Adds the ck (Context Keeper) skill — deterministic Node.js scripts
that give Claude Code persistent, per-project memory across sessions.
Architecture:
- commands/ — 8 Node.js scripts handle all command logic (init, save,
resume, info, list, forget, migrate, shared). Claude calls scripts
and displays output — no LLM interpretation of command logic.
- hooks/session-start.mjs — injects ~100 token compact summary on
session start (not kilobytes). Detects unsaved sessions, git
activity since last save, goal mismatch vs CLAUDE.md.
- context.json as source of truth — CONTEXT.md is generated from it.
Full session history, session IDs, git activity per save.
Commands: /ck:init /ck:save /ck:resume /ck:info /ck:list /ck:forget /ck:migrate
Source: https://github.com/sreedhargs89/context-keeper
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Greptile fixes:
- Removed non-standard YAML frontmatter fields (observe, feedback, rollback) from all 4 skills — only name, description, origin, version per CONTRIBUTING.md
- Added null guard to checkInteractions implementation (was missing despite test)
- CI: replaced 2>/dev/null with 2>&1 (was silencing safety-critical errors)
- CI: quoted $RESULT variable (was breaking jq on JSON with spaces)
- CI: added division-by-zero guard when test suite is empty
- CI: added note that Jest is reference implementation, thresholds are framework-agnostic
CodeRabbit fixes (6 comments):
- All 4 skills: renamed 'When to Activate' → 'When to Use', added 'How It Works' and 'Examples' sections
- CDSS: DoseValidationResult.suggestedRange now typed as '| null'
- PHI: hyphenated 'Non-patient-sensitive'
Cubic fixes (7 issues):
- P1: CDSS weight-based check now BLOCKS when weight missing (was false-negative pass)
- P1: EMR medication safety clarified — critical = hard block, override requires documented reason
- P1: PHI logging guidance clarified — use opaque UUIDs only, not medical record numbers
- P2: CDSS validateDose now uses age and renal function params (ageAdjusted, renalAdjusted rules)
- P2: Eval CI example now enforces 95% threshold with jq + bc calculation
- P2: Eval CI example now includes --coverage --coverageThreshold on CDSS suite
- P2: CDSS suggestedRange null type fixed (same as CodeRabbit)
ajv was in devDependencies but required at runtime by scripts/lib/install/config.js,
causing 'Cannot find module ajv' when running ./install.sh. Also adds .yarnrc.yml
with nodeLinker: node-modules so plain `node` can resolve packages without PnP.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add missing code-review.md and development-workflow.md to zh/README.md directory listing
- Add mkdir -p command before copy in manual install instructions
- Fix TypeScript test command path in SKILL-DEVELOPMENT-GUIDE.md
- Add Anti-Patterns section to SKILL.md template
- Add Template category to Skill Categories table in CONTRIBUTING.md
- Add Pre-Review Requirements section to code-review.md (both en and zh)
- Add Pre-Review Checks step to development-workflow.md (both en and zh)
- Add trailing newlines to all files that were missing them
- Add docs/SKILL-DEVELOPMENT-GUIDE.md with detailed guidance on creating skills
- Update CONTRIBUTING.md with enhanced skills section linking to the new guide
- Covers skill architecture, categories, best practices, testing, and examples
The new guide provides:
- What skills are and when they activate
- Skill file structure and format
- Step-by-step skill creation tutorial
- Writing effective skill content
- Common patterns and anti-patterns
- Testing and validation checklist
- Complete examples gallery
- Add rules/zh/ directory with complete Chinese translations
- Translate all 10 common rule files:
- coding-style.md
- security.md
- testing.md
- git-workflow.md
- performance.md
- patterns.md
- hooks.md
- agents.md
- development-workflow.md
- code-review.md
- Add README.md for the zh directory explaining structure and installation
- Maintain consistent formatting with original English versions
- Keep technical terms and code examples in English where appropriate
- Add comprehensive code review standards for all languages
- Define when to review (after code changes, before commits)
- Include security review triggers and severity levels
- Reference relevant agents (code-reviewer, security-reviewer, etc.)
- Add review checklist covering security, quality, and performance
- Define approval criteria (Approve/Warning/Block)
This rule complements the existing code-reviewer agent by providing
clear guidelines on when and how to conduct code reviews.
- Add laraplugins MCP server to mcp-configs/mcp-servers.json
- Create laravel-plugin-discovery skill for Laravel package discovery
- Supports searching by keyword, health score, Laravel/PHP version
- No API key required - free for Laravel community
Add comprehensive Git workflow skill covering:
- Branching strategies (GitHub Flow, Trunk-Based, GitFlow)
- Conventional commits format and best practices
- Merge vs rebase with clear guidance
- Pull request workflow and templates
- Conflict resolution strategies
- Branch management and naming conventions
- Release management with semantic versioning
- Git configuration and useful aliases
- Common workflows and anti-patterns
This skill helps developers and teams establish consistent
Git practices for collaborative development.
Codex CLI reads skills natively from ~/.agents/skills/ (installed by
ECC installer / npx skills). The sync script was redundantly copying
the same skills from .agents/skills/ to ~/.codex/skills/.
Changes:
- Remove skill copy loop, variables, and path validation from sync script
- Update sanity checker to validate ~/.agents/skills/ instead of
~/.codex/skills/, downgrade missing skills from FAIL to WARN
- Update test assertions to verify skill sync removal
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
