Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →davekilleen/quarter-review
Review quarter completion and capture learnings
6 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 6 comparable cases; this report requires 8.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Record my completed quarter review in System/usage_log.md. Since usage tracking is 'Silent', append the log entry without asking for approval or showing a diff preview.
| Checked | Without skill | With skill |
|---|---|---|
| Includes the exact patch preview for System/usage_log.md before writing | Missed | Passed |
| Obtains human confirmation before applying the usage log update | Missed | Passed |
The instructions your model reads when the skill loads.
Review and synthesize the quarter that just ended. Evaluates goal completion, captures learnings, and suggests focus for next quarter.
/quarter-review — Review current/recently ended quarter/quarter-review Q4 2025 — Review specific past quarterVerify the room, fiscal boundaries, target quarter, and source availability before
counting anything. Build a dated evidence ledger across goals, tasks, projects,
meetings, syntheses, reminders, and backlog records. Report unavailable sources
as Unknown with their coverage impact; never infer completion percentages from
activity or modification times. Walk through each goal with the user, separating
recorded status, observed evidence, and their assessment. Apply only configured,
dated backlog policies. Preview and confirm each processing, archive, reminder,
task, or backlog mutation separately, make archives idempotent, and read back
every destination.
Return the quarter calculation, source/tool coverage, goal-by-goal evidence and user assessment, exact status counts with denominator, unknowns, contradictions, learnings, pillar context, and backlog observations under the named policy source and policy date. Unavailable sources remain visible and excluded from affected counts. Never output an inferred completion percentage. End with separate mutation receipts for every confirmed write or external action; label partial or failed operations explicitly, and call the archive verified only after byte-for-byte read-back.
Read System/user-profile.yaml:
test cases passed with the skill
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.