Build and use per-sequence project context shards so an agent can work on a feature film without loading the whole project state.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add badgids/Story-Film-Skills --skill context-shards --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Context Shards?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-context-shards)More formats (shields.io, HTML) on the badges page.
---
name: context-shards
description: Build and use per-sequence project context shards so an agent can work on a feature film without loading the whole project state.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Context Shards
## Use
1. Read `../../references/CONTEXT_SHARDS.md`.
2. Read the current durable project state before you make a decision.
3. Work on the smallest valid `SEQ-###`, job frontier, or global gate.
4. Use `../../scripts/context_shards.py` for deterministic state changes or checks.
5. Save the result before you continue.
6. If the result blocks progress, keep the current Todo target blocked until the problem is fixed.
## Rules
- Do not load the full feature-film state when a sequence shard is sufficient. A shard includes the relevant canon and current story-state subset needed for its related character/location/prop IDs.
- Do not treat a shard as a second canon; authoritative project files still win.
- Do not infer completion from file existence alone.
- Do not hide an exception. Record the exception and the reason.
- Preserve stable IDs and project-relative paths.
- Use global checks only when the check needs global evidence.
## Done
The requested feature-scale state is written, validated, and traceable from durable project files.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling