +-- .claude-plugin/plugin.json +-- .codex-plugin/plugin.json +-- skills/ +-- ai-debt-detector/SKILL.md +-- session-guard/SKILL.md +-- design-mode/SKILL.mdPortability notes
Resolves #570.