Review
Look back at how reliable "$ARGUMENTS" was, and decide what the error budget policy says to do now.
Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"ops-reliability-review","workflow":"ops","phase":6,"project":"<project>","event":"skipped","artifact":"06-review.md","note":"<reason or \"none given\">"}.
Compute with code. Perform every calculation (totals, balances, ratios, variances, projections) with a script — Bash, Python or a spreadsheet formula written to a file — and include the computation alongside the result. Never do arithmetic mentally.
Prerequisites
Part of a workflow. This skill is phase 6 (Review) of the Reliability Cycle workflow (ops); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or ops when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"ops-reliability-review","workflow":"ops","phase":6,"project":"<project>","event":"refused","artifact":"06-review.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"ops-reliability-review","workflow":"ops","phase":6,"project":"<project>","event":"started","artifact":"06-review.md","note":""}.
Read .singularskills/ops/<project>/02-slos.md for the SLOs, budgets and policy. Read 03-alerting.md and 05-on-call.md when they exist, and any incident reviews in .singularskills/ops/<project>/incidents/.
If .singularskills/ops/<project>/06-review.md already exists, keep it as 06-review-<date>.md (today's date as YYYY-MM-DD; if that name is taken, add -2, -3 and so on) before you write, and compare against it.
Process
Get the data: ask once for the SLI data over the period (good and valid events, or the SLO tool's report), page and alert history, and the incidents. Without data, the review lists what to measure and every number is
not measured.Compute per SLO with a script written to
.singularskills/ops/<project>/and included beside the result: attainment over the window, error budget consumed, and the burn rate now. Scripts read the user's files where they keep them and write results under.singularskills/.Apply the policy: what
02-slos.md's error budget policy says for each SLO at its consumption (for example, a freeze at over 100%), stated plainly as the policy's action, not a new decision.Alert and on-call health: alert volume, the actionable ratio, and pages per shift against the target, computed from the history.
Incidents and action items: the incidents in the period, their impact, and whether each action item from their reviews is done, late or not started.
Compare with the previous review when one was kept: the change in attainment, budget and pages.
Write the artifact to
.singularskills/ops/<project>/06-review.mdwith sections Period, SLOs and budgets, Policy actions, Alerts and on-call, Incidents and action items and Compared with last review.
Output
The review written to .singularskills/ops/<project>/06-review.md. Present the policy actions first (freeze or not), then the SLOs at risk, then overdue action items.
Record the run. After you have written the artifact, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"ops-reliability-review","workflow":"ops","phase":6,"project":"<project>","event":"finished","artifact":"06-review.md","note":""}.
Open the artifact with this frontmatter (agent is the agent you run in, or unknown; gate is passed when the gate ran clean and skipped under --skip-checks):
---
skill: ops-reliability-review
workflow: ops
phase: 6
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
End the artifact with ## Decisions and ## Open questions, in this shape:
## Decisions
- <what was chosen> — <why> — <what was rejected>
## Open questions
- <what the next phase or a reviewer must settle>