planning-with-files
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Explicit overlay: use for /show-me-your-work or a user
$ npx -y skills add khaneliman/khanelinix --skill show-me-your-work --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/show-me-your-workContext preview
The summary Claude sees to decide when to auto-load this skill.
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Explicit overlay: use for /show-me-your-work or a user
name: show-me-your-work description: "Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Explicit overlay: use for /show-me-your-work or a user request for a decision trail, not merely because work is long or multi-phase." metadata: disable-model-selection: "true"
Maintain a reviewable decision trail for unattended, multi-phase, or high-risk runs. Record what was decided, why, and on what evidence so reviewers can inspect decisions without parsing entire transcripts.
A single TSV file with one row per decision point or checkpoint:
Header template: [decision-log-template.tsv](references/decision-log-template.tsv).
Log rows using [scripts/log.sh](scripts/log.sh):
scripts/log.sh <logfile> <phase> <decision> <why> <evidence> <result>
Helper automatically stamps ISO timestamps, creates headers, escapes spreadsheet formula triggers, and strips raw control characters.
gates. Skip trivial edits.
history.
Commit only when a reviewer requires the persistent audit trail.
presenting completion.
Run packages directly with: Or install from the packages output. For example:
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Audit coding-agent sessions and mine cross-harness history for recurring corrections, skill-routing gaps, and harness faults. Use…
Design and audit agent instructions, skills, plugins, subagents, prompts, hooks, and provider configuration. Use for AI-tool…
Sketch interfaces, state, and module structure before code. Use for explicit design-led implementation or as a caller-owned…
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena,…
Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot…