agentleFS
liormeshliormesh/trestle/skills/cq/SKILL.md

cq

Skill2 starsChanged 11 days agoMITView on GitHub

Calling a project - tune this session into one project's full context (handoff doc, overview, state, gotchas) before working. Triggers on '/cq <project>', 'work on <project>', 'load <project>', 'tune into <project>'.

The file

Files
SKILL.md

/cq - Calling a project

/cq is the radio opening call ("seeking contact") - the user wants to tune this session into a specific project's frequency before you work. The project is: $ARGUMENTS

Load that project's context now, then confirm you're tuned in. This is the Context leg in action: pull the right context at the right moment, instead of re-briefing from scratch every session.

Steps

  1. Resolve the project. Map $ARGUMENTS to a folder in the knowledge base's projects/. If empty, list the projects whose overview says state: project (what's in flight - grep, don't guess from memory) and ask which one. If ambiguous, list the closest matches and ask.
  2. Read its context, in this order (skip any that don't exist):
    • The resume prompt: pm/handoff/<project>-resume-prompt.md - live status, finish line, next step. Read this first; it's written to orient a fresh session.
    • The overview: projects/<project>/overview.md - the stable description, its state:, the health-check command, key decisions.
    • Anything either of them points to as a must-read for this kind of work (deploy notes, known footguns). Don't read the handoff log unless the resume prompt is missing or you need history.
  3. Surface the project's own rules - anything in MEMORY or the project docs that changes how you should behave on this project (where it deploys, which credential to use, conventions to respect).
  4. Check the state. If the overview says state: project but state_changed is 45+ days old, say so in one line: a project is supposed to finish - is there still a finish line, or is this now an area / archive? If it's area, treat the session as maintenance; archive / icebox, confirm the user means to reopen it (and offer to flip it to project with today's date).
  5. Run a health check if this is a coding session (per feedback-health-check.md) - run the command in the overview's ## Health Check section before writing code. Skip for read-only work.
  6. Report back, briefly:
    • What frequency we're on - project, its state, and the current finish line.
    • Live action items / open threads (from the resume prompt).
    • The gotchas you'll respect this session.
    • What you read to get there. Then ask what we're doing.

This is read-and-orient only - don't change anything until the user says what the task is. Append <ISO-UTC> cq <project> to _analytics/usage.log.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.