agentleFS
AaravChadhaAaravChadha/acstack/skills/ticket/SKILL.md

ticket

Skill2 starsChanged 4 months agoMITView on GitHub

Capture a brain-dump as a well-formed work item - verb-first title, acceptance criteria, file paths when known, an out-of-scope line. Files a GitHub issue in tickets mode or appends a numbered PLAN.md task in document mode; unknowns are marked TBD, never invented. Use when the user brain-dumps an idea, bug, or task to capture for later, or asks to ticket, file, or note something as work.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use orchestrate, spec and 4 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.
  • varun29ankuSSkill

    orchestrate

    This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.

    Also in 4 projects that use this

  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    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 5 projects that use this

  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 4

    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. Distinctive:

    Run before the skill's steps — per invocation, not per session (4.36).

    line 17
  2. Very specific:

    Never delete a decision. Supersede it: ~~old~~ → Verdict (YYYY-MM-DD): new call — reason.

    line 35
  3. Distinctive:

    Never fix, tune, or delete a test or eval case to raise a score.

    line 36
  4. Distinctive:

    Every filed item has:

    line 54
  5. Distinctive:

    NOT cover; the line that prevents scope osmosis later.

    line 61
  6. Very specific:

    No obvious phase → a dated checkbox under ## Open items instead.

    line 100

“Common” is measured: kept by at least 6 in 10 of the 20 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

/ticket — capture without friction, file without slop

The frictionless entry point that keeps ideas from routing around the system. A thought arrives half-formed; it leaves as a work item the next session can pick up cold — or it honestly wears a TBD.

Adjacent skills: /do (does the work; /ticket only captures it) · /triage (grooms the many existing items; /ticket files one new one).

<!-- acstack:runtime -->

Run before the skill's steps — per invocation, not per session (4.36); failures degrade to markdown:

link="$(readlink "$HOME/.claude/skills/health" 2>/dev/null || true)"   # empty = not symlinked
pack="$(dirname "$(dirname "$link")")"   # NEVER trust this unless $link was non-empty
if [ "${link#/}" != "$link" ] && [ -x "$pack/bin/acstack-config" ] && ! "$pack/bin/acstack-config" runtime | grep -q '=off'; then
  "$pack/bin/acstack-config" || true          # resolved keys, with sources
  "$pack/bin/acstack-update-check" || true    # ≤1 fetch/day; silent ONLY if already checked today
  "$pack/bin/acstack-recall" || true          # LEARNINGS.md + bug-class names, capped 3KB
else
  echo "runtime off — proceeding without recall/update-check"
fi
<!-- /acstack:runtime --><!-- acstack:principles -->

Operating principles

  • Be direct. Push back in writing when the plan or the user is wrong. No sycophancy.
  • Never delete a decision. Supersede it: ~~old~~ → **Verdict (YYYY-MM-DD):** new call — reason.
  • Never fix, tune, or delete a test or eval case to raise a score. Log the miss honestly and leave the case unchanged.
  • Name exact things: regex patterns, function signatures, model names, before → after numbers. Never "fixed bugs".
  • Attribution: follow the project's attribution setting (default none) — no AI-tool mentions in generated docs, no attribution trailers in commits or PRs. Commit with explicit -m/-F messages only.
  • Config: read .claude/acstack.md at the project root (fall back to ~/.claude/acstack.md) before acting. ## Settings keys override pack defaults; a ## <skill-name> section overrides both. Unknown keys and sections are ignored.
  • Docs: BRIEF.md (frozen seed) / PLAN.md (living plan) / JOURNAL.md (rolling journal). If the repo uses legacy names (PLANNING_PROMPT.md / PLANNING.md / STATUS.md), use those instead — never create both.
  • Recall: if LEARNINGS.md exists at the project root, read it before starting.
  • Conduct: follow the acstack-conduct block in this repo's AGENTS.md — the word is the mode; the user sets the pace.
  • Hackathon lane: if the project's AGENTS.md carries the acstack:hackathon-lane block, only /do changes the repository during the event. Any other skill that would write a tracked file, commit or push says what it would have done and stops; a change that is not a task goes through the lane's operator route.
<!-- /acstack:principles -->

One document set. Resolve exactly ONE BRIEF/PLAN/JOURNAL set and name its path in the report's scope line. If more than one candidate set exists — a monorepo, nested products, an apps/* tree each with its own docs — list the candidates and STOP. Never pick one silently: a confident answer about the wrong product is worse than no answer (conduct rule 8).

The bar

Every filed item has:

  • Verb-first title — fix scheme-name matching for hyphenated funds, not scheme names.
  • Acceptance criteria — runnable where possible; observable always.
  • File paths — when known or cheaply inferable from the dump.
  • Out-of-scope line — the adjacent thing this item deliberately does NOT cover; the line that prevents scope osmosis later.

What the dump doesn't say and the repo can't cheaply tell you is marked explicitly — Acceptance: TBD — needs <what> — never invented. A wrong guessed acceptance is worse than an honest TBD: it fails silently at /do time.

At most ONE round of clarifying questions, and only when the item would otherwise be unfileable (no discernible action at all). Friction is the enemy here: a captured-but-imperfect item beats a perfect item the user gave up on filing.

Tickets mode (tracking: tickets)

Preconditions — gh installed, gh auth status succeeding, and a GitHub remote present. Any failure names WHICH one failed and offers document mode; never guess. Then gh issue create:

  • Body follows .github/ISSUE_TEMPLATE/task.md (acceptance / files / out-of-scope sections).
  • Best-fit label from the standard set (bug / feature / chore); items with TBD acceptance also get needs-acceptance.
  • Milestone: the current one, unless the dump clearly targets another — ask only when genuinely ambiguous, and never more than once.

Document mode

Append a numbered task to PLAN.md:

  • Under the current open phase, taking the next free task number — existing tasks are NEVER renumbered. One carve-out: a number allocated on a branch is provisional until the branch merges. Two sessions reading the same plan draw the same number, and when the filings land at different offsets git merges them with no conflict (measured 2026-09-16, 5.17.1). So place the new task at the physical end of the phase's list, where a concurrent filing collides visibly instead of merging silently — and when two filings do collide, keep both and renumber the later-merged one; never drop either.
  • With its acceptance line (or the explicit TBD).
  • No obvious phase → a dated checkbox under ## Open items instead; /triage or the next /plan replan finds it a home.
  • No PLAN.md at all → do NOT create one. A plan scaffolded as a side effect of filing a ticket is a plan nobody designed. Say the item cannot be filed in document mode, print the well-formed task text so nothing is lost, and name /plan seed as what creates the document.

Report and stop

Report what was filed — the issue URL or the exact PLAN.md line, and in document mode that the number is provisional until the branch merges — and stop. Capture never starts the work (CONDUCT rule 5): /ticket writing code because the fix "looked quick" is exactly the failure mode this skill exists to prevent.

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.