agent-environment-retr…
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
Use when a repository decision needs an interview plus durable terminology and decision records. Not for remote, credential, publish, deploy, or irreversible changes.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill grill-with-docs --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/grill-with-docsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a repository decision needs an interview plus durable terminology and decision records. Not for remote, credential, publish, deploy, or irreversible changes.
name: grill-with-docs description: 'Use when a repository decision needs an interview plus durable terminology and decision records. Not for remote, credential, publish, deploy, or irreversible changes.' disable-model-invocation: true
| Field | Bound contract | |---|---| | Trigger | A repository decision needs an interview plus durable terminology and decision records. | | Authority | Reversible local: writes only CONTEXT.md and ADR files in the working repository; rollback is version control or undo. No remote mutation. | | Side effect | CONTEXT and ADR updates during the interview. | | Done | Frontier empty and no resolved term left unwritten. |
A repository working tree containing a decision to make. Optional: an existing CONTEXT.md and an ADR directory; both are created when absent.
1. Read the code domain model that the decision touches: entry points, types, and the modules on that surface. Bound the interview scope to this surface before any write. Done when: the entry points, types, and modules on the decision surface are read, and the interview scope is bounded to that surface with no write made. 2. Build the frontier: enumerate every unresolved term and open question the decision depends on. Done when: every unresolved term and open question the decision depends on is enumerated, and the frontier list is non-empty or the decision is confirmed to need no interview. 3. For each frontier item, ask one question. Consult the code, then resolve the term or decision against evidence found in the repository. Done when: each frontier item has a question asked, the code is consulted, and the term or decision is resolved against evidence found in the repository or marked unresolved. 4. As each item resolves, write the resolved term into CONTEXT.md and the resolved decision into a numbered ADR file. Done when: each resolved term is written into CONTEXT.md and each resolved decision is written into a numbered ADR file, and both files are confirmed on disk. 5. Repeat until the frontier is empty. Done when: the frontier list is empty, every item is resolved and written or marked open, and no unresolved item remains unrecorded.
The output is an updated CONTEXT.md containing every resolved term, one numbered ADR file per resolved decision, and a report listing any frontier items left open.
Formerly the ODIN Claude Plugin. The repository URL is unchanged. Outline-Driven Development, nicknamed ODIN, is a highly opinionated code-agent skill library: principles-first engineering, surgical editing, and workflow automation, published as installable
Repo: OutlineDriven/odin-claude-plugin
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential,…
Use when a human explicitly asks for a full repository agent-compatibility pass returning a scored report with prioritized fixes. Not for tasks that require…
Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Not for remote, credential,…
Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or…
Use when the user asks to make the skills framework work in a new harness, IDE, or CLI. Not for remote, credential, publish, deploy, or irreversible changes.