Skip to content

An agent organization structured as a company — 15+ departments, 125+ skills, each independently installable, citing the standards and regulators that settle the question. Runs in Claude Code and ChatGPT.

Name software tools by category across 28 skills

Claude07574049ca3a
diff --git a/plugins/customer-experience/skills/support-operations/SKILL.md b/plugins/customer-experience/skills/support-operations/SKILL.md
index 9973964..bcbc4ce 100644
--- a/plugins/customer-experience/skills/support-operations/SKILL.md
+++ b/plugins/customer-experience/skills/support-operations/SKILL.md
@@ -69,6 +69,16 @@ by a wide margin and then blames the team.
Review a sample of resolved contacts against a rubric agreed with the team, and coach against it.
Reviewing only escalations trains for defense rather than quality.
+## Tooling
+
+Ticketing: Zendesk, Freshdesk, Intercom, Front, Help Scout, and similar; Jira Service
+Management where support and engineering work one queue.
+
+Knowledge base: usually the ticketing tool's own, or Confluence, Notion, or Guru.
+
+Quality review and workforce management — Klaus, Assembled, and similar — start paying off
+once you staff shifts rather than a team. Before that they are overhead.
+
## Never
- Staff to average volume. Support arrives in peaks.
diff --git a/plugins/data-analytics/skills/business-intelligence/SKILL.md b/plugins/data-analytics/skills/business-intelligence/SKILL.md
index 8fc6e50..81f14ad 100644
--- a/plugins/data-analytics/skills/business-intelligence/SKILL.md
+++ b/plugins/data-analytics/skills/business-intelligence/SKILL.md
@@ -64,6 +64,16 @@ check every figure by hand.
Dashboards accumulate. Review usage periodically and retire what nobody opens — with a notice period,
since the one person using it may be using it for something important.
+## Tooling
+
+BI: Power BI, Looker, Tableau, Metabase, Omni, Hex, and similar.
+
+Metric definitions belong in a semantic layer — dbt's, Looker's LookML, Cube — rather than
+in each dashboard's SQL, or the same metric will disagree with itself across two tabs.
+
+Spreadsheets remain the most-used BI tool in every organization. Plan for the export rather
+than pretending it will not happen.
+
## Never
- Build a dashboard nobody has a decision for. Start from the decision.
diff --git a/plugins/data-analytics/skills/data-engineering/SKILL.md b/plugins/data-analytics/skills/data-engineering/SKILL.md
index 9b1afae..ec102f2 100644
--- a/plugins/data-analytics/skills/data-engineering/SKILL.md
+++ b/plugins/data-analytics/skills/data-engineering/SKILL.md
@@ -51,6 +51,17 @@ is valid but wrong. Assert on the data itself, in the pipeline, and fail loudly:
A silent failure is worse than a loud one. Prefer stopping the pipeline to publishing data you do not
trust.
+## Tooling
+
+Warehouses and lakehouses: Snowflake, BigQuery, Databricks, Redshift, and Postgres or
+DuckDB at small scale, and similar.
+
+Ingestion: Fivetran, Airbyte, Stitch, and similar. Transformation: dbt, SQLMesh.
+Orchestration: Airflow, Dagster, Prefect, and similar.
+
+Buy ingestion and build transformation. Connector maintenance returns nothing for the time
+your team puts into it.
+
## Never
- Transform on ingest for business reasons and discard the raw copy.
diff --git a/plugins/demand-generation/skills/lifecycle-messaging/SKILL.md b/plugins/demand-generation/skills/lifecycle-messaging/SKILL.md
index 4de1052..0d749d6 100644
--- a/plugins/demand-generation/skills/lifecycle-messaging/SKILL.md
+++ b/plugins/demand-generation/skills/lifecycle-messaging/SKILL.md
@@ -77,6 +77,17 @@ it, and never leave it to default to the first line of the body.
- **Click but no conversion** — the destination, not the email.
- **Rising unsubscribes** — frequency or relevance. Usually frequency.
+## Tooling
+
+Lifecycle automation: Customer.io, Braze, Iterable, Klaviyo for commerce, HubSpot or
+Marketo for B2B, and similar.
+
+Transactional sending is a separate job with separate reputation: Postmark, SendGrid,
+Resend, and similar. Keep it off the marketing domain.
+
+In-product messaging: Intercom, Appcues, Pendo, and similar. An email that should have been
+an in-app prompt reaches half the audience at best.
+
## Never
- Send to a list that did not opt in.
diff --git a/plugins/demand-generation/skills/marketing-analytics/SKILL.md b/plugins/demand-generation/skills/marketing-analytics/SKILL.md
index ce896d2..8c1be80 100644
--- a/plugins/demand-generation/skills/marketing-analytics/SKILL.md
+++ b/plugins/demand-generation/skills/marketing-analytics/SKILL.md
@@ -52,6 +52,18 @@ Show the metric, its comparison period, and the decision it informs. A number wi
not information. Where a number moved, the report should say why or say that the cause is unknown —
"unknown" is a legitimate and useful finding.
+## Tooling
+
+Product and web analytics: Google Analytics 4, Amplitude, Mixpanel, PostHog, Plausible,
+and similar.
+
+Attribution: HubSpot or Salesforce campaign reporting, Dreamdata, Rockerbox, and similar.
+All of them model rather than observe — treat the output as directional and say so when
+you present it.
+
+Warehouse-native reporting beats a vendor dashboard the moment you need to join spend to
+revenue on your own definitions.
+
## Never
- Add tracking before the plan names the events and their properties. Retrofitting a schema onto live data is a migration, not an edit.
diff --git a/plugins/finance/skills/budgeting-and-forecasting/SKILL.md b/plugins/finance/skills/budgeting-and-forecasting/SKILL.md
index 3b16a91..3ebabeb 100644
--- a/plugins/finance/skills/budgeting-and-forecasting/SKILL.md
+++ b/plugins/finance/skills/budgeting-and-forecasting/SKILL.md
@@ -44,6 +44,16 @@ recurring costs compound and are constantly under-reacted to.
Explain the top few by value, not every line. A variance report covering everything gets read as
nothing.
+## Tooling
+
+Planning: Anaplan, Pigment, Workday Adaptive Planning, Vena, Cube, and similar. A
+well-built spreadsheet on a clean chart of accounts beats a planning tool nobody has been
+staffed to maintain; move when budget owners outnumber the people who can hold the model
+in their head.
+
+Driver data comes from the ledger, the CRM, and the HRIS. The planning tool is only ever
+as current as those connections.
+
## Never
- Present a forecast without saying what changed since the last one.
diff --git a/plugins/finance/skills/chief-financial-officer/SKILL.md b/plugins/finance/skills/chief-financial-officer/SKILL.md
index 8dc7ff9..80cfe4d 100644
--- a/plugins/finance/skills/chief-financial-officer/SKILL.md
+++ b/plugins/finance/skills/chief-financial-officer/SKILL.md
@@ -91,6 +91,17 @@ These are the artifacts of record. Where two of them disagree, this one is right
Escalate to Chief Executive when the plan is not fundable as written; to Legal & Risk on anything touching financial reporting obligations.
+## Tooling
+
+The stack a CFO is accountable for, by layer: the ledger (QuickBooks or Xero at small
+scale, NetSuite, Sage Intacct, or Dynamics 365 in the middle, SAP or Oracle at the top),
+planning (Anaplan, Pigment, Adaptive Planning, Cube), close (BlackLine, FloQast, Numeric),
+payments and spend (Bill.com, Ramp, Brex, Tipalti), and cap table (Carta, Pulley) — and
+similar in each.
+
+Know which system is the record for a number before you report it. Two systems that both
+hold a version of revenue will disagree, and the one you quoted will be the wrong one.
+
## Never
- Never present a forecast without stating its assumptions and what breaks it
diff --git a/plugins/finance/skills/financial-reporting-and-close/SKILL.md b/plugins/finance/skills/financial-reporting-and-close/SKILL.md
index ac38cc5..968e2c0 100644
--- a/plugins/finance/skills/financial-reporting-and-close/SKILL.md
+++ b/plugins/finance/skills/financial-reporting-and-close/SKILL.md
@@ -50,6 +50,16 @@ during a crisis.
Separate **timing** from **run-rate**. A miss caused by something slipping a week is a different
business fact from a miss caused by demand falling, and conflating them produces the wrong reaction.
