Research Notes
Skill Writing
Findings:
- The trigger
descriptionis the most important skill line. - Keep
SKILL.mdshort; move detail to one-level reference files. - Use numbered workflows for multi-step tasks.
- Match instruction precision to fragility.
- Build validation loops into the workflow.
- Avoid explaining what agents already know.
Sources:
- https://www.skills.sh/docs
- https://www.mdskills.ai/docs/skill-best-practices
- Local skill creator:
~/.codex/skills/.system/skill-creator/SKILL.md
Zod First
Decision:
- Zod in
packages/core/src/schemas.tsis the source of truth. - JSON Schema is generated for external tools and review.
- Semantic cross-link validation stays in TypeScript because it is easier to maintain than encoding it in JSON Schema.
Sources:
Viewer Payloads
Decision:
- Hash payloads are the PlanPack viewer handoff target.
- Default to Brotli-compressed viewer JSON.
- Measure full JSON, viewer JSON, and TOON before changing transport.
- Hosted JSON is a fallback for large plans, private plans, or evidence-heavy plans.
Observed for examples/2026-06-03-comment-draft-autosave.planpack.json:
- Full minified JSON: 10907 chars.
- Viewer minified JSON: 5117 chars.
- Brotli viewer JSON hash: 1743 chars.
- TOON viewer payload: 5403 chars.
- Brotli TOON hash: 1774 chars.
Sources:
- https://github.com/toon-format/toon
- https://chromium.googlesource.com/chromium/src/+/main/docs/security/url_display_guidelines/url_display_guidelines.md
- https://developer.mozilla.org/en-US/docs/Web/API/URL/hash
Skills CLI
Finding:
npx skillsinstalls skill packages and syncs agent skill directories.- PlanPack profile prompts are not the same thing as Skills, so this repo keeps profiles under
agent-profiles/. - The PlanPack
SKILL.mdcan later be installed through the skills CLI after the format stabilizes.
Source:
npx skills --help
Plan Revisions
Decision:
- Keep durable revision summaries in
revisions. - Include revision
type,reason,changedPaths, and optional status transition. - Use JSONL only for detailed audit events. Do not require it for viewer state.
Claude Workflows
Findings:
- Dynamic workflows move orchestration into a repeatable script; intermediate state lives outside the main context.
- Use workflows for high-agent-count audits, migrations, cross-checked research, or hard plans drafted from multiple angles.
- Human sign-off should be modeled as a separate stage or run because workflows do not take arbitrary mid-run user input.
- Claude's taxonomy is useful: subagents are workers, skills are reusable procedures, agent teams use shared tasks, workflows hold the plan in code.
- Subagent profiles should declare capability envelopes: tools, model/effort, isolation, max turns, preloaded skills, and memory scope.
- Hooks and goals reinforce the PlanPack validation contract: done means transcript-visible evidence, not just agent confidence.
PlanPack decisions:
- Keep PlanPack JSON as the compact orchestration artifact, not a transcript.
- Let reusable skills/profiles hold execution details; plan steps reference those by ID.
- Treat the orchestrator as the owner of nested delegation. Workers return structured handoffs and should not recursively manage teams.
- Add workflow-style fields only when real runs need them; existing
pipeline.mode,dependsOn,parallelization, and handoff contracts cover v0.
Sources:
- https://code.claude.com/docs/en/workflows
- https://code.claude.com/docs/en/sub-agents
- https://code.claude.com/docs/en/skills
- https://code.claude.com/docs/en/agent-teams
- https://code.claude.com/docs/en/hooks
- https://code.claude.com/docs/en/goal
Mermaid Pipeline Views
Findings:
- Mermaid should be generated from PlanPack JSON, not authored as the source of truth.
- The strongest skill pattern is route by diagram intent, load only the needed guide, generate, validate, then render/export.
- Mermaid can act as an intermediate representation for validators or renderers, not just a pretty artifact.
- Keep renderer/export details separate from plan authoring; SVG/PNG/GIF themes are late-stage choices.
PlanPack decisions:
- Add a future diagram command or skill around
planpack diagram --type pipeline|handoff|validation|timeline. - Generate
.mmddeterministically frompipeline,dependsOn,parallelization,milestones, andvalidationContract. - Validate Mermaid before embedding it in the viewer or docs.
- Prefer a compact PlanPack-specific diagram skill over installing broad, verbose Mermaid skills as always-on context.
Sources:
- https://www.skills.sh/softaworks/agent-toolkit/mermaid-diagrams
- https://www.skills.sh/imxv/pretty-mermaid-skills/pretty-mermaid
- https://www.skills.sh/spillwavesolutions/design-doc-mermaid/design-doc-mermaid
- https://www.skills.sh/trailofbits/skills/mermaid-to-proverif
- https://www.skills.sh/davila7/claude-code-templates/mermaid-diagram-specialist
- https://www.skills.sh/zc277584121/marketing-skills/mermaid-to-gif
- https://www.skills.sh/intellectronica/agent-skills/beautiful-mermaid
- https://www.skills.sh/axtonliu/axton-obsidian-visual-skills/mermaid-visualizer