Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

category-spec-planning

Use after the user asks to plan category-spec work, decompose an approved plan into cards, or organize plan phases into task/decision/research work.

Exécuter dans Manus

Aperçu

Use after the user asks to plan category-spec work, decompose an approved plan into cards, or organize plan phases into task/decision/research work.

Commande d'installation

npx skills add https://github.com/dzackgarza/lattice-research --skill category-spec-planning

Copiez et collez cette commande dans Claude Code pour installer le skill

Source

dzackgarza/lattice-research

Étoiles0

Forks0

Mis à jour16 mai 2026 à 08:21

SKILL.md

readonly

Plus depuis ce dépôt

même dépôt

category-spec-workflow

dzackgarza/lattice-research

Use when handling category-spec workflow state: cards, plans, decisions, TODO triage, retired cards, visual windows, branch/PR routing, validation handoff, or status updates.

2026-05-200

research-state-machine

dzackgarza/lattice-research

Use when moving research work from plan to execution, deciding whether a card is atomic, routing implementation/self-check/adversarial audit, promoting or rejecting results, or claiming GOAL.md discharge.

2026-05-200

category-framework-design

dzackgarza/lattice-research

Use when designing or reviewing category refinement order, Sage category creation, Hom/End/Aut structures, autsets, WithGenerators/FinitelyPresented axioms, dual-object routing, or constructor interception policy.

2026-05-180

research-planning-cleanup

dzackgarza/lattice-research

Use when doing post-hoc meta-review of completed cards, scanning for shallow/confabulated work that passed gate review, cleaning up planning debt, or identifying systemic Jerry-behaviour patterns across cards. Load when "planning cleanup", "meta-review", "completed card audit", or "card quality scan" is mentioned.

2026-05-180

research-proof-auditing

dzackgarza/lattice-research

Use when auditing computational or formal proofs, writing or reviewing mathematical argument notes, checking evidence sufficiency, reviewing Sage/GAP/Lean/Aristotle verification, detecting proof fraud, or deciding whether a result is accepted.

2026-05-180

category-spec-style

dzackgarza/lattice-research

Use when editing, reviewing, or authoring category specs, type surfaces, Sage wrappers, constructors, method ownership, smoke files, or category-spec implementation code.

2026-05-160

Source

dzackgarza

dzackgarza/lattice-research

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Commande d'installation

Téléchargement

Exécuter dans Manus

Utile pourSOC

Développeurs de logicielsProfessions informatiques et mathématiques15-1252L4

name	category-spec-planning
description	Use after the user asks to plan category-spec work, decompose an approved plan into cards, or organize plan phases into task/decision/research work.

Category Spec Planning

Use this skill for planning and plan decomposition around category_specs.

Planning gate

Plans are human + LLM collaborative artifacts. Do not create or enact an operative plan unilaterally.

Before implementation:

Switch to planning mode when creating or materially revising a plan.
Iterate with the user until the plan is explicitly approved.
Store the approved plan under root .agents/plans/features/FEATURE-ID/plans/PLAN-ID/.
Decompose the approved plan into concrete tracked cards.

Decomposition rules

Use feature cards only for feature roots.
Use spec cards for feature-owned spec surfaces.
Use task cards for executable implementation, research, bug-fix, smoke-triage, and audit work.
Use decision cards for unresolved mathematical or organizational choices.
Put executable tasks under the relevant plan phase's tasks/ directory.
Add acceptance criteria and source provenance to every executable card.
Link cards back to the approved plan.

References

Load category-spec-workflow for the canonical planning workflow, priority rubric, theme grouping, and card requirements.