Agent skill
chain-system
Create, list, and load multi-session chain links that capture work context for later continuation. Use when you want to save current progress, resume a project from a prior session, or inspect chain history. Triggers: chain link, chain load, chain list, save context, resume work, continue later, session handoff.
Install this agent skill to your Project
npx add-skill https://github.com/DeevsDeevs/agent-system/tree/main/chain-system
SKILL.md
Chain System
Overview
Capture durable, structured summaries of work so a later session can resume without re-discovery. Provide three subcommands under one skill: link, load, and list.
Usage
Invoke with a subcommand:
$chain-system link <chain-name>
$chain-system load <chain-name>
$chain-system list
If the chain name is missing for link or load, ask the user for it.
Chain Root
Default to .claude/chains to remain compatible with the existing Claude chain-system plugin. If the user explicitly wants Codex-only storage, switch to .codex/chains and confirm.
Subcommands
link
Create a new chain link summarizing the current work.
Steps:
- Build a concise but complete summary using this structure:
- Primary Request and Intent
- Key Technical Concepts
- Work Completed
- Decisions and Rationale
- Files and Code Changes (Created/Modified/Read)
- Unresolved Issues and Blockers (only if any)
- Pending Tasks
- Current Work
- Next Step
- Create a slug (kebab-case) and a human readable title.
- Create the directory:
mkdir -p .claude/chains/<chain-name>. - Generate timestamp in local time:
date '+%Y-%m-%d-%H%M'. - Write the summary to:
.claude/chains/<chain-name>/<timestamp>-<slug>.md - Write only the summary (no analysis), then tell the user the file path and how to load it.
Use the same file format each time so load can extract summary and next step reliably.
load
Load the most recent chain link for a named chain.
Steps:
- Find the most recent link:
ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -1
- If none, tell the user the chain does not exist and suggest
list. - Read the file fully and internalize it as working context.
- List the 5 most recent links:
ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -5
- Detect insufficiency and ask questions if needed:
- Missing context referenced by the link
- Ambiguous "Next Step"
- Stale link (>7 days old)
- Show the user: chain name, most recent link filename, short summary, next step, and the 5 most recent links.
- If any insufficiency flags exist, stop and clarify before proceeding.
list
List all chains with counts and most recent link.
Steps:
- Check for chains:
ls -d .claude/chains/*/ 2>/dev/null
- For each chain, show:
- chain name (directory)
- link count (
ls .claude/chains/<chain-name>/*.md 2>/dev/null | wc -l) - most recent link filename (
ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -1)
- If no chains exist, suggest
linkto start one.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
arxiv-search
Search arXiv preprint repository for research papers in physics, mathematics, computer science, quantitative biology, finance, and statistics. Use when finding academic papers, preprints, ML research, scientific publications. Triggers: arxiv, preprint, research paper, academic paper, scientific literature.
mft-research-experts
Run research orchestration for data quality, factor geometry, hypothesis validation, and incident forensics. Use when you need SHIP/KILL/ITERATE decisions with strict validation. Triggers: mft-strategist, data-sentinel, factor-geometer, skeptic, forensic-auditor, research pipeline, hypothesis validation, post-mortem.
datetime
Get current date and time in various formats. Use whenever you need the current date, time, timestamps, or formatted datetime values for any purpose (logging, file naming, scheduling, comparisons, etc.)
97-dev
Apply timeless programming wisdom from "97 Things Every Programmer Should Know" when writing, reviewing, or refactoring code. Use for design decisions, code quality checks, professional development guidance, testing strategies, and workflow optimization.
dev-experts
Apply opinionated developer personas for architecture decisions, production debugging, language-specific code review, comprehensive reviewer passes, and test strategy. Use when you need an architect plan, devops investigation, Rust/Python/C++ review, grumpy reviewer audit, or tester-driven test plan. Triggers: architect, devops, rust-dev, python-dev, cpp-dev, reviewer, tester, pre-merge review, refactor for maintainability.
polars-expertise
This skill should be used when the user asks about Polars DataFrame library (Apache Arrow) for Python or Rust. Triggers: "polars expressions", "lazy vs eager", "scan_parquet streaming", "convert pandas to polars", "pyspark to polars", "kdb to polars", "group_by_dynamic", "rolling_mean", "polars window functions", "asof join", "polars GPU", "polars parquet", "LazyFrame". Time series: OHLCV resampling, rolling windows, financial data patterns. Performance: native expressions over map_elements, early projection, categorical types, streaming.
Didn't find tool you were looking for?