agent-comms
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against the agent whitelist, or a…
Systematic gathering of accurate, version-specific documentation. TRIGGER when: researching a new API, library, or best practice before implementation. SKIP: turning findings into a plan (use planning-methodology); writing proposal.md (use spec-research).
$ npx -y skills add komluk/scaffolding --skill research-methodology --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/research-methodologyContext preview
The summary Claude sees to decide when to auto-load this skill.
Systematic gathering of accurate, version-specific documentation. TRIGGER when: researching a new API, library, or best practice before implementation. SKIP: turning findings into a plan (use planning-methodology); writing proposal.md (use spec-research).
name: research-methodology description: "Systematic gathering of accurate, version-specific documentation. TRIGGER when: researching a new API, library, or best practice before implementation. SKIP: turning findings into a plan (use planning-methodology); writing proposal.md (use spec-research)."
Systematic approach for gathering accurate, version-specific documentation before implementation.
| Priority | Source | Trust Level | |----------|--------|-------------| | 1 | Official documentation | HIGH | | 2 | Migration guides | HIGH | | 3 | Release notes | HIGH | | 4 | GitHub repos | MEDIUM | | 5 | Blogs, tutorials | LOW | | ❌ | Stack Overflow, AI content | AVOID |
Deliver ResearchPack format:
## ResearchPack: [Library/API Name] ### Quick Reference - **Library**: name v1.2.3 - **Use Case**: [what we're implementing] - **Confidence**: HIGH/MEDIUM/LOW ### Key APIs | Function | Signature | Description | |----------|-----------|-------------| | func1 | `func1(arg: Type): Return` | Does X | | func2 | `func2(arg: Type): Return` | Does Y | ### Setup Steps 1. Install: `npm install library` 2. Configure: ... 3. Import: ... ### Gotchas - ⚠️ [Common mistake to avoid] - ⚠️ [Version-specific caveat] ### Code Examples ```typescript // Example usage
1. [Official Docs](url) - v1.2.3, Section X 2. [GitHub](url) - README
## Quality Standards - **Accuracy**: API signatures match docs exactly - **Citations**: Every claim has source URL - **Version-aware**: Information matches project version - **Actionable**: Clear implementation guidance - **Time**: Under 2 minutes total ## Project-Specific Sources ### React/TypeScript - https://react.dev/ - https://www.typescriptlang.org/docs/ ### Material-UI - https://mui.com/material-ui/ ### Vite - https://vitejs.dev/ ### AI APIs - https://docs.imagerouter.io/ - https://platform.openai.com/docs/ ## Confidence Levels | Level | Criteria | |-------|----------| | HIGH | Official docs, exact version, tested | | MEDIUM | Official docs, close version | | LOW | Community source, version uncertain | | AVOID | No citation, speculation |
Spec-driven multi-agent orchestration for Claude Code — pure markdown, zero backend, runs on the stock runtime. 13 agents, 36 skills, 19 commands, 15 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
Repo: komluk/scaffolding
SendMessage recipient validation and worktreePath safety (CWE-59). TRIGGER when: validating a SendMessage `to:` recipient against the agent whitelist, or a…
3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which…
RESTful API design standards: resource naming, HTTP methods, status codes, pagination, versioning. TRIGGER when: designing new API endpoints, defining error…
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets…
Schema design, index strategy, migration safety, and query analysis. TRIGGER when: designing tables or indexes, writing a migration, or diagnosing a slow…