Intent CLI — Semantic Recorder

Trust Score 82/100

Record and preserve semantic history (intents, snaps, decisions) across agent sessions using the `itt` workflow to capture what and why.

triggers:record semanticsitt inspectrecord intentsnap createrecord decision

GitHub SKILL.md

What it does

Provides a structured workflow and CLI (itt) for recording semantic history: a single intent (the goal), snaps (milestones), and decisions (long-lived constraints). It ensures agent work is summarized in durable, queryable objects that survive context loss.

When to use it

When a user asks to record what was done and why (e.g., "record what we did")
At natural milestones or session end to preserve decisions and outcomes
When you need an audit trail of goals and rationale for future agents or team members

What's included

Scripts: none in-situ, but a full command reference for itt (init, inspect, intent/snap/decision commands) and examples for creating intents, snaps and marking done.
References: none flagged, but the README describes the .intent/ layout and recovery commands.
Instructions: clear guidance on object shapes (what + why), snap boundary judgments, decision hygiene, and session recovery (itt inspect).

Compatible agents

Suited for code-capable assistants and CLIs that can run itt and parse JSON output; useful for agents that must maintain long-running project memory or handoffs.

Audit Summary

Intent CLI is a semantic recording tool for agent sessions, using an `itt` CLI to capture goals (intents), milestones (snaps), and long-lived constraints (decisions). The SKILL.md is thorough with good examples and command reference. Scripts include a static site builder, a showcase syncer, and platform-specific install scripts. build_pages.py and install.sh failed in test env due to missing web assets and PEP 668 restrictions respectively — both expected in isolation. update_showcase.py ran cleanly. No security concerns; install scripts fetch from a hardcoded GitHub repo without checksum verification.

Watch Out

install.sh fails on externally-managed Python (PEP 668) — needs --break-system-packages or venv
build_pages.py requires full repo checkout with web assets to run
install.ps1 is Windows-only and was skipped in test

Notes

Well-structured skill for semantic history tracking. SKILL.md is comprehensive with clear triggers and command reference. Scripts are utility/infrastructure (site building, installation) rather than core skill logic — the main functionality is the `itt` CLI which is installed separately. No security issues found.

Information

Repository: intent
Stars: 13
Installs: 0

Trust Score

Overall82

Security90

Code Quality78

Architecture68

Usefulness62

Related Skills

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Tmux Bridge

Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.

SourceSage CLI

Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.

Nit (Nitter CLI)

Terminal client to browse tweets, view profiles, and search posts via Nitter instances without opening a browser.

hn — Hacker News CLI

Terminal-based Hacker News client with a CLI and optional interactive TUI for browsing top/new/best/ask/show/jobs stories, viewing threads with nested comments,

Lokalise Migration — Deep Dive

Step-by-step migration guide and tooling for moving translations from Crowdin/Phrase/POEditor into Lokalise, including transforms, uploads and validation.

Vercel Common Errors

Diagnose and fix common Vercel build, serverless runtime, and edge/routing errors with step-by-step checks and fixes.

Back to Skills