Operations manager
- When to use it
- Staff rotas from who is available, what each shift needs and the working-time rules: a week or fortnight built and drawn as a grid, shown only once a script has checked every shift's cover and skills, and every person's hours, rest between shifts and days in a row.
- Covers
- Staff the shifts (1)
- Where you decide
- No gated loop of its own; the skills run one at a time.
- Size
- 6 skills · 0 loops
npx skilldrop-cli install --pack operations-manager
Installs 6 skills, including core.
Other ways to install
The pack's loops too, each as an invokable skill:
npx skilldrop-cli install --loop --pack operations-manager
In Claude Code, as a plugin (after /plugin marketplace add sananthanarayan/skilldrop):
/plugin install operations-manager@skilldrop
Into Cursor, Kiro or another IDE:
npx skilldrop-cli install --pack operations-manager --ide cursor
Start here: Get next week's rota, with every shift covered and nobody short of rest
Paste this into your agent:
Make next week's rota for the café, Monday to Saturday. Every day: an opening shift 06:30–14:30 and a closing shift 14:00–21:00, each needing one keyholder and one barista. Staff: Amira (keyholder, barista, max 40 h), Ben (barista, max 24 h, not Wednesdays), Chloe (keyholder, barista, max 32 h), Dev (keyholder, barista, max 40 h), Ema (barista, max 24 h, not Mondays or Tuesdays), Fay (barista, max 32 h). At least 11 hours between shifts, nobody more than 5 days in a row.
- Before you start
- Who works for you, what they can do, and when they can't work
- The shifts you need covered, with how many people of each kind
- Python 3 on the machine, which the rota check and week drawing run on
- How to tell it worked
- shift-roster leads with the rota as a table of days by people, says which shifts it couldn't fill and why, lists the rules it assumed, and saves a week grid drawn from a check that found every shift covered and no rest, hours or consecutive-day rule broken.
- If nothing happens
- If shift-roster does not activate, ask for it by name ("use shift-roster"). If it says a week can't be covered, it names the smallest change that would; give it that change or say which rule may bend.
A typical session
When: You need next week's rota, or want to know whether the one you drew breaks any rule.
You bring:
- your staff, with what each can do and their hours
- when each person can't work
- the shifts, with times and how many of each role they need
- your rules: rest between shifts, days in a row, hours in a day
-
- You
- Give it the staff, the shifts and the rules, or a rota you've already drawn.
- You get
- A rota that passes every rule, as a table and a week grid, or the problems in yours with the fix for each.
- You decide
- Publish the rota, or say which preference to trade (a person's day off, a rule that may bend).
-
- You
- Tell it what changed: someone off sick, a swap two people asked for.
- You get
- The rota re-checked with the change, and who can cover any shift it leaves short.
You end with: A rota you can publish, checked shift by shift and person by person.
Compare Operations manager with another pack
Skills in this pack (1)
Included from core (5)
- brief-intake Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, slide-outliner) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need. standard
- context-graph Map the decisions behind a codebase from its ADRs, RFCs and design records — each record's status and date, what supersedes or amends what, which records cite which, the files and folders each decision governs, and with git the commits that implemented it and the commits that changed each decision's code since it was made, and who made them — then answer "why is it like this?" from the record and check the record is still true. Finds supersessions only one side records, current decisions pointing at code that is gone, code that has drifted from its decision, two current decisions governing the same path, and references to records that don't exist. Use when the user asks "why do we use X", "which decisions govern this file or service", "is this ADR still current", "has the code drifted since we decided this", "are our ADRs out of date", "what was decided before I change this", wants a map of the architecture decisions, or is onboarding onto a codebase's history. standard
- council-review Convene a council of distinct senior-engineer personas (Architect, Security, Operator/SRE, Pragmatist, User-Advocate, plus optional bench seats) to deliberate a decision, design, or code change — each takes an independent stance, the genuine disagreements are surfaced as named cruxes, and a Chair issues a reconciled verdict that records dissents and states what would change the decision. The "Claude Council." Use when a choice has real tradeoffs and one reviewer's voice isn't enough: architecture decisions, risky changes before merge, RFC/design scrutiny, "should we adopt X?", rewrite-vs-refactor, or a pre-mortem. heavy
- doc-critique Review an existing document — ADR, design doc, runbook, exec summary, tech-comparison matrix, deck outline, decision log — and produce a structured critique against the same quality bars the skilldrop generators enforce. Categorizes findings by severity (blocker / major / minor / nit), points to the exact section/line, and suggests a concrete fix for each. Use when the user wants a second-pair-of-eyes review before sharing a doc, or has been handed someone else's artifact and wants to know what to push back on. heavy
- output-hygiene Review agent-written text before it ships and strip the machine artifacts it carries — invisible Unicode, non-breaking spaces, homoglyphs, harness-added provenance trailers, trailing chat closers — then flag the prose tells a script cannot catch, each quoted with a rewrite. Use when the user wants to clean up AI-generated output, asks to remove a Claude watermark, attribution footer, or "Generated with" line, wants a draft that does not read as machine-written, or needs a pre-ship hygiene pass on a document, commit message, or pasted chat answer. light