context-engineering-checklist
The context-engineering-checklist skill provides a structured approach for implementing agent capabilities following Hugging Face Context Course principles. It guides developers through selecting appropriate layers (skills, MCP tools, workflows, sub-agents, or hooks/gates) and ensures proper implementation of each component with specific requirements for SKILL.md files, tool definitions, and workflow patterns.
Recursos
2Instal·la
npx skillscat add igorganapolsky/thumbgate/context-engineering-checklist Instal·la des del registre de SkillsCat.
The context-engineering-checklist skill provides a structured approach for implementing agent capabilities following Hugging Face Context Course principles. It guides developers through selecting appropriate layers (skills, MCP tools, workflows, sub-agents, or hooks/gates) and ensures proper implementation of each component with specific requirements for SKILL.md files, tool definitions, and workflow patterns.
Context Engineering Checklist (HF course → ThumbGate)
Source: The Context Course
Pick the right layer (Clarify)
| Need | Layer | Do not |
|---|---|---|
| How-to / policy for agents | Skill (Unit 1) | Long chat-only prompts |
| External API/tool | MCP (Unit 2) | Fake tools in prose |
| Multi-step pack / fan-out | Workflow/plugin (Unit 3) | One mega-prompt |
| Parallel specialists | Sub-agents (Unit 4) | Dual-edit without locks |
| Irreversible deny | Hook/gate (Unit 5) | Skill-only “never do X” |
Unit 1 — Skills
-
SKILL.mdfrontmatter:name, trigger-richdescription, slash - One failure class per skill
- NEVER / ALWAYS table with zero-ratio rules
- Scripts for mechanical steps; no secrets in body
Unit 2 — MCP
- Tool names match discovery / allowlist
- Side-effect annotations truthful
- Mutating tools covered by PreToolUse / gate-check
Unit 3 — Plugins / workflows
- Context → specialists → verify → synthesize
- Smoke + full modes; read-only reviews
Unit 4 — Sub-agents
- Linear claim or complement (no steal)
- Vault one-writer; scoped prompts
Unit 5 — Hooks / gates
- Matchable tool surface (not English prose)
- Hard floor if irreversible
- Deny + allow + false-positive tests
- Live probe before “protected”
Six-block context envelope
Before generation, package reusable context into all six blocks:
goal: one measurable outcome.businessData: current evidence with source and timestamp.examples: concrete good or bad few-shot cases.procedures: ordered actions and verification.constraints: safety, business, and SLA limits.rubric: grading criteria supplied before the answer is generated.
Use construct_context_pack.contextEnvelope instead of repeating these blocks
in chat. All blocks are required when the envelope is present, count againstmaxChars, and are part of semantic-cache identity.
For connector evidence, set metadata.sourceUpdatedAt,metadata.maxAgeSeconds, and metadata.sourceUrl on the stored context
object. Treat stale, future, invalid, and unknown freshness as
explicit evidence states, not current truth.
Scripts
bash ~/.grok/skills/context-engineering-checklist/scripts/check_context_layers.sh [path...]Related
- [[gsd-ralph-context-loop]]
- [[three-bus-ship-cycle]]
- [[xai-workflows-for-system]]
Instal·la
npx skillscat add igorganapolsky/thumbgate/context-engineering-checklist Instal·la des del registre de SkillsCat.