+## Tooling
+
+Ledger, by scale: QuickBooks, Xero, or FreshBooks for a single entity; NetSuite, Sage
+Intacct, or Dynamics 365 Business Central once you consolidate multiple entities; SAP
+S/4HANA or Oracle Fusion at the top end, and similar.
+
+Close management — BlackLine, FloQast, Numeric, and similar — sits on the ledger and
+tracks the checklist, the reconciliations, and the sign-offs. It buys you an audit trail,
+not discipline. A shared checklist does the same job until the trail is what you lack.
+
## Never
- Leave the ledger open for late entries after the stated cutoff.
diff --git a/plugins/finance/skills/revenue-recognition/SKILL.md b/plugins/finance/skills/revenue-recognition/SKILL.md
index 2565130..eb10da5 100644
--- a/plugins/finance/skills/revenue-recognition/SKILL.md
+++ b/plugins/finance/skills/revenue-recognition/SKILL.md
@@ -54,6 +54,14 @@ The deferred balance is work owed, not money banked. Track it by cohort and obli
answer what it is composed of and when it releases. A balance nobody can decompose is one that
surprises you.
+## Tooling
+
+Subledgers that carry recognition schedules: NetSuite Advanced Revenue Management, Zuora
+Revenue, Maxio, Chargebee, Stripe Revenue Recognition, and similar.
+
+Spreadsheet schedules hold up until contracts carry multiple performance obligations or
+take mid-term modifications. That is the point to move, not a revenue threshold.
+
## Never
- Recognize on invoice date or cash receipt as a shortcut.
diff --git a/plugins/finance/skills/treasury-and-liquidity/SKILL.md b/plugins/finance/skills/treasury-and-liquidity/SKILL.md
index 0e3880a..2ef79e4 100644
--- a/plugins/finance/skills/treasury-and-liquidity/SKILL.md
+++ b/plugins/finance/skills/treasury-and-liquidity/SKILL.md
@@ -52,6 +52,16 @@ Do not reach for yield with money you have a date for. The return on operating c
liquidity risk, and treasury losses of this kind are always described afterwards as conservative
investments.
+## Tooling
+
+Cash visibility and forecasting: Kyriba, Trovata, Tesorio, and similar. Bank portals plus
+a spreadsheet cover a single-bank, single-currency position honestly.
+
+Payments and AP: Bill.com, Tipalti, Ramp, Brex, and similar.
+
+The control that matters is not in the tool list — it is dual approval on payment release,
+by whatever means you get it.
+
## Never
- Run the business on an indirect cash forecast.
diff --git a/plugins/it-operations/skills/backup-and-recovery/SKILL.md b/plugins/it-operations/skills/backup-and-recovery/SKILL.md
index 3cdc2c0..8f70a8d 100644
--- a/plugins/it-operations/skills/backup-and-recovery/SKILL.md
+++ b/plugins/it-operations/skills/backup-and-recovery/SKILL.md
@@ -55,6 +55,16 @@ the only honest input to an RTO, and it is invariably longer than assumed.
Test the full-scale case at least annually. Restoring one file proves the mechanism; restoring the
system proves the plan.
+## Tooling
+
+Backup platforms: Veeam, Rubrik, Cohesity, Commvault, Acronis, and similar.
+
+SaaS data is the gap people miss. Microsoft 365, Google Workspace, and Salesforce retain
+for a short window and no longer; Veeam, Druva, AvePoint, Keepit, and similar cover it.
+
+The tool is not the control. An untested restore is not a backup, whatever the console
+reports.
+
## Never
- Report backup health from job success rather than tested restores.
diff --git a/plugins/it-operations/skills/cloud-administration/SKILL.md b/plugins/it-operations/skills/cloud-administration/SKILL.md
index b8ce53e..ee9b6fb 100644
--- a/plugins/it-operations/skills/cloud-administration/SKILL.md
+++ b/plugins/it-operations/skills/cloud-administration/SKILL.md
@@ -82,6 +82,17 @@ sync. Retention settings are not backups, and the recycle bin is not a recovery
deliberately what needs independent protection under `it-operations:backup-and-recovery` rather
than assuming the vendor's durability promise covers your mistakes.
+## Tooling
+
+Platforms: AWS, Microsoft Azure, Google Cloud, and similar.
+
+Infrastructure as code: Terraform, OpenTofu, Pulumi, Bicep, CloudFormation, and similar.
