Skip to content

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

fp-explore

Verified

Explore a feature or CLI, reproduce defects and record bounded findings. Use for "explore X", "find issues with X", or the exploration stage of feature- pipeline; standalone runs return findings without automatically expanding scope.

Explore the feature

Objective: give the operator or next worker a reproducible view of defects.

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

Resolve the feature from the operator's instruction, then state. If both are missing, request the target. Exercise relevant happy, edge, invalid-input, flag-combination and composed-output cases in a sandbox. Retain this decomposition for cheap workers; avoid arbitrary probes that do not apply to the feature. Capture expected/actual behavior, exact reproduction and severity. Bound the initial pass to eight distinct findings; prioritize real high-impact problems.

Deduplicate before any authorized issue filing and use --body-file. Existing operator instructions may prohibit new issues; keep findings locally or in the existing PR instead. Record each finding/authorized issue immediately. No findings is a valid outcome; do not fabricate an issue to unlock planning.

Done: findings are reproducible and scoped, no forbidden external action occurred, and state phase advances from 1 to 2. In a full authorized pipeline continue to fp-plan after a routine checkpoint; in hard-gated mode present M1 evidence and wait. A standalone exploration returns the finding receipt.

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: 197kUpdated 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