‹ Back to apps
grillspec
Spec-driven agentic development: grill the user until nothing is guessed, write the spec, plan, then execute with TDD.
What’s inside
18 skills- Skillgrillspec-archiveUse when a change is done (every plan task ticked, final review clean, branch finished) - to merge its spec deltas into the living specs or mark it archived, after showing the user exactly what will change.
- Skillgrillspec-councilUse while grilling with a council turned on - before putting a root or hard-to-reverse decision to the user (every decision at deep depth) - to gather independent views from role subagents and external agent CLIs and show agreement and dissent inside the question.
- Skillgrillspec-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- Skillgrillspec-finishingUse when implementation is complete, all tests pass, and you need to decide how to integrate the work
- Skillgrillspec-grillUse when a change involves decisions the user should make - before writing a spec, plan or code for a feature, module, interface, schema or infrastructure change - and when the user says grill, interview me, let's plan, or asks how to build something. Interviews until nothing is left to guess and keeps a decision log that survives context loss.
- Skillgrillspec-initUse when setting grillspec up in a project, when the user asks to install or configure grillspec, or when grillspec status says to run init.
- Skillgrillspec-inline-executionUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
- Skillgrillspec-memoryUse right after a spec is approved, or when the user says "remember that…" - to propose the durable facts this change taught, get the user's approval, and store them in the project memory block in AGENTS.md (or long-form docs) so every future session starts knowing them.
- Skillgrillspec-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- Skillgrillspec-plansUse when a change's spec is approved and the phase is plan - to write the implementation plan in grillspec's task format (valid as an OpenSpec tasks.md), check it with grillspec validate, get the user's approval and executor choice, and hand off to execution.
- Skillgrillspec-receiving-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
- Skillgrillspec-requesting-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirements
- Skillgrillspec-specsUse when a grill is confirmed and the change is in the spec phase - to turn the decision log into a spec with requirements and ID-tagged scenarios, check it with grillspec validate and a builder-check, and get the user's approval before any plan or code.
- Skillgrillspec-subagent-executionUse when executing implementation plans with independent tasks in the current session
- Skillgrillspec-tddUse when implementing any feature or bugfix, before writing implementation code
- Skillgrillspec-verificationUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
- Skillgrillspec-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
- Skillusing-grillspecUse when starting any conversation, and before acting on any request that involves choosing between options - routes work through grilling, specs, plans and execution so the agent never guesses what the user would decide.