agentleFS
Sign inStart free
salvo8519salvo8519/fairmark/.claude/skills/session-start/SKILL.md

session-start

Skill1 starsChanged 8 days agoApache-2.0View on GitHub

Open a working session on Fairmark with full context — current branch and issue, latest journal entry, open pull requests and CI, sprint progress, work in progress and issues that can be started in parallel — then propose a plan. Use at the beginning of every session, or when the maintainer asks where the project stands.

41 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use deploy-verify, reflect and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • danielarif26Skill

    deploy-verify

    Verify a Vercel deployment actually went live and serves the correct production domain. Self-improving: reads its own run history before checking and logs the outcome after. Use when the user asks "did you deploy?", "is it live?", "verify the deploy", "check vercel", or after any Vercel deploy. Part of the Agentic OS (Level 1 backbone).

    Also in 3 projects that use this

  • Microsoft AzureSkill

    reflect

    Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

    Also in 4 projects that use this

  • ibahgatSkill

    autopilot

    Run autonomous multi-stage execution loops until acceptance criteria pass or blockers are reached.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 34 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the GitHub CLI is not authenticated, say so and continue with git only.

    line 13
  2. Distinctive:

    Read the context that the script points to:

    line 17
  3. Distinctive:

    Check hygiene and report each problem with the command that fixes it:

    line 25
  4. Distinctive:

    Wait for the maintainer's choice.

    line 37
  5. Very specific:

    create the branch <type>/<issue>-<slug> from an up-to-date main (for example feat/42-dcf-mid-year).

    line 38

“Common” is measured: kept by at least 6 in 10 of the 34 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from .agents/skills/session-start/SKILL.md by scripts/sync_agents.py. Edit the source, not this file. -->

Talk to the maintainer in their preferred language (CLAUDE.local.md). Do not change any file in this skill: it only reads and proposes.

  1. Collect the state, deterministically: uv run python scripts/project_state.py (add --json if you need to process it). If the GitHub CLI is not authenticated, say so and continue with git only. Then uv run python scripts/roadmap.py sync: it compares roadmap/roadmap.yaml with GitHub (statuses, milestones, open issues missing from the roadmap). Report any difference and propose sync --write --apply-milestones in a chore(project) pull request.
  2. Read the context that the script points to:
    • the latest entry in .agents/journal/ for the current branch, otherwise the latest overall; its "Next steps" are the default continuation;
    • the issue linked to the branch (gh api repos/{owner}/{repo}/issues/<n>) and its spec, if any (specs/NNNN-*/), with plan.md and tasks.md;
    • CHANGELOG.md section "Unreleased" and the fragments in changes/, for recent changes in the areas you will touch;
    • ADRs referenced by the spec or the issue.
  3. Check hygiene and report each problem with the command that fixes it:
    • uncommitted changes, or a branch behind main (propose git rebase origin/main);
    • work committed directly on main;
    • an open pull request of this branch with failing checks (propose /fix-ci);
    • issues labelled in-progress with no branch or pull request (stale claims).
  4. Propose the session plan, short:
    • Continue: the next step from the journal or tasks.md, if a branch is in progress.
    • Review queue: pull requests waiting for the maintainer (propose /pr-triage).
    • Start next: up to three ready issues from the active sprint (or the current milestone), ordered by dependency. Mark which ones can run in parallel: different area: labels and disjoint files, no dependency between them. For each, say whether it needs an Approved spec first.
  5. Wait for the maintainer's choice. When a new issue is chosen:
    • create the branch <type>/<issue>-<slug> from an up-to-date main (for example feat/42-dcf-mid-year);
    • label the issue in-progress and assign it: gh api -X POST repos/{owner}/{repo}/issues/<n>/labels -f "labels[]=in-progress";
    • for parallel work, suggest one git worktree per issue (git worktree add ../fairmark-<n> -b <branch> origin/main) or /run-sprint.

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.

Check your setup, free