opencode-skills-collection 4.1.0 → 4.1.2

package/bundled-skills/day-book/references/related-skills.md

@@ -0,0 +1,18 @@
+# Related Skills
+
+- @accounting-audit-system-builder - routes to this skill and the other 15 modules.
+- @receipt-accounting - the detail behind the receipt lines in this book.
+- @payment-accounting - the detail behind the payment lines in this book.
+- @petty-cash-management - the float that the cash book section is counting.
+- @source-document-filing - holds the `Source Documents` target.
+- @party-ledger-reconciliation - takes the balances this book produces and proves them.
+- @expense-accounting - the expense detail behind the payments booked here.
+- @inventory-stock-reconciliation - the same count discipline applied to stock.
+- @monthly-closing-statements - takes the closed day book into the trial balance.
+- @audit-preparation - a daily book with verified balances is an audit-trail item.
+- @accounting-software-selection - decides the day-book format this table must capture.
+- @credit-cycle-analysis - reads the debtor movement out of the receipts booked here.
+- @salary-wage-accounting - the salary run lands in the bank book here.
+
+
+See the [Reusable Prompt](references/reusable-prompt.md) reference for the full guidance.

package/bundled-skills/day-book/references/relations.md

@@ -0,0 +1,14 @@
+# Relations
+
+Link fields: `Source Documents`
+
+`Source Documents` points at the filing register, so a day-book line can be traced back to the
+voucher, receipt or bank advice behind it. In SQL it is `VARCHAR(255)` with a comment rather than
+a foreign key, and in Notion it resolves only once the filing register has been imported. The
+`VARCHAR(255)` with a comment is deliberate: no `FOREIGN KEY` is declared to a table this build
+does not create.
+
+`Transaction Reference` is deliberately free text, not a relation. On a `Movement` row it holds the
+receipt, payment or petty-cash number the line came from, and the same number also appears in the
+filing register; on a `Day Summary` row it holds the day's own reference. Confirm with the
+business whether they want it as a live relation before adding one.

package/bundled-skills/day-book/references/reusable-prompt.md

@@ -0,0 +1,50 @@
+# Reusable Prompt
+
+```
+I want to set up a day book for my company - daily cash, bank and digital receipts and payments,
+one movement row per entry, one day-summary row per day, an opening and a closing balance for each
+book, a duplicate check and a day-end balance verification.
+
+Ask me one short question per message, and only about what I have not already told you. Never
+batch two questions into one message.
+
+Before you generate anything, check the proposed design against itself. If the rules, the
+examples, the field definitions, the row meanings or the output formats disagree with each other,
+do not reproduce them as they stand: tell me the conflict and resolve it with the simplest
+accounting-safe interpretation, then derive all four artifacts from one consistent field model so
+that no field exists in one artifact and is missing or differently defined in another.
+
+Keep the two row types apart with a Row Type field. On a Movement row the amount, the reference,
+the voucher number and the party are the entry, the Book Section names the one book it touched,
+and only that book's In/Out amounts and balances are affected. On a Day Summary row the per-book
+In/Out figures are the day's totals, the balances are the day's opening and closing, the reference
+fields describe the day's detail set rather than one voucher, and Book Section is All Books.
+
+Define every balance field exactly: the Opening * Balance fields are what was brought into the
+day, the * Closing Balance fields are what was left at the end of it, and neither is ever today's
+movement. A day's opening balance is the previous day's closing balance for the same book, and the
+check that closes a day is previous closing plus today's movement equals today's closing, proved
+separately for cash, for bank and for digital.
+
+Keep the Debit/Credit presentation software-dependent. Never hardcode a Dr/Cr pair and never
+assume that all receipts are debit - record what the business's own software does in Debit/Credit
+Presentation.
+
+Record the day's break as a signed Balance Difference with a Reconciliation Status of Reconciled,
+Needs Review, Unreconciled or Unknown, taking the worst of the three books, and write per-book
+figures in Notes. A day must not be Done while the cash count or the bank position is
+unreconciled, or while the duplicate check has not been run.
+
+An ambiguous answer is not an answer: if I say yes, maybe, same, okay or fine to a choice, ask me
+again as an explicit choice. Never invent an amount, a balance, a date, a voucher number, a bank
+reference, a mode or a status. Unknown is a correct answer and is never turned into zero, so a book
+a movement did not touch is left blank rather than filled with 0.00.
+
+Then recommend the smallest setup that fits, and wait for me to ask before you build it. When I ask,
+output CSV, SQL DDL, JSON Schema and a Notion property mapping, with identical field names, types,
+order and meaning across all four. Use obviously fake example data only.
+
+If I ask for a review, review the design instead of rebuilding it. If I ask for a fix, preserve
+the valid information I supplied and correct only the structural, calculation and consistency
+problems.
+```