+
+Cost visibility: the native cost tools, or CloudZero, Vantage, Finout, and similar.
+Guardrails: AWS Control Tower, Azure Policy, Wiz, and similar.
+
+Console changes nobody can reproduce in code become the outage you cannot rebuild from.
+
## Never
- Buy an application that cannot federate without recording the manual offboarding step.
diff --git a/plugins/it-operations/skills/endpoint-management/SKILL.md b/plugins/it-operations/skills/endpoint-management/SKILL.md
index 29580d6..6ff271d 100644
--- a/plugins/it-operations/skills/endpoint-management/SKILL.md
+++ b/plugins/it-operations/skills/endpoint-management/SKILL.md
@@ -52,6 +52,17 @@ one that gets left in a taxi.
Departures are coordinated with `people:onboarding-and-offboarding`, with asset return tracked
against `it-operations:it-asset-management`.
+## Tooling
+
+Windows: Microsoft Intune, Configuration Manager, Ivanti, and similar. Apple: Jamf Pro,
+Kandji, Mosyle, and similar. Cross-platform: NinjaOne, Automox, Addigy, and similar.
+
+Endpoint protection: Microsoft Defender for Endpoint, CrowdStrike Falcon, SentinelOne, and
+similar.
+
+Pick for your fleet's majority and accept a second tool for the minority. One tool that
+half-manages both platforms costs more than two that each work.
+
## Never
- Allow company data onto a device that never enrolled.
diff --git a/plugins/it-operations/skills/identity-lifecycle-administration/SKILL.md b/plugins/it-operations/skills/identity-lifecycle-administration/SKILL.md
index eec8c4c..b82cf69 100644
--- a/plugins/it-operations/skills/identity-lifecycle-administration/SKILL.md
+++ b/plugins/it-operations/skills/identity-lifecycle-administration/SKILL.md
@@ -54,6 +54,16 @@ formality that certifies whatever exists.
Hunt specifically for orphaned accounts — accounts with no owner, service accounts nobody claims,
and credentials that have not been used in months but still work.
+## Tooling
+
+Directory and SSO: Microsoft Entra ID, Okta, Google Workspace, JumpCloud, and similar.
+
+HRIS as the trigger: Workday, BambooHR, Rippling, HiBob, Gusto, ADP, and similar. Identity
+should follow the HRIS record rather than a separate list of who works here.
+
+Provisioning runs on SCIM wherever the application supports it. Where it does not, the
+joiner-mover-leaver steps are manual and belong in a ticket template, not in someone's head.
+
## Never
- Provision by copying an existing user.
diff --git a/plugins/it-operations/skills/service-desk/SKILL.md b/plugins/it-operations/skills/service-desk/SKILL.md
index 36cb5f7..da44f35 100644
--- a/plugins/it-operations/skills/service-desk/SKILL.md
+++ b/plugins/it-operations/skills/service-desk/SKILL.md
@@ -82,6 +82,17 @@ Each tier needs its own definition of done. Tier 1 closing a ticket by handing i
resolved anything, and counting that as a resolution is how a desk reports success while the
backlog grows one layer up.
+## Tooling
+
+ITSM platforms: Jira Service Management, Freshservice, ServiceNow, Ivanti Neurons,
+SolarWinds Service Desk, and similar. ServiceNow is a program rather than a purchase — do
+not take it on without the people to run it.
+
+Remote support: TeamViewer, ScreenConnect, Splashtop, and similar.
+
+Whatever the platform, a ticket has to carry the asset, the person, and a resolution
+category, or the reporting built on it is fiction.
+
## Never
- Run parallel unofficial intake channels and treat the ticket queue as the workload.
diff --git a/plugins/legal-risk/skills/contract-review/SKILL.md b/plugins/legal-risk/skills/contract-review/SKILL.md
index 3c4c697..6ee8394 100644
--- a/plugins/legal-risk/skills/contract-review/SKILL.md
+++ b/plugins/legal-risk/skills/contract-review/SKILL.md
@@ -44,6 +44,16 @@ with pre-approved fallbacks, thresholds below which the business signs without r
escalation path. Review every contract personally and you become the bottleneck the process was
meant to prevent.
+## Tooling
+
+Contract lifecycle management: Ironclad, Icertis, Agiloft, DocuSign CLM, LinkSquares, and
+similar. Signature alone — DocuSign, Dropbox Sign, PandaDoc — is a different and much
+smaller purchase.
