skills/project-state/SKILL.md
Manage lightweight project state files such as SPEC.md, DESIGN.md, TODO.md, .spec/, and .mem/. Use when starting multi-step work, planning features, recording decisions, updating next steps, preserving cross-session context, or preparing handoff notes.
npx skillsauth add oornnery/.agents project-stateInstall 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.
Use this skill to keep durable project context current without bloating AGENTS.md.
Top-level docs:
SPEC.md -- user goal, scope, requirements, success criteria, validation planDESIGN.md -- architecture, UX/API decisions, product/design constraintsTODO.md -- active task list, next steps, blocked items, done itemsOperational state:
.spec/state.md -- current objective, done, next steps, validation, open questions.spec/checks.md -- known validation commands and latest meaningful results.spec/handoff.md -- concise handoff for the next agent/sessionMemory:
.mem/hot.md -- stable high-value facts, max 80 lines.mem/decisions.md -- accepted decisions with date, reason, impact.mem/open-loops.md -- unresolved questions, blockers, follow-upsCreate or update these files when work is multi-step, spans sessions, changes product/architecture/design direction, or leaves meaningful next steps.
Do not create state files for trivial one-file fixes unless the repo already uses them.
SPEC.md, DESIGN.md, TODO.md, .spec/state.md, and .mem/hot.md if present.SPEC.md or .spec/state.md when scope is non-trivial..spec/state.md with done/next/validation only after facts are verified..mem/decisions.md or DESIGN.md.TODO.md, .spec/handoff.md, and .mem/open-loops.md when work remains.AGENTS.md stable; put project-specific state in these files..mem/hot.md short and factual. No transcripts, guesses, secrets, credentials, tokens, or private user data.YYYY-MM-DD.UNKNOWN or an explicit open question..spec/state.md:
# Project State
## Current Objective
## Done
## Next Steps
## Validation
## Open Questions
.mem/hot.md:
# Hot Memory
- [YYYY-MM-DD] Stable fact, decision, or preference.
Use this before ending multi-step work:
# Handoff
## Current State
## Completed
## Remaining
## Validation
## Risks
development
--- name: verification description: Discover and run project validation gates: format, lint, typecheck, LSP diagnostics, tests, build, static security checks, dependency audits, and RTK output handling. Use before claiming work is complete, when fixing broken checks, or when setting up a validation plan. --- # Verification Use this skill to prove changes with the strongest practical checks the repo already supports. ## Discovery Order 1. Read task aliases: `package.json`, `pyproject.toml`, `
tools
Build, review, or validate standalone Python scripts run with uv inline metadata. Use for one-file automation, operational scripts, script dependencies, shebangs, idempotency, safety, representative runs, and promoting scripts to packages.
development
Build, review, or validate Python packages and libraries where public API stability, packaging metadata, imports, examples, changelogs, build output, and compatibility matter.
tools
Build, review, or validate Python command-line applications and terminal tools. Use for argparse, Typer, Rich, Textual-adjacent CLI UX, stdout/stderr contracts, exit codes, automation-friendly flags, help output, and CLI tests.