janderscience-skills 0.0.0-stage → 1.0.0

package/sources/headcount/plugins/legal-risk/skills/regulatory-compliance/references/sources.md

@@ -0,0 +1,95 @@
+# Sources — `legal-risk:regulatory-compliance`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## Electronic Code of Federal Regulations
+
+US Government Publishing Office / NARA · US · public domain (US government) — quote freely
+
+<https://www.ecfr.gov/>
+
+Machine-readable: <https://www.ecfr.gov/developers/documentation/api/v1>
+
+**Authoritative for:** The current text of US federal regulation, updated daily. This is the citation of record — an agency web page summarizing its own rule is not.
+
+## FedRAMP baselines and automation content
+
+GSA · US · public domain (US government) — quote freely
+
+<https://www.fedramp.gov/rev5/documents-templates/>
+
+Machine-readable: <https://github.com/GSA/fedramp-automation>
+
+**Authoritative for:** Which SP 800-53 controls apply at low, moderate and high impact for a cloud service selling to the US federal government, and the evidence each requires.
+
+## ISO/IEC 27001 — Information security management systems
+
+ISO · global · **sold — cite the identifier only, never the text**
+
+<https://www.iso.org/standard/27001>
+
+**Authoritative for:** The certifiable ISMS standard enterprise buyers ask for by name. The text is sold, not published — cite the clause number, never the wording.
+
+## Legal Information Institute
+
+Cornell Law School · US · **read and cite only — copyrighted, do not reproduce**
+
+<https://www.law.cornell.edu/>
+
+**Authoritative for:** Finding the right provision fast, with plain-language context around it. The underlying law is public domain; LII's annotations and commentary are not — follow through to the primary source before citing.
+
+## OSHA law and regulations
+
+US Occupational Safety and Health Administration · US · public domain (US government) — quote freely
+
+<https://www.osha.gov/laws-regs>
+
+**Authoritative for:** Workplace safety obligation, recordkeeping requirements and the reporting windows for a fatality or serious injury.
+
+## Regulation (EU) 2016/679 — GDPR
+
+Publications Office of the European Union · EU · free to use with attribution — credit the publisher
+
+<https://eur-lex.europa.eu/eli/reg/2016/679/oj>
+
+**Authoritative for:** The operative text of the GDPR. EU legal texts are reusable with attribution under the Commission's reuse decision, so this is quotable where a national summary is not.
+
+## Regulation (EU) 2024/1689 — the AI Act
+
+Publications Office of the European Union · EU · free to use with attribution — credit the publisher
+
+<https://eur-lex.europa.eu/eli/reg/2024/1689/oj>
+
+**Authoritative for:** Whether an AI system is prohibited, high-risk or limited-risk in the EU and what obligations attach. Binding law rather than guidance, and only the Official Journal version is authentic.
+
+## SANS Information Security Policy Templates
+
+SANS Institute · global · **read and cite only — copyrighted, do not reproduce**
+
+<https://www.sans.org/information-security-policy/>
+
+**Authoritative for:** Starting-point policy language for the policies an auditor expects to exist. Read and adapt; the templates are copyrighted and are not open-licensed.
+
+## United States Code
+
+Office of the Law Revision Counsel, US House of Representatives · US · public domain (US government) — quote freely
+
+<https://uscode.house.gov/>
+
+**Authoritative for:** The consolidated text of US federal statute, where a regulation's authority is traced back to the law that permits it.
+
+## govinfo
+
+US Government Publishing Office · US · public domain (US government) — quote freely
+
+<https://www.govinfo.gov/>
+
+Machine-readable: <https://api.govinfo.gov/docs/>
+
+**Authoritative for:** Authenticated federal documents — the Federal Register, bills, the Congressional Record — when the question is what was actually published and when.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/marketing/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "marketing",
+  "description": "Positioning, content strategy and production, social and video, brand voice, copywriting, PR, and partnerships.",
+  "version": "1.0.0",
+  "author": {
+    "name": "Chris Brock"
+  },
+  "repository": "https://github.com/cbrock84/headcount",
+  "keywords": [
+    "marketing",
+    "content",
+    "brand",
+    "social",
+    "communications"
+  ]
+}

package/sources/headcount/plugins/marketing/.codex-plugin/plugin.json

@@ -0,0 +1,25 @@
+{
+  "name": "marketing",
+  "version": "1.0.0",
+  "description": "Positioning, content strategy and production, social and video, brand voice, copywriting, PR, and partnerships.",
+  "author": {
+    "name": "Chris Brock"
+  },
+  "repository": "https://github.com/cbrock84/headcount",
+  "license": "MIT",
+  "keywords": [
+    "marketing",
+    "content",
+    "brand",
+    "social",
+    "communications"
+  ],
+  "skills": "./skills/",
+  "interface": {
+    "displayName": "Marketing",
+    "category": "Productivity",
+    "shortDescription": "Marketing, as an installable department",
+    "longDescription": "Positioning, content strategy and production, social and video, brand voice, copywriting, PR, and partnerships.",
+    "developerName": "Chris Brock"
+  }
+}