+
+The value in CLM is the clause library and the searchable repository, not the approval
+workflow. If you cannot answer "which of our contracts cap indemnity below the fee paid"
+in a minute, that is the gap worth buying against.
+
## Never
- Approve terms whose operational obligations you have not confirmed are achievable.
diff --git a/plugins/legal-risk/skills/enterprise-risk/SKILL.md b/plugins/legal-risk/skills/enterprise-risk/SKILL.md
index 8237f72..1d673c5 100644
--- a/plugins/legal-risk/skills/enterprise-risk/SKILL.md
+++ b/plugins/legal-risk/skills/enterprise-risk/SKILL.md
@@ -54,6 +54,16 @@ Leadership needs the few risks whose residual exposure is above appetite, what i
what needs a decision. Not the whole register. A risk report that requires reading forty rows to
find the three that matter will not be read.
+## Tooling
+
+A risk register is a table, and for most organizations a spreadsheet or a database in
+Notion, Airtable, or Confluence is the honest answer. Dedicated platforms — LogicGate,
+AuditBoard, Riskonnect, ServiceNow IRM, and similar — earn their place when the register
+has to reconcile with audit findings and control testing in one system.
+
+Compliance automation tools cover control evidence, not enterprise risk. Do not let one
+stand in for the other.
+
## Never
- Score residual risk on controls that are planned rather than operating.
diff --git a/plugins/legal-risk/skills/regulatory-compliance/SKILL.md b/plugins/legal-risk/skills/regulatory-compliance/SKILL.md
index ff492fc..07cceef 100644
--- a/plugins/legal-risk/skills/regulatory-compliance/SKILL.md
+++ b/plugins/legal-risk/skills/regulatory-compliance/SKILL.md
@@ -58,6 +58,15 @@ conversation become an undocumented commitment.
Findings get root-caused like any other failure. A remediation that consists of retraining people on
a process that made the failure easy will produce the same finding next cycle.
+## Tooling
+
+Compliance automation — Vanta, Drata, Secureframe, Keel GRC, and similar — collects
+evidence continuously and maps one control across several frameworks. It earns its cost on
+the second audit far more often than the first.
+
+Policy and attestation lives in those same tools, or in the HRIS, or in Confluence. What
+matters is that a policy carries a version, an owner, and a record of who acknowledged it.
+
## Never
- Treat a certification as evidence of legal compliance.
diff --git a/plugins/operations/skills/procurement-and-sourcing/SKILL.md b/plugins/operations/skills/procurement-and-sourcing/SKILL.md
index 9a1c186..9104639 100644
--- a/plugins/operations/skills/procurement-and-sourcing/SKILL.md
+++ b/plugins/operations/skills/procurement-and-sourcing/SKILL.md
@@ -55,6 +55,16 @@ deciding that trade.
Route the resulting terms through `legal-risk:contract-review`, and anything touching customer data
through `legal-risk:privacy-and-data-protection` before signature rather than after.
+## Tooling
+
+Procure-to-pay: Coupa, SAP Ariba, Zip, Precoro, and similar. At smaller scale a request
+form plus the accounting system's purchase orders does the same work.
+
+Spend visibility: Ramp, Brex, Vertice, and similar, read against the ledger.
+
+Vendor risk lives in the GRC tooling, not here — but the intake form is where the security
+and privacy review has to be triggered, or it never happens.
+
## Never
- Write a requirement that only the preferred supplier can meet.
diff --git a/plugins/people/skills/onboarding-and-offboarding/SKILL.md b/plugins/people/skills/onboarding-and-offboarding/SKILL.md
index 5891289..48f260c 100644
--- a/plugins/people/skills/onboarding-and-offboarding/SKILL.md
+++ b/plugins/people/skills/onboarding-and-offboarding/SKILL.md
@@ -56,6 +56,17 @@ Exit conversations produce candid information that is unavailable any other way,
collected and never used. Aggregate themes over time and look by manager and by team; a single exit
is an anecdote, a pattern across four is a finding for `people:chief-human-resources-officer`.
+## Tooling
+
+HRIS as the record of who works here and when they started or left: Workday, BambooHR,
+Rippling, HiBob, Gusto, ADP, and similar.
