agentleFS
alabenkhlifaalabenkhlifa/dayjob/skills/whats-next/SKILL.md

whats-next

Skill1 starsChanged 31 days agoMITView on GitHub

Use when the user asks what to work on, what's next, where to start, or opens a session without a clear task (e.g. "good morning", "what now?", "I'm back"). Points them to the dayjob skill that fits this moment.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use release and handoff.

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.
  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    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

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look at where the engineer is in their day and suggest the 1–3 skills that fit right now.

    line 8
  2. Distinctive:

    Run these; skip any that fail and never mention the failure.

    line 12
  3. Very specific:

    If git rev-parse prints nothing, this is not a git repo: skip the git and gh lines and the rows that need them, and find task lists with …

    line 38
  4. Distinctive:

    If MCP tools are available, also check: tickets assigned to me and not started (Jira, Linear, ClickUp, Trello, Asana).

    line 45
  5. Distinctive:

    Only suggest skills that are installed (they appear in your available skills).

    line 66
  6. Very specific:

    If another installed skill or command does the same job as a row's skill (a project /commit for ship-pr, a task runner like /opsx:apply for …

    line 68
  7. Very specific:

    If <base> comes back empty, skip the "commits not yet on <base>" check.

    line 72
  8. Distinctive:

    Every reason cites something concrete you saw.

    line 87
  9. Distinctive:

    Never start the suggested skill, and never commit, push, or edit anything, until the user says so.

    line 88

“Common” is measured: kept by at least 6 in 10 of the 13 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

What's next

Look at where the engineer is in their day and suggest the 1–3 skills that fit right now. Suggest only; never run them yourself.

Gather context

Run these; skip any that fail and never mention the failure.

date '+%A %H:%M'
git rev-parse --is-inside-work-tree 2>/dev/null
git status --short --branch
git log -1 --format='%cr'
base=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')
[ -n "$base" ] || base=$(git branch --list main master | head -1 | tr -d ' *')
git log --oneline "$base"..HEAD
# task lists this branch changed that still have open items:
git diff --name-only --diff-filter=d "$(git merge-base "$base" HEAD 2>/dev/null)" -- '*.md' ':!incident-*' ':!postmortem-*' 2>/dev/null | xargs grep -l '^ *[-*] \[ \]' 2>/dev/null
# only with a GitHub remote (git remote -v), as the gh account picked below:
gh pr list --search 'review-requested:@me' --limit 5 2>/dev/null
gh pr checks 2>/dev/null
grep -l '^Status: \(Open\|Mitigated\)' incident-*.md 2>/dev/null
grep -l '^Status: Resolved' incident-*.md 2>/dev/null
ls postmortem-*.md 2>/dev/null || true

gh account: the user may have several gh accounts, and the active one may not see this repo. Before the first gh call, list each account's access:

for u in $(gh auth status 2>&1 | sed -n 's/.*account \([^ ]*\).*/\1/p'); do echo "$u $(GH_TOKEN=$(gh auth token --user "$u") gh repo view --json viewerPermission -q .viewerPermission 2>/dev/null)"; done; true

Pick the first account with ADMIN, MAINTAIN or WRITE, else one with READ or TRIAGE. If none shows a permission, skip every gh call. Run every gh call as that account, GH_TOKEN=$(gh auth token --user <account>) gh ..., with 2>/dev/null. Never run gh auth switch.

If git rev-parse prints nothing, this is not a git repo: skip the git and gh lines and the rows that need them, and find task lists with these instead:

grep -l '^ *[-*] \[ \]' tasks.md TODO.md 2>/dev/null
grep -rl --include=tasks.md '^ *[-*] \[ \]' openspec/changes 2>/dev/null || true

If MCP tools are available, also check: tickets assigned to me and not started (Jira, Linear, ClickUp, Trello, Asana); 1:1 meetings today (calendar). Otherwise skip.

Pick

Go down the table; take the first matches, max 3, each skill once.

SignalSuggest
An incident-*.md with Status: Open or Status: Mitigatedincident
An incident-*.md with Status: Resolved and no postmortem-<same date>-<same slug>.mdpostmortem
Failing checks on the current branchfix-bug
Uncommitted changes (ignore incident-*.md and postmortem-*.md)ship-pr
An open item (- [ ]) in a task list found abovestart-ticket, naming the first open item (number and title)
Commits not yet on <base>, and no open item in a task listship-pr
Review requests waitingreview-pr
Start of the day or a greetingstandup
Friday afternoonweekly-update
A 1:1 on the calendar todayone-on-one
A ticket assigned and not startedstart-ticket
Nothing abovestart-ticket, reason "no open work found on <branch>"; or ask what they're working on

Only suggest skills that are installed (they appear in your available skills); skip any row whose skill isn't installed.

If another installed skill or command does the same job as a row's skill (a project /commit for ship-pr, a task runner like /opsx:apply for start-ticket), suggest that one in its place.

<base> is the remote's default branch (snippet above), falling back to main or master.

If <base> comes back empty, skip the "commits not yet on <base>" check.

Output

**Right now:** `<skill>` — <reason with evidence: branch, file count, PR number>
**Also:** `<skill>` — <reason>

Say "go" to start `<first skill>`.

The reply is exactly this template: the "Right now" line, 0–2 "Also" lines, and the "Say go" line.

Rules

  • Every reason cites something concrete you saw. No generic advice.
  • Never start the suggested skill, and never commit, push, or edit anything, until the user says so.
  • A failed command is not a finding; don't mention tool errors.

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.