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 the user asks to classify a batch of projects against eligibility rules and generate an approval preview before creating hierarchical child documents.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill eligibility-batch-organizer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/eligibility-batch-organizerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user asks to classify a batch of projects against eligibility rules and generate an approval preview before creating hierarchical child documents.
name: eligibility-batch-organizer description: 'Use when the user asks to classify a batch of projects against eligibility rules and generate an approval preview before creating hierarchical child documents.' disable-model-invocation: true
| Field | Bound contract | |---|---| | Trigger | User asks to classify projects against eligibility rules and create hierarchical child documents from a work summary. | | Authority | Human-gated: requires explicit human confirmation before creating any child document; every other write is reversible local, with version control as the rollback. | | Side effect | Creates one child document per eligible project under the specified parent, using the provided template. | | Done | Child documents created per eligible project and partial failures reported. |
1. Validate inputs. Confirm every required input is present and non-empty. Halt if any is missing. Done when: every required input is confirmed present, or a missing field is named. 2. Parse the work summary. Extract every project entry. Treat each entry as a candidate. Done when: every project entry is extracted, or zero projects found is reported. 3. Classify each project against the provided eligibility criteria as eligible or not. Produce a list of eligible projects with the matching criteria noted per project. Done when: the eligible list is produced, or zero eligible projects is reported. 4. Present the preview list to the human: every project with its eligibility classification and the criteria that matched or did not match. Wait for explicit human confirmation. Done when: the human confirms, or authority is withheld and the skill stops. 5. Upon confirmation, sequentially create one child document per eligible project under the target parent using the project template. Populate the template fields from the work summary entry. If any individual creation fails, record the failure by project name and continue with the remaining projects. Do not retry failed creations. Done when: every eligible project has a child document or a recorded failure. 6. Report completion. List every child document that was created successfully, every project that failed, and the total count. Done when: the report lists successes, failures, and totals.
A structured completion report: target parent ID and URL, table of child documents (project name, document ID, document URL, status of created or failed), counts of eligible projects, documents created, and documents failed. If zero documents were created, the report states the skill did not complete and names the blocking failure.
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.