package/bundled-skills/day-book/references/security-safety-notes.md

@@ -0,0 +1,19 @@
+# Security & Safety Notes
+
+- Never fill in real names, bank details or transaction references. Placeholders only.
+- Label example rows as synthetic, and keep bank details masked.
+- A day book is a map of every movement of the business's money. Do not paste real statements,
+  balances or UTR references into a chat.
+- A duplicate or a balance break is a control finding, not a clerical fix. Report it, do not edit
+  the balance to make it go away.
+- Local reads, generation commands, and validation are part of a requested artifact build.
+  External writes, messages, provisioning, and publication require authorization for that
+  action and target; existing explicit authorization does not need to be repeated.
+- If sensitive data is supplied, avoid repeating unnecessary identifiers. Use only what
+  the requested review needs; keep generated templates empty. Do not claim deletion
+  from the conversation or service storage.
+- Privacy, legal and disciplinary cases need a qualified human reviewer before anything is acted
+  on.
+
+
+See the [Common Pitfalls](references/common-pitfalls.md) reference for the full guidance.

package/bundled-skills/day-book/references/select-options.md

@@ -0,0 +1,38 @@
+# Select Options
+
+Every list below is a starting set, not the business's confirmed taxonomy. The user's own values
+win. In Notion, add the options after import.
+
+**Row Type**
+
+```
+Movement | Day Summary
+```
+**Book Section**
+
+```
+Cash Book | Bank Book | Digital Payments Book | All Books
+```
+**Mode**
+
+```
+Cash | Bank | Cheque | Fonepay/QR | Other Digital Payment | Mixed
+```
+**Duplicate Check**
+
+```
+Checked - Clear | Checked - Duplicate Found | Not Checked
+```
+**Reconciliation Status**
+
+```
+Reconciled | Needs Review | Unreconciled | Unknown
+```
+**Entry Verified**
+
+```
+Not started | In progress | Blocked | Done | Cancelled
+```
+
+
+See the [Relations](references/relations.md) reference for the full guidance.

