Agent skill

Chronicle

by ailyProject in ailyProject/aily-blockly

Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing.

GPL-3.0Auto-check passedDatabases

Install Chronicle

skills CLI
$ npx skills add ailyProject/aily-blockly --skill chronicle -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ailyProject/aily-blockly chronicle --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ailyProject/aily-blockly.git skills-src && mkdir -p .claude/skills && cp -r skills-src/public/skills/chronicle .claude/skills/chronicle && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
chronicle
GitHub stars
3.8k
Token cost
~1.6k tokens
SKILL.md length
529 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing.

  • Databases work in your project
  • SKILL.md covers Tool, Local SQLite Query Rules, Tables and Common Queries, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Chronicle is an agent skill from ailyProject/aily-blockly. Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases. It works with SQL. The repository describes itself as: AI IDE for hardware development, support Arduino, MicroPython, ESP32, STM32, RP2040, Nrf5x... The licence is GPL-3.0.

When your agent uses it

  • Databases work in your project

Example prompts

  • “/chronicle”

What it can do on your machine

Read from SKILL.md and the folder at commit 4aace5a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are sql and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chronicle loads about 1.6k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 529 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ailyProject/aily-blockly at commit 4aace5a, republished under its GPL-3.0 licence (© ailyProject). 529 words, ~1,550 tokens.

Download SKILL.mdSave it as .claude/skills/chronicle/SKILL.md (or your agent's skills folder).
name
chronicle
description
Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing.

Chronicle

Use this skill when the user asks about previous conversations, earlier project decisions, prior tool executions, compacted-away details, generated artifacts, daily summaries, usage/workflow tips, or rebuilding the local session index.

Chronicle is separate from memory_tool:

  • memory_tool reads and writes explicit notes under /memories/....
  • session_store_sql queries the read-only indexed session store containing saved turns, checkpoints, files, refs, tool requests, and artifacts.

Tool

Use session_store_sql.

Actions:

ActionPurposeRequired input
queryExecute one read-only SQL querydescription, query
reindexRebuild the local index from saved session historydescription, optional force

Only call action="reindex" when the user asks to rebuild the index, or when query results look stale and you explain why reindexing is needed.

Local SQLite Query Rules

  • Queries are read-only.
  • Use exactly one statement.
  • Use only SELECT or WITH.
  • Use datetime('now', '-1 day') for local date math.
  • Do not use DuckDB syntax such as now() - INTERVAL.
  • Use search_index MATCH ... for FTS search over indexed turn/checkpoint content.
  • Use LIKE for file paths, refs, and Chinese/no-whitespace fallback searches.
  • Escape single quotes in user text by doubling them.

Tables

sessions

One row per indexed session.

Important columns:

  • id: session id
  • cwd: working directory
  • repository: repository label when known
  • host_type: host/client label
  • branch: branch label when known
  • summary: session summary when available
  • agent_name, agent_description: agent surface metadata
  • created_at, updated_at
turns

One row per indexed turn.

Important columns:

  • session_id
  • turn_index
  • user_message
  • assistant_response
  • timestamp
checkpoints

Compaction/checkpoint summaries.

Important columns:

  • session_id
  • checkpoint_number
  • title
  • overview
  • history
  • work_done
  • technical_details
  • important_files
  • next_steps
  • created_at
session_files

Files touched or referenced by tools.

Important columns:

  • session_id
  • file_path
  • tool_name
  • turn_index
  • first_seen_at
session_refs

Lightweight external references extracted from turns.

Important columns:

  • session_id
  • ref_type
  • ref_value
  • turn_index
  • created_at
tool_requests

Tool-call audit rows.

Important columns:

  • session_id
  • turn_index
  • tool_call_id
  • tool_name
  • arguments
  • result
  • state
  • created_at
search_index

FTS table for session text and artifacts.