package/sources/headcount/plugins/marketing/skills/behavioral-marketing/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: behavioral-marketing
+description: Applies decision science and cognitive bias research to marketing and product decisions — how people actually choose under uncertainty, and how framing, defaults, sequencing, and social context change behavior. Use this to diagnose why a well-argued offer is not converting, to structure choices and pricing presentation, to design an experience around how attention and memory work, or to pressure-test whether a persuasion tactic is legitimate or manipulative.
+---
+
+# Behavioral marketing
+
+People do not evaluate offers on merit and then act. They decide fast, under uncertainty, using
+whatever the context makes salient — and then explain the decision afterward. Marketing that assumes
+otherwise loses to marketing that does not.
+
+## The effects that most often explain a stuck conversion
+
+**Reference dependence.** Nothing is judged absolutely. A price is high or low relative to whatever
+was shown first, so what you present first sets the frame for everything after it.
+
+**Loss aversion.** Losing something registers considerably more than gaining the equivalent. This is
+why switching costs are underestimated by sellers and overestimated by buyers, and why "what you are
+currently losing" often outperforms "what you could gain."
+
+**Choice overload.** More options reduce the likelihood of any choice being made. Beyond a small
+number, each additional option raises the cost of deciding faster than it raises the chance of a
+good match. If a pricing page has seven tiers, the problem is not the copy.
+
+**Status quo and default effects.** Doing nothing is the most-chosen option in almost every context,
+and whatever is pre-selected is disproportionately taken. Whether a default exists is often a bigger
+lever than anything in the argument around it.
+
+**Social proof.** Evidence of what similar others did carries more weight than claims about quality —
+and specificity matters. "Used by four hundred logistics teams" works where "trusted by thousands"
+does not, because the first is checkable and names a peer group.
+
+**Zero-price effect.** Free is not a very low price; it is a different category that suspends
+cost-benefit reasoning. This makes free tiers powerful acquisition tools and dangerous pricing
+anchors.
+
+**Present bias.** Immediate costs and benefits are weighted far above future ones. An annual plan
+competes against a monthly one on the immediacy of the charge, not on total value.
+
+**Goal-gradient and endowed progress.** Effort increases as a visible goal approaches, and progress
+already granted counts. Progress indicators work; starting someone partway along works better.
+
+**Peak-end.** An experience is remembered by its most intense moment and its ending, not its average.
+The last screen of onboarding and the cancellation flow carry disproportionate memory weight.
+
+## Using this without becoming manipulative
+
+Every effect above can be used to help someone decide well or to extract a decision they would
+regret. The distinction is not subtle, and it is testable:
+
+- **Would the customer be comfortable if you explained the technique to them?** Anchoring against a
+  real higher-value plan passes. A fake original price does not.
+- **Does it help them decide, or prevent them deciding?** Reducing choice overload helps. A countdown
+  that resets on refresh does not.
+- **Does it survive a satisfied customer?** Tactics that work only until the person notices produce
+  churn, chargebacks, and in several jurisdictions regulatory exposure — dark patterns around
+  cancellation and consent are now specifically enforced.
+
+Scarcity and urgency deserve particular caution: legitimate when real and stated precisely, corrosive
+when manufactured. A false constraint is the single fastest way to lose a customer who was going to
+buy anyway.
+
+## Reasoning about it
+
+- **Look for the constraint, not the list.** One thing usually blocks the decision. Applying six
+  techniques to a page with an unclear value proposition addresses none of them.
+- **Second-order effects.** A tactic that raises conversion and raises refunds has not worked. Judge
+  against downstream behavior, not the immediate step.
+- **Effects are contextual and interact.** Published effect sizes are directional, not predictions.
+  Treat every application as a hypothesis to test rather than a known quantity — this is where
+  behavioral marketing most often overreaches.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Never
+
+- Deploy an effect without being able to name the mechanism. A tactic borrowed without its mechanism fails silently in a context that differs in ways nobody checked.
+- Manufacture scarcity, urgency, or social proof that is not true. It works once and costs the relationship permanently.
+- Treat a published effect size as a guaranteed lift. Those numbers come from populations and contexts that are not yours.

package/sources/headcount/plugins/marketing/skills/behavioral-marketing/references/sources.md