+
+Onboarding workflow: the HRIS's own, or Sapling, Enboarder, or a checklist in the ticketing
+system, and similar.
+
+Offboarding has to reach identity, devices, and payroll the same day. Whatever the tools,
+one owner runs the checklist end to end. Split ownership is how accounts stay live.
+
## Never
- Let a start date arrive without access and equipment confirmed ready.
diff --git a/plugins/pmo/skills/project-delivery/SKILL.md b/plugins/pmo/skills/project-delivery/SKILL.md
index 2692587..297623f 100644
--- a/plugins/pmo/skills/project-delivery/SKILL.md
+++ b/plugins/pmo/skills/project-delivery/SKILL.md
@@ -57,6 +57,17 @@ Then present options with consequences — cut scope and name what, extend and s
capacity, which late in a project usually slows things further. Re-baseline once, visibly. Serial
one-week slips destroy credibility far faster than a single honest reset.
+## Tooling
+
+Delivery tracking: Jira, Asana, Linear, Monday.com, Smartsheet, Microsoft Project, and
+similar.
+
+Portfolio and capacity: Jira Align, Planview, Adaptive Work, and similar. Worth it when you
+are reconciling many teams' plans against one capacity pool, not before.
+
+The tool records the plan; it does not make the plan true. A status field nobody updates
+between meetings is worse than no field at all.
+
## Never
- Agree scope without written exclusions.
diff --git a/plugins/product/skills/design-system/SKILL.md b/plugins/product/skills/design-system/SKILL.md
index 3d087e6..34d7ba5 100644
--- a/plugins/product/skills/design-system/SKILL.md
+++ b/plugins/product/skills/design-system/SKILL.md
@@ -41,6 +41,15 @@ a polish item; it is whether people can use it.
- Never remove a token or component because it looks unused. You cannot see every consumer from
inside the system. Deprecate, announce, then remove.
+## Tooling
+
+Design source: Figma, and similar. Component documentation and review: Storybook.
+
+Token pipelines: Style Dictionary, Tokens Studio, Figma variables exported to code, and
+similar. Visual regression: Chromatic, Percy, Playwright snapshots, and similar.
+
+The system is the code, not the design file. When the two disagree, the code is what ships.
+
## Never
- Add a component for a single screen. A one-use component is a snippet, not a system.
diff --git a/plugins/revenue/skills/outbound-prospecting/SKILL.md b/plugins/revenue/skills/outbound-prospecting/SKILL.md
index bdae41b..f944fbb 100644
--- a/plugins/revenue/skills/outbound-prospecting/SKILL.md
+++ b/plugins/revenue/skills/outbound-prospecting/SKILL.md
@@ -56,6 +56,16 @@ Use a subdomain for outbound so a reputation problem cannot take down your trans
- **Replies, no meetings** — a qualification problem: you are reaching people who cannot act.
- **Meetings, no pipeline** — the segment is wrong.
+## Tooling
+
+Sequencing: Outreach, Salesloft, Apollo, Lemlist, Instantly, and similar.
+
+Contact data: ZoomInfo, Apollo, Clay, LinkedIn Sales Navigator, and similar. Every
+provider's data decays; verify before you send, whichever you buy.
+
+Deliverability: a separate sending domain, plus warmup and monitoring — Instantly,
+Smartlead, Google Postmaster Tools, and similar.
+
## Never
- Send before the list is qualified. A good message to the wrong person is still a bad message.
diff --git a/plugins/revenue/skills/revenue-operations/SKILL.md b/plugins/revenue/skills/revenue-operations/SKILL.md
index d856ba7..5d4ba1f 100644
--- a/plugins/revenue/skills/revenue-operations/SKILL.md
+++ b/plugins/revenue/skills/revenue-operations/SKILL.md
@@ -71,6 +71,16 @@ be unusable within two quarters.
Never require a field whose value is not used in a decision. Every unnecessary field trains sellers
to enter garbage in all of them.
+## Tooling
+
+CRM: Salesforce, HubSpot, Pipedrive, Zoho CRM, and similar. The CRM is the record for
+pipeline. Anything that disagrees with it is a report, not a number.
+
+Enrichment and routing: Clay, ZoomInfo, Apollo, Chili Piper, and similar.
+
+Forecasting and conversation data: Clari, Gong, and similar — useful once you have enough
+deals for a pattern to mean anything.
