gaia-research/gaia-skill-tree / .agents/skills/fp-plan
fp-plan
VerifiedTurn verified findings into a bounded file-aware plan and reuse or prepare a draft PR. Use for "plan the fix", "draft the implementation plan", or the planning stage of feature-pipeline; preserve actual human gates without making every plan require approval.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.6 KB |
SKILL.md
View on GitHub---
name: fp-plan
description: >-
Turn verified findings into a bounded file-aware plan and reuse or prepare a
draft PR. Use for "plan the fix", "draft the implementation plan", or the
planning stage of feature-pipeline; preserve actual human gates without
making every plan require approval.
version: 4.0.0
---
# Plan the bounded change
**Objective:** give the implementer a scoped plan with observable done-checks.
## 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
Read findings and relevant source; issue numbers may legitimately be empty.
State phase 2 expects recovered exploration evidence, not necessarily public
issues. Write the problem, constraints, file-aware plan and finish state. In
structured economy, keep a small numbered plan with change/rationale/check per
item and bounded worker briefs; request a separate planner only when useful.
Reuse the existing branch and PR, and verify their actual base. Create a branch
or draft PR only within current authorization. Use real newlines and `--body-file`
for PR text; link governing issues without closing any prematurely. Persist branch,
PR number/URL and the plan reference for recovery.
In lean/economy mode a routine plan needs no user approval: leave `planApproved`
false and advance state to phase 3. In hard-gated mode present the concrete plan at
M2-plan and await explicit approval before implementation; record `planApproved`
true only after receiving it. A true schema/ontology/design/security boundary
stays held in every mode. State cannot approve it. Continue unaffected work.
Done: the implementer can locate the plan, branch, finish-state checks and held
decisions. Continue to `fp-implement` in an authorized full run; a standalone plan
returns that deliverable without implementing unrequested work.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |