skills/write-plan/SKILL.md
Write detailed implementation plans at file-level specificity. Use when breaking a design into executable steps.
npx skillsauth add the-own-lab/Claude-company-of-one write-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Author implementation plans that can be executed without ambiguity.
Write as if the executor is an enthusiastic junior engineer with no project context.
Every step must be self-contained and unambiguous. If someone has to guess what you meant, the plan failed.
Each step in the plan must include:
Each step should take 2-5 minutes to execute. If a step feels larger, break it down further. If it feels smaller, consider combining with an adjacent step.
Steps must be ordered by dependency. No step should reference code that has not yet been created by a prior step. Draw the dependency graph mentally before writing the sequence.
Read the relevant template before producing output:
Read ${CLAUDE_PLUGIN_ROOT}/templates/PLAN.mdRead ${CLAUDE_PLUGIN_ROOT}/templates/DESIGN.mdEvery plan starts with a prerequisites section listing:
documentation
Update BRIEF.md sections during a command run. Any skill that produces a brief-persisted artifact calls this to write it back.
development
Post-code check: run tests + confirm TODO acceptance items map to passing tests; applies a security lens but is not a separate scan.
documentation
Command post-step: write CHANGELOG + TODO once per command run. One call, not per-skill doc writes.
content-media
Author REQUIREMENTS.md + DESIGN.md + TODO.md for a feature. The three files are one contract; they ship together.