borghei/Claude-Skills / project-management/discovery/plan-grilling
plan-grilling
VerifiedInterrogate a plan, design or idea one round of questions at a time until every decision is settled. Use when stress-testing a plan before building, when a design feels underspecified, or turning a fuzzy workflow into a spec.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.6 KB |
| assets/question_log_template.md | markdown | 2.0 KB |
| assets/sample_question_log.json | config | 3.4 KB |
| assets/sample_question_log_flawed.json | config | 1.7 KB |
| assets/sample_question_log_midway.json | config | 3.7 KB |
| assets/sample_workflow_spec.json | config | 2.2 KB |
| assets/sample_workflow_spec_flawed.json | config | 578 B |
| assets/workflow_spec_template.md | markdown | 1.5 KB |
| references/question-taxonomy.md | markdown | 9.4 KB |
| references/running-the-grilling.md | markdown | 10.1 KB |
| scripts/question_log_checker.py | script | 11.0 KB |
| scripts/workflow_spec_checker.py | script | 9.1 KB |
assets/workflow_spec_template.md
View on GitHub# Workflow Spec — <name>
**Status:** draft | implementable
**Grilling sessions:** <n> (log: <link to question log>)
**Owner:** <person who runs or answers for this workflow>
## Summary
<Two sentences: what recurs, and what each run leaves behind.>
## Trigger
- **Type:** event | schedule | manual
- **Detail:** <the exact event, or the cadence with time and timezone>
- **Not triggered when:** <the cases that look like triggers but are not>
## Inputs
| Name | Source | Shape / example |
|------|--------|-----------------|
## Steps
| ID | Actor (agent / human / script) | Action | Uses |
|----|--------------------------------|--------|------|
## Human checkpoints
Put each checkpoint as late as it can go, so the person is asked once and
handed everything they need.
| After step | Decision asked | Brief presented (not raw output) | Default if no answer by |
|------------|----------------|----------------------------------|-------------------------|
Or: **Autonomous** — no checkpoint, because <reason the risk is acceptable>.
## Outputs
| Output | Destination | Who reads it |
|--------|-------------|--------------|
## Failure handling
<What happens when a step fails, when an input is missing, and who hears about it.>
## Done definition
Each line must be checkable by someone who was not in the grilling.
- <Every … / No … / … within N minutes>
## Vocabulary
| Term | Meaning in this workflow |
|------|--------------------------|
## Open questions
Must be empty before the status changes to implementable.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |