tactic-spec-grill
Skill0 starsChanged 3 months agoMITView on GitHub
Stress-test a completed OpenSpec change through a one-question-at-a-time decision interview, reconcile confirmed findings across its planning artifacts, and revalidate apply readiness. Use after proposal or planning artifacts are complete and before openspec-apply-change; requires the OpenSpec CLI and an initialized project or registered store.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- more-with-lessSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- openspec-verify-changeSkill
- tactic-lean-orchestrateSkill
- tactic-spec-brainstormSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use references/workflow.md as the authoritative workflow.
- Distinctive: line 12
Ask exactly one material decision question at a time and include a recommendation.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenSpec Change Grill
Use references/workflow.md as the authoritative workflow.
Remain between planning and implementation. Do not implement application code, start the apply workflow, or mark implementation tasks complete. Resolve one OpenSpec change through CLI-reported roots, stores, schemas, paths, and readiness state; never assume default artifact filenames.
Ask exactly one material decision question at a time and include a recommendation. Investigate factual questions from repository and planning evidence. Do not edit planning artifacts until the user confirms the shared understanding, and never claim a write or readiness result that was not observed.
Complete when: confirmed decisions have been reconciled across the selected change's planning artifacts, strict validation passes, every planning artifact is done or intentionally skipped, apply state is ready, and the user receives a truthful readiness report. Stop before implementation.
Subagent coordination
The grilling conversation and reconciliation remain in the main agent. Bounded read-only workers may verify facts or review one artifact dimension. Do not run several reviewers when their questions depend on the same unresolved user decision. Subagents never edit the change.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