package/bundled-skills/dei-dashboard/SKILL.md

@@ -0,0 +1,307 @@
+---
+name: dei-dashboard
+description: 'Diversity, equity and inclusion dashboard: metric by department and period, value against target, group size and minimum-threshold flag. Use for DEI reporting.'
+category: business
+risk: safe
+source: self
+source_type: self
+date_added: "2026-09-26"
+author: WHOISABHISHEKADHIKARI
+tags: [sme, business, operations, database, csv, notion, sql, engage]
+tools: []
+source_repo: WHOISABHISHEKADHIKARI/sme-ops-system-builder
+---
+
+# DEI Dashboard
+
+**What it is:** Diversity & inclusion.
+
+## Overview
+
+Works out the smallest useful **DEI Dashboard** setup for the business in front of it, then
+builds it only when asked. The default output is a short recommendation, not a
+spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on
+request, from one field list so they cannot drift apart.
+
+Layer: Layer 6: Engage. Fits: Scale stage. Table code: n/a.
+
+## When to Use This Skill
+
+- dei dashboard
+- diversity reporting
+- workforce diversity metrics
+- inclusion tracker
+
+Also use it when the user says "diversity & inclusion", or describes the same process happening in a
+spreadsheet, a document or someone inboxes.
+
+Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces
+empty templates only - it never holds or processes real employee or customer data.
+
+## How It Works
+
+Follow the shared execution contract. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.
+
+### Step 1 - Identify intent
+
+Read the request and pick the intent before asking anything.
+
+- "set up" or "build" or "create" -> the user wants artifacts; go to Step 2.
+- "our process is ..." or "it is in a sheet" -> the user wants to move an existing process; capture it, then Step 2.
+- "is this right" or "review" or "audit" -> the user wants a check, not a build; answer from what they share.
+- "how do I ..." -> advice question; answer directly and offer the build only if it helps.
+
+Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
+
+> **Q:** Which stages of hiring do you want to look at?
+
+### Step 2 - Ask only what is missing
+
+Skip anything the user already answered, in any earlier message. Ask the rest one at a
+time, and stop as soon as the remaining answers would not change the output.
+
+- **Scope** - Hiring, progression or both? / Which stages? / By department or overall?
+- **Data** - What data exists today? / Voluntary self-ID? / Anonymised?
+- **Baselines** - Compare against what? / External benchmark? / Internal target?
+- **Current process** - Anything tracked now? / HRIS or a sheet? / Is it anonymised?
+- **Outcome** - What do you need? / A metric set or a dashboard view?
+
+Never invent an answer. If the user does not know, record it as unknown and carry on.
+
+### Step 3 - Hold the internal context
+
+Hold the answers in this shape. It stays internal - it is not shown to the user unless
+they ask, and it never carries a value the user did not give.
+
+```yaml
+module: dei-dashboard
+intent: null            # setup | advice | review | fix | build | convert | export
+scale: null             # Starter | Growth | Scale, only if the answer changes it
+areas:
+  "Scope": null
+  "Data": null
+  "Baselines": null
+  "Current process": null
+  "Outcome": null
+requested_outputs: []   # csv | sql | json | notion | xlsx - requested formats only
+confirmed_facts: []     # only what the user actually said
+open_questions: []      # the unanswered ones, in the order worth asking
+```
+
+### Step 4 - Recommend the smallest workflow
+
+If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.
+
+**Recommended approach:** Use voluntary, anonymised data and aggregate to groups large enough to protect people. Skip any breakdown that would identify someone.
+
+**Why this one:** Diversity data is easy to collect and easy to misuse. Anonymity and minimum group size are conditions of doing it at all, not nice-to-haves.
+
+**Workflow:** Voluntary data → Anonymised aggregation → Stage metrics → Review → Action
+
+### Step 5 - Build only on request
+
+Once the user asks for it, derive the fields from the confirmed context and emit the
+requested artifacts. For machine-readable text, keep prose outside the data; for files,
+provide a usable link. Report material validation failures or limitations separately.
+
+**A selected Notion output is rendered by `notion-manual-import`, so route the
+Notion step there.** When the user selects Notion, hand that step to
+@notion-manual-import: it holds the CSV, the property
+mapping, the import steps and the verification checklist, and it renders the Field
+Reference below instead of defining a table of its own. Do not restate the mapping
+here and do not improvise the import steps. Manual CSV and mapping outputs need no
+connection. For requested workspace changes, follow the shared contract: verify actual
+tool access and the target before writing. A user saying "connected" is not tool evidence.
+Never ask for a Notion password or token.
+
+For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the
+text correctly. A CSV is not an `.xlsx` workbook; create `.xlsx` only when the user
+requests a workbook.
+A CSV carries no types, so after it, name the columns
+that need a number, date or currency format applied.
+
+```csv
+Metric,Department,Period,Measure Type,Value,Target,Group Size,Minimum Group Size Met,Data Source,Notes,Metric ID
+Net revenue,Delivery,2026-03,Count,139240,95,12,TRUE,Manual,"Baseline captured in February; headcount denominators still exclude the contract workforce.",
+```
+
+```sql
+CREATE TABLE dei_dashboard (
+  metric VARCHAR(255),
+  department VARCHAR(255),
+  period VARCHAR(255),
+  measure_type VARCHAR(100) NOT NULL,
+  value NUMERIC NOT NULL,
+  target NUMERIC NOT NULL,
+  group_size NUMERIC NOT NULL,
+  minimum_group_size_met BOOLEAN NOT NULL,
+  data_source VARCHAR(255),
+  notes TEXT,
+  metric_id SERIAL PRIMARY KEY,
+  created_at TIMESTAMP DEFAULT NOW(),
+  updated_at TIMESTAMP DEFAULT NOW()
+);
+```
+
+```json
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "DEI Dashboard",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+      "Metric": { "type": "string" },
+      "Department": { "type": "string" },
+      "Period": { "type": "string" },
+      "Measure Type": { "type": "string" },
+      "Value": { "type": "number" },
+      "Target": { "type": "number" },
+      "Group Size": { "type": "number" },
+      "Minimum Group Size Met": { "type": "boolean" },
+      "Data Source": { "type": "string" },
+      "Notes": { "type": "string" },
+      "Metric ID": { "type": "integer" }
+  },
+  "required": [
+      "Measure Type",
+      "Value",
+      "Target",
+      "Group Size"
+  ]
+}
+```
+
+```markdown
+| CSV column | Notion property | Set after import |
+|---|---|---|
+| Metric | Title | Use as the database title |
+| Department | Text | Leave as Text |
+| Period | Text | Leave as Text |
+| Measure Type | Select (add options after import) | Convert to Select, add options: "Count", "Percentage", "Ratio", "Average" |
+| Value | Number | Convert to Number |
+| Target | Number | Convert to Number |
+| Group Size | Number | Convert to Number |
+| Minimum Group Size Met | Checkbox | Convert to Checkbox |
+| Data Source | Text | Leave as Text |
+| Notes | Text | Leave as Text |
+| Metric ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
+```
+
+The rows above are documentation examples only. Emit empty templates unless the user explicitly requests examples. Money stays `currency`, dates stay `date`,
+and anything pointing at another table stays `relation`.
+
+## Field Reference
+
+| # | Field | Type | SQL | JSON Schema | Notion | CSV example |
+|---:|---|---|---|---|---|---|
+| 1 | Metric | `text` | `VARCHAR(255)` | `string` | Text | `Net revenue` |
+| 2 | Department | `text` | `VARCHAR(255)` | `string` | Text | `Delivery` |
+| 3 | Period | `text` | `VARCHAR(255)` | `string` | Text | `2026-03` |
+| 4 | Measure Type | `select` | `VARCHAR(100)` | `string` | Select (add options after import) | `Count` |
+| 5 | Value | `number` | `NUMERIC` | `number` | Number | `139240` |
+| 6 | Target | `number` | `NUMERIC` | `number` | Number | `95` |
+| 7 | Group Size | `number` | `NUMERIC` | `number` | Number | `12` |
+| 8 | Minimum Group Size Met | `checkbox` | `BOOLEAN` | `boolean` | Checkbox | `TRUE` |
+| 9 | Data Source | `text` | `VARCHAR(255)` | `string` | Text | `Manual` |
+| 10 | Notes | `long_text` | `TEXT` | `string` | Text | `Baseline captured in February; headcount denominators still exclude the contract workforce.` |
+| 11 | Metric ID | `id` | `SERIAL PRIMARY KEY` | `integer` | Text (preserve source ID) | `(blank)` |
+
+## Select Options
+
+**Measure Type**
+
+```
+Count | Percentage | Ratio | Average
+```
+
+## Relations
+
+Link fields: none
+
+## Examples
+
+**Prompt**
+
+```
+We want to see where our hiring process drops people out.
+```
+
+**Context first** - one question per message, nothing already answered:
+
+> **Q:** Which stages?
+> **A:** Apply to offer.
+>
+> **Q:** Voluntary self-ID?
+> **A:** Yes, at joining.
+>
+> **Q:** Anonymised?
+> **A:** Not yet.
+
+**Recommended next step** - offered, not built:
+
+> Use voluntary, anonymised data and aggregate to groups large enough to protect people. Skip any breakdown that would identify someone.
+>
+> Workflow: Voluntary data → Anonymised aggregation → Stage metrics → Review → Action
+>
+> Want the CSV, SQL, JSON Schema and Notion mapping for this?
+
+## Best Practices
+
+- Build when requested; recommend and offer a build for advice-only requests.
+- One question per message. A batched intake reads as a form and gets guessed at.
+- Keep display names identical across CSV and JSON; document normalized SQL identifiers.
+- Use `relation` for anything that points at another table, `text` only for free text.
+- Money fields are `currency`, never `text`. Dates are `date`, never free text.
+- If the user requests an example row, keep it obviously fake so nobody imports it as real data.
+
+## Limitations
+
+- Empty template only. It does not compute payroll, tax, leave balances or KPIs.
+- Notion relations need both databases imported before the link column resolves.
+- Select options are a starting set. Rename them to match how the business talks.
+- No automation, reminders or sync. Those need the integration layer.
+- Does not collect personal data, make hiring decisions or set targets on your behalf.
+- Legal, tax and HR review is still required before this drives real decisions.
+
+## Security & Safety Notes
+
+- Never fill in real names, salaries, medical or banking data. Placeholders only.
+- Label example rows as synthetic, and keep bank details masked.
+- Local reads, generation commands, and validation are part of a requested artifact build.
+  External writes, messages, provisioning, and publication require authorization for that
+  action and target; existing explicit authorization does not need to be repeated.
+- If sensitive data is supplied, avoid repeating unnecessary identifiers. Use only what
+  the requested review needs; keep generated templates empty. Do not claim deletion
+  from the conversation or service storage.
+- Privacy, legal and disciplinary cases need a qualified human reviewer before anything
+  is acted on.
+
+## Common Pitfalls
+
+- **Problem:** a static mapping is described as a completed workspace build.
+  **Solution:** deliver manual mappings without a connection; claim a live change only
+  after the authorized tool operation succeeds.
+- **Problem:** asked all six questions in one message.
+  **Solution:** ask one, wait, and drop any the first answer already covered.
+- **Problem:** built a full system when one table was asked for.
+  **Solution:** build what was requested; mention the parent skill separately.
+- **Problem:** all four artifacts drift apart.
+  **Solution:** derive all four from the field list in this file, never by hand.
+- **Problem:** Notion import shows every column as Text.
+  **Solution:** that is expected. Apply the property mapping table once, after import.
+
+## Related Skills
+
+- ](https://github.com/sickn33/agentic-awesome-skills/blob/main/CATALOG.md) - find the relevant module, then read its skill.
+- @people-directory - the employee master record most modules link to.
+- @notification-reminder-hub - turns due dates in this module into reminders.
+
+## Reusable Prompt
+
+```
+I want to set up diversity & inclusion for my company.
+Ask me one short question at a time, and only about what I have not already told you.
+Then recommend the smallest setup that fits, and wait for me to ask before you build it.
+When I ask, output CSV, SQL DDL, JSON Schema, a Notion property mapping or an Excel workbook. Data only.
+```
+