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 filing an approved task spec as a GitHub issue with a local archive and optional worktree implementer. Don''t use for spec drafting without human interrogation and redaction gates.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill issue-intake --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/issue-intakeContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when filing an approved task spec as a GitHub issue with a local archive and optional worktree implementer. Don''t use for spec drafting without human interrogation and redaction gates.
name: issue-intake description: 'Use when filing an approved task spec as a GitHub issue with a local archive and optional worktree implementer. Don''t use for spec drafting without human interrogation and redaction gates.' disable-model-invocation: true
| Field | Bound contract | |---|---| | Trigger | the user runs /issue-intake with a task idea | | Authority | Remote: files one GitHub issue; requires explicit human invocation. Preview the filing target and consequence before publication. | | Side effect | a filed GitHub issue plus a local spec archive and an optional worktree implementer | | Done | the spec is filed and archived with frontmatter, with any requested implementer spawned |
1. Receive the task idea from the `/issue-intake` invocation. If none was supplied, ask the user for one and stop until it is provided. Done when: one task idea is in hand. 2. Interrogate the user to resolve scope: problem statement, acceptance criteria, constraints, and explicit out-of-scope boundaries. Ask targeted questions; stop when the user confirms the spec is complete. Done when: the user confirms the spec covers all four scope dimensions. 3. Draft the spec as a GitHub issue title and body from the confirmed scope. The title summarizes the problem in one line; the body states the problem, acceptance criteria, constraints, and out-of-scope boundaries. Done when: the draft issue title and body state these elements. 4. Apply redaction gates: scan the draft title and body for secrets, credentials, private identifiers, and any content the user has not approved for public publication. Show the user the redacted title and body and the list of redactions. Proceed only after explicit human approval of the redacted form. Done when: the user approves the redacted draft. 5. Preview the filing target (repository and issue title) and the consequence: a public GitHub issue will be created. Require explicit human confirmation before filing. Done when: the user confirms the filing target and consequence. 6. File the approved, redacted spec as a GitHub issue in the target repository using the user's authenticated `gh` context. Done when: a GitHub issue URL is returned. 7. Archive the spec locally as a markdown file with YAML frontmatter capturing the issue URL, title, and filing timestamp, under the project's spec archive location. Done when: the local archive file exists with frontmatter. 8. If the user requested an implementer, spawn a worktree implementer bound to the filed issue. Otherwise stop. Done when: the implementer handle is returned, or no implementer was requested and the skill stops.
The filed GitHub issue URL, the local archived spec file path with frontmatter, and the implementer handle (or an explicit statement that no implementer was requested).
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.