Skip to content

gaia-research/gaia-skill-tree / .agents/skills/fp-drift

fp-drift

Verified

Inspect scope and unexpected registry drift against the actual PR base and leave a concise final receipt. Use for "check for PR drift" or the final stage of feature-pipeline; never silently discard unknown changes or infer a clean diff from validator success.

Inspect drift and prove the finish state

Objective: leave a reviewable PR with honest final evidence and held decisions.

Shared execution contract

Read ../feature-pipeline/SKILL.md relative to this skill directory. Inherit its mode, authority, hard stops and finish-state proof. Default is structured economy; lean mode may combine stages. A routine checkpoint records progress and continues in lean/economy mode. Only explicit hard-gated milestones or an actual unapproved authority boundary wait for human approval. Standalone invocation ends when this skill's scoped deliverable is complete; it does not require approval to perform already-authorized work. Use the actual harness tools, never invented spawn APIs.

State helper: bash .agents/skills/feature-pipeline/scripts/state.sh. Inspect existing state and Git/PR state before work. State and planApproved are recovery notes, never authorization or L4 approval. Refer to the shared skill's checkpoint command before advancing; do not classify a real boundary as routine.

Work and done-check

Recover live PR base, tip, review evidence and CI. Fetch the actual base and inspect its diff, not an assumed main branch. A standalone drift audit can run with CI pending but must report that limit. A full pipeline cannot claim complete until required checks are green at the reviewed SHA.

Inspect changed files and, where relevant, gaia dev diff against registry state. A failed diff is an inspection failure; do not hide it with || gaia dev validate. Validation proves integrity, not absence of drift. Classify changes against the objective. If unexpected registry/evidence changes have no known owner, stop the affected decision, show ID/field/base/branch values and request disposition; do not silently revert, normalize or accept them. Continue independent work.

When available, python scripts/ci_churn.py <pr-number> can inform a concise cost receipt; missing telemetry is not a task blocker. No mandatory verbatim report.

Done: behavior, tests, review, scope and current-SHA CI are inspected. Receipt includes feature/scope, PR/base/branch/SHA, fixes, commands/results, review identity and independence limits, CI and any concrete founder decision still required. Record phase 7 only when terminal proof holds; retain actual ciStatus green rather than replacing verification status with a vague done flag. Never merge or close issues as an automatic terminal action.

writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall