feat: add applying-coding-baseline skill (6 curated rules) - #22
Conversation
…ine rules A new skill that applies a pre-vetted set of baseline behavioral discipline rules to coding agent directive files (CLAUDE.md, AGENTS.md, referenced documents). Replaces semantically similar existing content with canonical wording so coverage stays complete and consistent across projects. The 6 curated rules: 1. Think Before Coding 2. Simplicity First (incl. no over-defending and no defensive logging) 3. Surgical Changes 4. Goal-Driven Execution 5. Fail Fast vs Graceful Handling 6. Documentation Priority The skill skips guarding-agent-directives verification because the rule set is pre-vetted by construction. New rules can be added by appending a section to reference/baseline-rules.md — no other code changes required.
|
Warning Rate limit exceeded
To continue reviewing without waiting, purchase usage credits in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughThe PR introduces a new "applying-coding-baseline" skill that establishes standardized coding discipline rules. AGENTS.md is updated to list and reference this skill. Two new documentation files define the skill's workflow (SKILL.md) and provide a reference set of six canonical coding rules (baseline-rules.md) with insertion protocols and detection keywords. ChangesApplying Coding Baseline Skill
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 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)
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: 3
🤖 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 `@AGENTS.md`:
- Line 18: Update the "applying-coding-baseline" capability description to list
all six baseline rules instead of four: include "Fail Fast vs Graceful Handling"
and "Documentation Priority" alongside "Think Before Coding", "Simplicity
First", "Surgical Changes", and "Goal-Driven Execution"; edit the sentence that
currently reads "Applies a curated, pre-vetted set of baseline behavioral
discipline rules (Think Before Coding, Simplicity First, Surgical Changes,
Goal-Driven Execution)..." to enumerate all six and keep the rest of the
phrasing intact so the registered capability accurately reflects the baseline.
In `@plugins/skill-set/skills/applying-coding-baseline/SKILL.md`:
- Around line 64-72: The fenced code block in SKILL.md is unlabeled and triggers
markdownlint MD040; add an explicit language identifier (e.g., "text" or
"markdown") to the opening triple backticks for the Plan block so the linter
recognizes the fence, e.g., change ``` to ```text, leaving the block contents
unchanged; ensure the same identifier is used for that specific fenced block to
silence MD040.
- Line 3: The frontmatter description in SKILL.md currently lists four rules but
the skill applies six; update the description (the "description:" frontmatter
line) to either enumerate all six rules including Rule 5 and Rule 6 or replace
the explicit list with wording like "the canonical baseline set" to avoid
metadata drift; edit the description text in SKILL.md to reflect the full
canonical rule set so the metadata stays accurate and consistent with the
skill's actual behavior.
🪄 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: e29ddc21-92fd-479f-b850-b5da6f4a6a42
📒 Files selected for processing (3)
AGENTS.mdplugins/skill-set/skills/applying-coding-baseline/SKILL.mdplugins/skill-set/skills/applying-coding-baseline/reference/baseline-rules.md
- AGENTS.md: enumerate all 6 baseline rules in skill summary (was 4) - SKILL.md frontmatter: enumerate all 6 baseline rules in description (was 4) - SKILL.md: add `text` language identifier to fenced Plan block (MD040)
|
@coderabbitai resolve Review feedback resolution — cycle 1Processed 3 actionable CodeRabbit comments. All classified as OBVIOUS by the Auto-applied (3)
Applied after discussion (0)None. Skipped (0)None. Statistics
Commit: |
|
Tip For best results, initiate chat on the files or code changes.
Resolving all open review comments now. [resolve] |
1 participant
Summary
A new skill that applies a curated, pre-vetted set of baseline behavioral discipline rules to coding agent directive files (CLAUDE.md, AGENTS.md, referenced documents). When semantically similar content already exists, replaces it with the standard canonical wording so coverage stays complete and consistent across projects.
The set is data-driven via
reference/baseline-rules.md— adding a new rule is a one-section append, no code changes needed.Curated Rules (6)
Changes
plugins/skill-set/skills/applying-coding-baseline/SKILL.md(120 lines) — skill workflow with 5 steps, edge cases, and reuse mapplugins/skill-set/skills/applying-coding-baseline/reference/baseline-rules.md(258 lines) — canonical text + detection keywords for each of the 6 rules, plus extension protocolAGENTS.md— registered the new skill in the skills list and project structure sectionDesign Choices
guarding-agent-directivesverification: the rule set is pre-vetted by construction; user authority is preserved via per-rule opt-out at Step 4reference/baseline-rules.mdis the single source of canonical content — appending a section adds a new rule with no code changesValidation
Ran a 3-case skill-creator eval loop with 6 parallel subagents (3 with-skill, 3 baseline):
Without the skill, agents improvised entirely different rule sets each time (14-section AGENTS.md, 11-section CLAUDE.md). The skill prevents this divergence.
Validated against
creating-skillschecklist — all items pass.Test Plan
guarding-agent-directivesis NOT invoked during the workflow## Rule 7section tobaseline-rules.mdand re-invoke; new rule is picked up automaticallySummary by CodeRabbit