SuperAPI AI Directory

implement-cr

Coding & development

View repository

Updated 10-30 20:28

About this skill

/implement-cr

Implement the CRs in $ARGUMENTS. This command does not author CRs; authoring goes through the governance skill.

Usage: /implement-cr <CR-ID | docs/cr/CR-*.md> [more CRs ...]

Preconditions

The procedure per CR is the change_flow of the operating_model block, with the subagent_creation, task_delegation, continuous_commit, testing, and user_scenario_testing blocks of the consumer's agent instructions. This skill depends on those blocks; when they are loaded, apply them, do not restate them.

Fallback. When those blocks are absent from the agent instructions, follow skills/governance/reference/cr-implementation-workflow.md instead, so a consumer without them still gets a working implementation step.

Tools

  • Create subagents only through the Workflow tool. Load the workflow-authoring skill before the first workflow.
  • Every agent() call passes model claude-opus-5-5 and effort low. The oracle of the mandate block is the exception: it uses model claude-fable-5-1 and effort high. A tier that the task states stays permitted.
  • Commit through the /checkpoint-commit workflow and recover context through /checkpoint-read.

1. Parse

  • Each argument is a CR ID (CR-NNNN) or a path under docs/cr/.
  • If $ARGUMENTS is empty, stop and print: usage: /implement-cr <CR-ID | docs/cr/CR-*.md> [more CRs ...].

2. Resolve all arguments first

  • Each argument must match exactly one docs/cr/CR-NNNN-*.md that is not a -validation-report, -rollback-log, or -iterate file.
  • Files under docs/cr/iterations/ are iteration ledgers and MUST NOT be resolved as a CR.
  • If any argument fails, stop before any work, name the failed argument, and make no commit.

3. Recover context

Run /checkpoint-read before the first CR, and again whenever the run resumes after context loss. When a CR in the argument list already has checkpoint commits, continue that CR from its last checkpoint rather than from its start, and do not repeat a CR that already completed.

4. Run each CR, strictly sequentially

In argument order. A CR starts only after the previous CR completes, so it reads the tree the previous CR left.

  1. Layer 0: write the intent statement from the CR.
  2. Review: a separate agent in a workflow, which did not author the CR, reviews it. On approval, set frontmatter status: approved.
  3. Layer 2: update the docs first.
  4. Layer 3: implement the code from the spec diff. Delegate each unit of work per task_delegation, with the fixed 8-section prompt.
  5. Commit each coherent step through the /checkpoint-commit workflow with the scope CR-NNNN, so the subject is checkpoint(CR-NNNN): ....
  6. Gate destructive changes with a rollback log per core_principles.
  7. Verify against the CR acceptance criteria, then against the intent. Use a user scenario per testing where the CR has a user surface.

If a CR fails review or verification, stop. Do not start later CRs.

5. Report

  • One line per CR: CR-NNNN status: completed|failed|not-started.
  • For a failed CR, add the failed step.
  • Set frontmatter status: implemented on each completed CR.
  • End the report with the /iterate-cr command that covers every completed CR, for example /iterate-cr CR-XXXX CR-YYYY, as the next step for post-implementation adjustment.