Use this skill in Codex to run the DART dart-retro workflow. The editable workflow source lives in .claude/commands/; this file is its generated adapter in the shared .agents/skills/ catalog.

Invocation

Claude Code/OpenCode: /dart-retro <arguments>
Codex: $dart-retro <arguments>

Treat the text after the skill name as $ARGUMENTS. When the workflow references $1, $2, etc., map those to the positional values supplied by the user.

Command Body

Run a retrospective and capture durable lessons: $ARGUMENTS

Required Reading

@AGENTS.md @docs/AGENTS.md @docs/ai/principles.md @docs/ai/components.md @docs/ai/verification.md @docs/onboarding/ai-tools.md

Skip If

Stop without editing when all are true:

no new patterns, gotchas, or failure modes were discovered
no workflow improvement is needed
the learning is too session-specific to help future agents or contributors
existing docs already cover what happened
the task was routine and left no durable insight

Routing

docs/ai/components.md owns routing for durable session learnings. Use this command as the hindsight workflow; do not duplicate the routing table here.

Workflow

Search existing docs before adding content.
Inventory the completed work before routing lessons. Consider domain/design choices, public API or package compatibility, CI/review failure modes, workflow friction, and cleanup or handoff steps separately so a late operational task does not hide feature-level learnings.
Decide whether each lesson is general enough for shared AI infra. Do not update AI components after every session.
Prefer update, remove, consolidate, or restructure over adding new files.
Make every durable learning discoverable from its owner surface: update an existing owner doc when possible, and when a new durable file is justified, link it from the relevant owner index or plan before retiring temporary context.
Keep docs/ai/principles.md compact; put procedures in the owner docs it links to.
Avoid ephemeral branch, PR, commit, or username details.
If adding a workflow command or skill, edit .claude/ source files and run pixi run sync-ai-commands.
Run pixi run lint before committing. For AI docs or adapter changes, also run the verification gates from docs/ai/verification.md: pixi run lint-md, pixi run check-lint-md, pixi run sync-ai-commands, pixi run check-ai-commands, pixi run check-docs-policy, and pixi run check-lint-spell.

Output

What learning was captured
Where it was documented
Checks run

Más de este repositorio

mismo repositorio

dart-analyze

dartsim/dart

DART Analyze: analyze repository evidence without editing

2026-07-131.2k

dart-architecture

dartsim/dart

DART Architecture: the DART 7 multi-physics, multi-solver, multi-backend simulation pipeline and where each abstraction is owned

2026-07-131.2k

dart-audit-agent-compliance

dartsim/dart

DART Audit Agent Compliance: audit and fix gaps when agents miss or cannot discover documented rules

2026-07-131.2k

dart-backport-pr

dartsim/dart

DART Backport PR: backport a merged main PR to a release branch

2026-07-131.2k

dart-benchmark-packet

dartsim/dart

DART Benchmark Packet: author or refresh a benchmark evidence packet for an owning plan

2026-07-131.2k

dart-branch-cleanup

dartsim/dart

DART Branch Cleanup: analyze or clean stale repository branches

2026-07-131.2k

dart-retro

Use this skill in Codex to run the DART dart-retro workflow. The editable workflow source lives in .claude/commands/; this file is its generated adapter in the shared .agents/skills/ catalog.

Invocation

Claude Code/OpenCode: /dart-retro <arguments>

Codex: $dart-retro <arguments>

Treat the text after the skill name as $ARGUMENTS. When the workflow references $1, $2, etc., map those to the positional values supplied by the user.

Command Body

Run a retrospective and capture durable lessons: $ARGUMENTS

Required Reading

@AGENTS.md @docs/AGENTS.md @docs/ai/principles.md @docs/ai/components.md @docs/ai/verification.md @docs/onboarding/ai-tools.md

Skip If

Stop without editing when all are true:

no new patterns, gotchas, or failure modes were discovered

no workflow improvement is needed

the learning is too session-specific to help future agents or contributors

existing docs already cover what happened

the task was routine and left no durable insight

Routing

docs/ai/components.md owns routing for durable session learnings. Use this command as the hindsight workflow; do not duplicate the routing table here.

Workflow

Search existing docs before adding content.

Inventory the completed work before routing lessons. Consider domain/design choices, public API or package compatibility, CI/review failure modes, workflow friction, and cleanup or handoff steps separately so a late operational task does not hide feature-level learnings.

Decide whether each lesson is general enough for shared AI infra. Do not update AI components after every session.

Prefer update, remove, consolidate, or restructure over adding new files.

Make every durable learning discoverable from its owner surface: update an existing owner doc when possible, and when a new durable file is justified, link it from the relevant owner index or plan before retiring temporary context.

Keep docs/ai/principles.md compact; put procedures in the owner docs it links to.

Avoid ephemeral branch, PR, commit, or username details.

If adding a workflow command or skill, edit .claude/ source files and run pixi run sync-ai-commands.

Run pixi run lint before committing. For AI docs or adapter changes, also run the verification gates from docs/ai/verification.md: pixi run lint-md, pixi run check-lint-md, pixi run sync-ai-commands, pixi run check-ai-commands, pixi run check-docs-policy, and pixi run check-lint-spell.

Output

What learning was captured

Where it was documented

Checks run