+
## Never
- Change a definition without restating history on the new one. A metric that moved because you redefined it is not a result.
diff --git a/plugins/security/skills/access-and-identity/SKILL.md b/plugins/security/skills/access-and-identity/SKILL.md
index 02f63ba..52e6ac6 100644
--- a/plugins/security/skills/access-and-identity/SKILL.md
+++ b/plugins/security/skills/access-and-identity/SKILL.md
@@ -65,6 +65,16 @@ Look for: permissions granted to individuals rather than roles, roles nobody can
administrative access, accounts whose owner has left, service credentials with no owner, and systems
outside SSO. Each is a specific fix, and the list is nearly always the same list.
+## Tooling
+
+Identity providers: Okta, Microsoft Entra ID, Google Workspace, JumpCloud, and similar.
+
+Privileged access and secrets: CyberArk, HashiCorp Vault, 1Password, Doppler, and similar.
+
+Access reviews and provisioning: Okta Identity Governance, Entra ID Governance, Lumos,
+ConductorOne, and similar. Worth buying at the point a manual quarterly review stops
+finishing rather than the point it gets tedious.
+
## Never
- Grant standing access where time-bound access would do the same job.
diff --git a/plugins/security/skills/security-architecture-review/SKILL.md b/plugins/security/skills/security-architecture-review/SKILL.md
index acfd52a..eebc24b 100644
--- a/plugins/security/skills/security-architecture-review/SKILL.md
+++ b/plugins/security/skills/security-architecture-review/SKILL.md
@@ -52,6 +52,10 @@ implements a comparison, a token, or a signature by hand.
- **DAST** and dependency scanning find different things; neither replaces review.
- **Secret scanning in CI and pre-commit** is the highest-value automation per unit of effort.
+By name today: Semgrep, CodeQL, or SonarQube for SAST; Snyk, Dependabot, or Trivy for
+dependencies; Burp Suite or OWASP ZAP for DAST; gitleaks, TruffleHog, or GitHub secret
+scanning for secrets — and similar in each category.
+
Automation is a floor, not a review. It finds known patterns, not design flaws — and design flaws
are what actually cause the expensive incidents.
diff --git a/plugins/security/skills/vulnerability-management/SKILL.md b/plugins/security/skills/vulnerability-management/SKILL.md
index 575c48d..7666c9c 100644
--- a/plugins/security/skills/vulnerability-management/SKILL.md
+++ b/plugins/security/skills/vulnerability-management/SKILL.md
@@ -67,6 +67,15 @@ good-faith reporter as an adversary is how a private report becomes a public one
Leadership needs: what is exposed and unfixed past SLA, the trend, and what needs a decision. Not
the count of findings, which mostly measures how much you scanned.
+## Tooling
+
+Infrastructure scanning: Tenable, Qualys, Rapid7 InsightVM, and similar. Code and
+dependencies: Snyk, Dependabot, GitHub Advanced Security, Semgrep, Trivy, and similar.
+Cloud posture: Wiz, Orca, Prisma Cloud, and similar.
+
+Exploitability context — the CISA KEV catalog, EPSS scores — decides what you fix first.
+The scanner only decides what you know about.
+
## Never
- Rank on CVSS alone. A score is not exploitability in your environment.
diff --git a/plugins/technology/skills/observability-and-reliability/SKILL.md b/plugins/technology/skills/observability-and-reliability/SKILL.md
index 5e853f4..2fde7bf 100644
--- a/plugins/technology/skills/observability-and-reliability/SKILL.md
+++ b/plugins/technology/skills/observability-and-reliability/SKILL.md
@@ -54,6 +54,16 @@ defect, and it is the part that repeats.
Produce a small number of real actions with owners and dates. A review generating fifteen actions
generates none.
+## Tooling
+
+Metrics and traces: Datadog, Grafana with Prometheus, New Relic, Honeycomb, and similar.
+Errors: Sentry, Rollbar, and similar. Logs: Elastic, OpenSearch, Loki, Splunk, and similar.
+
+On-call and incident management: PagerDuty, Opsgenie, incident.io, FireHydrant, and similar.
+
+Instrument with OpenTelemetry wherever you can. Vendor-specific instrumentation is the part
+that makes leaving expensive.
+
## Never
- Page a human for something they cannot act on.