Important columns:

  • content
  • session_id
  • project_path
  • source_type
  • source_id
  • turn_index
  • title
  • created_at
Show full SKILL.md (226 more words)Show less

Common Queries

Search previous sessions for a topic:

sql
SELECT session_id, source_type, title, substr(content, 1, 300) AS excerpt
FROM search_index
WHERE search_index MATCH '"command_exec" OR "terminal"'
ORDER BY created_at DESC
LIMIT 10

Find recent sessions:

sql
SELECT id, cwd, summary, updated_at
FROM sessions
WHERE updated_at >= datetime('now', '-7 days')
ORDER BY updated_at DESC
LIMIT 20

Find prior command-line tool executions:

sql
SELECT session_id, turn_index, tool_name, arguments, state, created_at
FROM tool_requests
WHERE tool_name IN ('command_exec', 'run_in_terminal')
ORDER BY created_at DESC
LIMIT 20

Find sessions that touched a file:

sql
SELECT s.id, s.summary, f.file_path, f.tool_name, f.first_seen_at
FROM session_files f
JOIN sessions s ON s.id = f.session_id
WHERE f.file_path LIKE '%project.abs%'
ORDER BY f.first_seen_at DESC
LIMIT 20

Find checkpoint summaries:

sql
SELECT session_id, checkpoint_number, title, overview, created_at
FROM checkpoints
ORDER BY created_at DESC
LIMIT 20

Chinese/no-whitespace fallback search:

sql
SELECT session_id, source_type, title, substr(content, 1, 300) AS excerpt
FROM search_index
WHERE content LIKE '%命令行%' OR content LIKE '%工具%'
ORDER BY created_at DESC
LIMIT 10

Token/usage analysis when usage columns are present:

sql
SELECT s.agent_name,
       SUM(e.usage_input_tokens) AS input_tokens,
       SUM(e.usage_output_tokens) AS output_tokens,
       e.usage_model
FROM events e
JOIN sessions s ON s.id = e.session_id
WHERE e.event_type = 'assistant.usage'
GROUP BY s.agent_name, e.usage_model
ORDER BY input_tokens + output_tokens DESC
LIMIT 20

If the local store does not contain usage columns, say that token-level analysis is unavailable in the current index and use proxies such as long sessions, large turns.user_message, repeated session_files, and repeated tool_requests.

Workflows

When the user asks whether something happened before, search the current project/session index with session_store_sql. Prefer FTS search_index for free-text history and join to sessions only after you have candidate session_ids. Also check tool_requests, session_files, and session_refs when the user's question mentions tools, files, PRs, issues, commits, or artifacts.

If no results are found, say that the indexed history does not contain evidence. Do not claim the event never happened outside the indexed scope.

Standup / Summary

For daily or project summaries, first query recent sessions, then enrich with turns, checkpoints, session_files, and session_refs. Keep the summary grounded in the rows returned by session_store_sql.

Workflow Tips

For usage or workflow tips, inspect recent sessions, turn counts, repeated file touches, and repeated tool requests. Provide only recommendations grounded in observed rows.

Reindex

If the user asks to rebuild or refresh the session index, call:

json
{
  "action": "reindex",
  "description": "Rebuild local Chronicle session index",
  "force": true
}

After reindexing, report the before/after stats and retry the user's intended query if appropriate.

© ailyProject, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in public/skills/chronicle of ailyProject/aily-blockly.

Open the folder on GitHubat commit 4aace5a

Compare with similar skills

Chronicle next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Chronicle compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chronicle this skillailyProject/aily-blockly3.8k—~1.6kAutomated safety check: PassGPL-3.0
Evolving The Data ModelTriliumNext/Trilium38k—~2.1kAutomated safety check: PassAGPL-3.0
Orchardcore Data MigrationOrchardCMS/OrchardCore8.2k—~1.7kAutomated safety check: PassBSD-3-Clause
SQL Optimization Patternsynulihao/AgentSkillOS61711 repos~3.3kAutomated safety check: PassNone
SQL PortabilityHL7/sql-on-fhir151—~512Automated safety check: PassCustom licence
StmoSAP/project-foxhound1802 repos~1.8kAutomated safety check: PassGPL-3.0

Similar skills

  • Evolving The Data Model

    TriliumNext/Trilium

    A skill your agent uses when adding a DB migration or a new column/field to a Becca entity in Trilium ("add a migration", "new column on notes/attributes", "ALTER TABLE", "add a field to…

    38k GitHub stars~2.1k tokensUpdated today
    DatabasesAuto-check passed
  • Orchardcore Data Migration

    OrchardCMS/OrchardCore

    Creates and updates OrchardCore data migrations (DataMigration classes with CreateAsync/UpdateFromX).

