AGENT SKILL

sre-start-sprint

Work the active sprint as SRE, with stories as GitHub issues. Observability review of the sprint's drafts first (architecture's contract review waits on it), then instrumentation verification for stories at review, then SRE's own backlog. Run once PM has activated the sprint; it also resumes a sprint already under way.

License 许可
Apache-2.0
最近更新
2026-10-28
Stars
★ 0
Forks
0

01 前言 Front Matter

name
sre-start-sprint
description
Work the active sprint as SRE, with stories as GitHub issues. Observability review of the sprint's drafts first (architecture's contract review waits on it), then instrumentation verification for stories at review, then SRE's own backlog. Run once PM has activated the sprint; it also resumes a sprint already under way.
allowed-tools
Bash(.claude/bin/role:*) Bash(.claude/bin/sprint-state:*) Bash(.claude/bin/story list:*) Bash(.claude/bin/story show:*) Bash(.claude/bin/story check:*)
disable-model-invocation
true

02 资源文件 1

03 SKILL.md 正文

SRE: work the active sprint

Follow the order of work in your role file.

Preflight

  1. Run .claude/bin/role require sre ${CLAUDE_SESSION_ID}. If it fails, stop and tell the owner to run /role sre first. Then confirm the repo has switched over: .claude/roles/_repo.md has stories: github and sprints: project. If it doesn't, stop. This skill works the GitHub board, and this repo still keeps stories in files.
  2. Run git fetch origin and work from origin/main (repo §11 session start). Read .claude/skills/role/references/stories-on-github.md.
  3. Run .claude/bin/sprint-state. Unless it reports state: active, stop and report its output: PM hasn't activated a sprint yet. The active sprint is current; its goal is in the current sprint issue, and its stories are story list --sprint <n>.
  4. Read the session-start documents in the order repo §11 gives them, then every SLO doc in docs/specs/slo/ and the runbook index.
  5. Check where the sprint stands. If every draft in the sprint already has an Observability review (sre) comment, step 1 is done: go straight to step 2.

Steps

  1. Observability review. For every draft in the sprint, check its Observability requirements section against repo §7:

    • metric names, types, labels, and cardinality bounds (no unbounded labels)
    • required log fields, including the correlation ID
    • span names and parentage
    • symptom-based alerts tied to an SLO, each with its runbook entry

    Amend only that section (story body <ID> --body-file <f> --note "observability": keep every other section byte-for-byte). Then record story comment <ID> --record "Observability review" with what you checked and changed. Architecture's contract review waits on this, so do it first. Don't change status; that's architecture's.

  2. Instrumentation verification. story check done --status review lists every story at review still waiting on your §8 instrumentation, under sre owes. For each, verify its §7 instrumentation is emitting against a real backend (make up), or record exactly which series have no caller yet, per repo §8. Record it with story comment <ID> --record "§8 instrumentation". Architecture moves the story to done.

  3. Your own backlog: story list --sprint <n> --lane sre, in Rank order. Skip a story whose story show lists Labels: person-only: it needs what a lane never has (docker, a cluster, the network, credentials), so the owner runs it, and story start refuses it in a lane. When a story you reach needs those and isn't labelled, comment --to owner that it should be person-only, and leave it. Start each other one with story start <ID>, and deliver it in an sre/ PR carrying Story: <ID> and role:sre. The merge moves it to review.

As you reach the stories they concern, answer the comments addressed --to sre.

Stop

When nothing on your list can be picked up, stop. Report what's blocking each remaining item: the story, its status, and what it waits on.

04 同仓库更多 Skills

valesordev
valesordev/automate.valesordev.com

up-skill

Upstream skill, for when the dependency's job is asked for. Not for local work.

★ 0
valesordev
valesordev/automate.valesordev.com

do-thing

Do the thing when asked to do the thing. Not for other things.

★ 0
valesordev
valesordev/automate.valesordev.com

sprint-run

Plan the active sprint's role lanes and, once the owner confirms, start them in parallel. Reads the board, shows which stories and queues each role the repo runs as a lane (implementation, architecture, SRE, PM, and where the charters say so visual-designer and product) can pick up now and what everything else is waiting on, then runs one isolated `claude -p` session per lane (own worktree, role set, hooks on) via `.claude/bin/coordinator`, and reports from live state. Trigger on "run the sprint", "/sprint-run", "start the lanes", "what can the agents pick up", "kick off implementation and SRE". Not for working one story yourself (impl-start-sprint), activating or closing a sprint (pm-start-sprint, pm-close-sprint), or merging.

★ 0
valesordev
valesordev/automate.valesordev.com

role

Set this session's role (e.g. pm, product, architecture, sre, implementation, visual-designer, or none) and load its charter, then start an optional task given after the role; or show the current role when run with no argument, or the repo's role catalog with `help`. The owner runs it at session start. Never invoke it on your own or to change roles mid-task.

★ 0
valesordev
valesordev/automate.valesordev.com

release-review

Review a release's readiness across every delivery planner's board and repo (each feature's success signal, the milestones and stories delivering it, blockers and who owns them) and recommend go, no-go, or cut, written to docs/product/reviews/ (one file per review). Trigger on "/release-review", "where are we on R1", "are we ready to ship", "what's blocking the release", "go/no-go", and when a planner closes the last milestone a release names. Requires the product role. Not for sprint or cycle status (project-sync, producer-close-cycle), changing release scope (release-plan), or shipping or announcing anything (the owner).

★ 0
valesordev
valesordev/automate.valesordev.com

release-plan

Define or re-cut the product's releases in docs/product/releases.md (each release's promise, audience, bet, features, cut line, success signals), drafting docs/product/vision.md first if it doesn't exist, then check that the delivery planners' milestones each target a release and hand the gaps to the planners once the plan merges. Trigger on "/release-plan", "what's in the first release", "plan the releases", "re-cut R2", "what comes after phase 1", "does the roadmap still serve the players". Requires the product role. Not for a single feature's definition (feature-brief), readiness of a release in progress (release-review), or sprint and cycle planning (pm, producer).

★ 0