Interview the user relentlessly about a plan, decision, or idea until reaching shared understanding. Use when the user wants their thinking stress-tested, or asks to be "grilled" or "interviewed".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Interview me relentlessly about every aspect of this until we reach a shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one.
Ask questions one at a time, waiting for feedback before continuing. Asking multiple questions at once is bewildering.
If a *fact* can be found by exploring the environment (filesystem, tools, etc.), look it up rather than asking me. The *decisions* are mine — put each one to me with your recommended answer and wait for mine.
When a decision has discrete options:
- Cap at 4 total, free-text catch-all included. If more genuine options exist than fit, merge the most similar/adjacent ones rather than exceeding the cap or dropping the free-text slot.
- State each option's tradeoff against the others; mark the recommended one "(Recommended)".
- Numeric answer (count, date, size)? Skip the list, ask openly with an optional default — plain-number answers collide with plain-number labels.
- Selectable-question tool available? Use it; its built-in "Other" option is the free-text catch-all — don't number options yourself or add a second "something else" entry.
…
The line at the top of this page pins the label git:20260829.47ff630, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_kd7jdpfzpdgfmvyv
GET https://markdownregistry.com/api/v1/resolve?ref=vivantel/kms/clarify
GET https://markdownregistry.com/api/v1/blob/52c755b2e5e445a86ea877b2d76e6140735b4ac083cc25ef58ed10a77ef6d645
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
vivantel/kms · plugins/kms/skills/attribute/SKILL.md · Write commit messages and PR descriptions that lead with intent (why, not what), using Conventional Commits type…
vivantel/kms · plugins/kms/skills/bootstrap/SKILL.md · One-time setup of a fact/decision/guardrail/skill knowledge system in a project that has none yet, or a gap-fill pass…
vivantel/kms · plugins/kms/skills/brainstorm/SKILL.md · Generative ideation partner that explores multiple approaches to a problem or feature without writing anything or…
vivantel/kms · plugins/kms/skills/capture/SKILL.md · Turn what a work session produced into durable knowledge — draft new decisions, update changed facts, flag…
vivantel/kms · plugins/kms/skills/changelog/SKILL.md · Generate a CHANGELOG.md entry from git commit history (since the last tag, or full history if none exists), grouped…
vivantel/kms · plugins/kms/skills/conform/SKILL.md · Checks whether a pending changeset conforms to existing decisions and guardrails before it lands. Use before committing…
vivantel/kms · plugins/kms/skills/onboard/SKILL.md · Creates a role-specific onboarding plan from a project's existing knowledge artifacts, without writing anything. Use…
vivantel/kms · plugins/kms/skills/query/SKILL.md · Answer a question from a project's fact/decision/guardrail/skill knowledge base, with citations to the artifacts the…
vivantel/kms · plugins/kms/skills/quickstart/SKILL.md · Sets up a project's knowledge system and captures one real decision live, in the same sitting, so the value is felt…
zaxbyhub/opencode-swarm · .opencode/skills/clarify/SKILL.md · Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user…
zaxbyhub/opencode-swarm · .claude/skills/clarify/SKILL.md · Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user…
umputun/cc-thingz · plugins/workflow/skills/clarify/SKILL.md · This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and…
ericrisco/rsc-harness · skills/clarify/SKILL.md · Use when a spec exists and must be de-risked before planning — hunt its ambiguities, unstated assumptions and edge…
educlopez/ui-craft · .codex/skills/clarify/SKILL.md · UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request…
educlopez/ui-craft · .agents/skills/clarify/SKILL.md · UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request…
swingerman/engineer · engineer/skills/clarify/SKILL.md · Use when a single DAE artifact has ambiguities to resolve. Triggers — "/engineer.clarify", "clarify this spec"…