    8.2k GitHub stars~1.7k tokensUpdated today
    DatabasesAuto-check passed
  • SQL Optimization Patterns

    ynulihao/AgentSkillOS

    Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.

    617 GitHub starsUsed in 11 repos~3.3k tokens
    DatabasesAuto-check passed
  • SQL Portability

    HL7/sql-on-fhir

    Analyse whether a SQL query is portable across database implementations using sqlglot transpilation.

    151 GitHub stars~512 tokensUpdated 2 days ago
    DatabasesAuto-check passed
  • Stmo

    SAP/project-foxhound

    Official

    Manage Redash queries and dashboards on Mozilla's STMO (sql.telemetry.mozilla.org) using stmo-cli.

    180 GitHub starsUsed in 2 repos~1.8k tokens
    DatabasesAuto-check passed
  • DB Migrations

    kurealnum/dotfiles

    A skill your agent uses when generating or regenerating Drizzle migration files, changing database schema tables or columns, resolving migration sequence conflicts after rebase, reviewing migration…

    290 GitHub stars~820 tokensUpdated 5 mo ago
    DatabasesAuto-check passed

More from ailyProject/aily-blockly

  • Abs Syntax Reference

    ailyProject/aily-blockly

    ABS 语法快速参考:权威 ABS 规则与示例 skill,覆盖块连接类型、参数顺序、语句输入、变量引用与常见示例。触发词:ABS、语法、块脚本

    3.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Blockly Best Practices

    ailyProject/aily-blockly

    Aily Blockly implementation workflow for scoped library evidence, ABS editing, workspace synchronization, and focused validation.

    3.8k GitHub stars~962 tokensUpdated today
    Auto-check passed
  • Library Migration Guide

    ailyProject/aily-blockly

    Complete guide for converting Arduino/ESP32 hardware libraries into Aily Blockly compatible format.

    3.8k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Blockly Project Planning

    ailyProject/aily-blockly

    Blockly project planning and creation workflow for no-project hardware requests.

    3.8k GitHub stars~630 tokensUpdated today
    Auto-check passed
  • Review

    ailyProject/aily-blockly

    Review uncommitted code changes

    3.8k GitHub starsUsed in 1 repo~274 tokens
    Auto-check passed

Works with

Categories

Questions about Chronicle

What does Chronicle do?

Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing. Chronicle is an agent skill from ailyProject/aily-blockly. Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing.

When should I use Chronicle?

Chronicle fits situations like: databases work in your project.

How do I install Chronicle in Claude Code?

Run `npx skills add ailyProject/aily-blockly --skill chronicle -a claude-code`. Or copy the skill folder (public/skills/chronicle in ailyProject/aily-blockly) into .claude/skills/chronicle in your project. Claude Code loads it when a task matches its description.

How do I install Chronicle in Codex?

Run `npx skills add ailyProject/aily-blockly --skill chronicle -a codex`. Or copy the skill folder (public/skills/chronicle in ailyProject/aily-blockly) into .agents/skills/chronicle in your project. Codex loads it when a task matches its description.

Can I use Chronicle in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ailyProject/aily-blockly --skill chronicle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chronicle, .gemini/skills/chronicle, .github/skills/chronicle and .opencode/skills/chronicle in your project.

What does Chronicle need to run?

SKILL.md names no scripts, command-line tools or credentials: Chronicle is instructions for the agent only.

Does Chronicle access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Chronicle safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Chronicle use?

Chronicle is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chronicle use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Chronicle?

Skills that share tags, products or a category with Chronicle: Evolving The Data Model (TriliumNext/Trilium, 38k stars), Orchardcore Data Migration (OrchardCMS/OrchardCore, 8.2k stars), SQL Optimization Patterns (ynulihao/AgentSkillOS, 617 stars) and SQL Portability (HL7/sql-on-fhir, 151 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chronicle?

ailyProject (a GitHub organization) maintains it in ailyProject/aily-blockly, which has 3,834 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 9, 2026.

Source: ailyProject/aily-blockly on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.