agentleFS
Sign inStart free
NicegarrryNicegarrry/claude-skills/delivery-deck/SKILL.md

delivery-deck

Skill0 starsChanged 5 months agoMITView on GitHub

Build the end-of-sprint delivery deck for Nick in qWork: what shipped (PRs, preview URLs, screenshots), deploys and rollbacks, gate/claims/review stats, spend against budget, open issues and the asks that need him. Use at sprint close (after budget_close and the scorecard), or when Nick says "what shipped", "sprint report", "delivery deck".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Read the qWork skill (~/qubit-wiki/os/connectors/qwork/skills/qwork/SKILL.md), then qw create deck and refine with qw ops.

    line 21
  2. Distinctive:

    Keep numbers from the scorecard.

    line 31
  3. Very specific:

    When he says he has reviewed, qw comment <id>.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

delivery-deck: sprint close report in qWork

Input: project slug and the sprint's budget id. Output: a qWork deck link sent to Nick, reviewed.

1. Gather (summaries only)

  • scorecard_export {project, budgetId}: tickets, clean/rework/failed rates, retries by kind, review verdicts, claims, spend, Codex tokens, deploys.
  • budget_status {project}: cap vs spent.
  • Merged PRs in the sprint window: gh pr list --state merged --search "merged:>=<opened date>" --json number,title,url,mergedAt.
  • Deploys (if Helm has C2a): deploy_status {project}: target, env, sha, state, url; note rollbacks.
  • Open issues: gh issue list --state open --json number,title,labels (map issue checklist first).
  • Asks for Nick: NEEDS-NICK items, taps pending, needs_human questions, anything blocked.

2. Build

Read the qWork skill (~/qubit-wiki/os/connectors/qwork/skills/qwork/SKILL.md), then qw create deck and refine with qw ops. Answer-first, one idea per slide:

  1. Headline: what the sprint delivered in one sentence, plus 3 numbers (tickets shipped, clean rate, spend vs cap).
  2. Shipped: one row per feature: PR link, preview URL, one-line outcome. For user-facing features add a screenshot (qw upload <deck id> <png>, then place it as an image element).
  3. Deploys: targets, what went where, any rollbacks and why.
  4. Quality: gate first-pass rate, retries by kind, review REQUEST_CHANGES count, claims flags, disputed reviews (a chart element).
  5. Spend: USD and Codex tokens against the budget cap (chart).
  6. Open: remaining tickets and follow-ups.
  7. Asks for Nick: each ask with the decision needed and a recommended answer. Last slide.

Keep numbers from the scorecard; don't recount by hand.

3. Review

  1. Send Nick the link: https://qwork.qubitstudio.app/s/<id>.
  2. When he says he has reviewed, qw comment <id>; apply with qw ops, reply and --resolve each thread; repeat until approved.

4. Publish (external action)

Sharing beyond Nick is his call. Only when he asks, tell him to set General access to "Anyone with the link" in the deck's Share sheet (agents cannot change sharing). Never share unasked.

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