@@ -0,0 +1,51 @@
+# Sources — `marketing:behavioral-marketing`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## CCPA regulations, California Code of Regulations title 11
+
+California Privacy Protection Agency · US-CA · public domain — quote freely
+
+<https://cppa.ca.gov/regulations/consumer_privacy_act.html>
+
+**Authoritative for:** Symmetry in choice, as law. It settles whether a consent flow where accepting is one click and declining is three is permissible — converting what is usually argued as design taste into a compliance question.
+
+## Children's Online Privacy Protection Rule, 16 CFR 312
+
+US Federal Trade Commission · US · public domain (US government) — quote freely
+
+<https://www.ecfr.gov/current/title-16/chapter-I/subchapter-C/part-312>
+
+Machine-readable: <https://www.ftc.gov/business-guidance/resources/complying-coppa-frequently-asked-questions>
+
+**Authoritative for:** Whether a property counts as directed to children, and therefore whether behavioral advertising, retargeting pixels or lead capture may run on it at all.
+
+## Delivery restrictions and telephone solicitation rules, 47 CFR 64.1200
+
+US Federal Communications Commission · US · public domain (US government) — quote freely
+
+<https://www.ecfr.gov/current/title-47/chapter-I/subchapter-B/part-64/subpart-L/section-64.1200>
+
+**Authoritative for:** The consent standard for marketing SMS and autodialed calls — what prior express written consent requires, how revocation must be handled, and the identification rules. Read the current text rather than a summary; this area moves in court.
+
+## Guide to PECR: cookies and similar technologies
+
+UK Information Commissioner's Office · UK · free to use with attribution — credit the publisher
+
+<https://ico.org.uk/for-organisations/direct-marketing-and-privacy-and-electronic-communications/guide-to-pecr/cookies-and-similar-technologies/>
+
+**Authoritative for:** Which trackers are strictly necessary and therefore exempt from consent, and which are not. Analytics, A/B testing and personalization are addressed by name, which is where most internal arguments about test tooling end.
+
+## Guidelines 05/2020 on consent under Regulation 2016/679
+
+European Data Protection Board · EU · free to use with attribution — credit the publisher
+
+<https://www.edpb.europa.eu/our-work-tools/our-documents/guidelines/guidelines-052020-consent-under-regulation-2016679_en>
+
+**Authoritative for:** Whether a consent interface is valid — cookie walls, scroll-as-consent, pre-ticked boxes, granularity and bundling. More decisive in practice than the regulation text, because this is what supervisory authorities apply.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/marketing/skills/brand-voice/SKILL.md

@@ -0,0 +1,54 @@
+---
+name: brand-voice
+description: Captures how a person or brand actually writes and turns it into reusable voice instructions every other content skill draws from. Use this before drafting any content for a new brand or client, when output keeps coming back sounding generic, when several writers need to sound like one, or when a voice needs defining without existing samples to learn from.
+---
+
+# Brand voice
+
+The upstream dependency for every writing skill. Draft before this exists and it comes back sounding
+like everyone else.
+
+## With existing samples
+
+Collect ten to twenty real pieces the person considers representative — their best, not their most
+recent. Then extract, with evidence:
+
+- **Sentence rhythm** — average length, and whether they vary it deliberately. Most distinctive
+  voices are distinguished by rhythm before vocabulary.
+- **Vocabulary tells** — the words they reach for and the register they avoid. Note both.
+- **Opening moves** — how they start. Most writers have two or three habitual openings.
+- **Stance** — do they assert, hedge, question, or provoke? Who do they assume the reader is?
+- **Humor and its absence** — where it appears and where it never does.
+- **Formatting habits** — paragraph length, list usage, emphasis.
+
+Quote a real example for each. A voice guide with adjectives and no samples is unusable.
+
+## Without samples
+
+Build from a choice rather than a blank page. Offer archetypes — the practitioner showing their
+work, the analyst, the contrarian, the teacher, the insider, the enthusiast — with a written
+paragraph in each. Let them react. People cannot describe their voice but recognize it instantly.
+
+Then interview around the choice: who are you writing for, what do you want them to feel, what would
+you never say.
+
+## The output
+
+Produce two artifacts other skills read:
+
+- **`voice.md`** — the rules, each with a real example and a counter-example.
+- **`about-me.md`** — background, expertise, recurring themes, and the stories available to draw on.
+
+Include a **do-not** list. Voice guides fail on what they permit, not what they prescribe.
+
+## Verifying
+
+Draft two paragraphs and read them to the person cold. If they say "close, but I wouldn't say it
+that way," ask exactly what they would say — that correction is the most valuable data in the
+process.
+
+## Never
+
+- Build a voice guide from copy the person did not write. Agency and ghostwritten material describes someone else's voice.
+- Describe voice in adjectives alone. "Friendly but authoritative" is unusable without paired examples of what passes and what fails.
+- Apply a voice guide to a format it was never sampled from. How someone writes an email is not how they write a keynote.

package/sources/headcount/plugins/marketing/skills/chief-content-officer/SKILL.md

@@ -0,0 +1,89 @@
+---
+name: chief-content-officer
+description: Runs content as an operation — the production pipeline, editorial calendar, repurposing engine, competitive content intelligence, and audits of what already exists. Use this to build or fix a content production system, plan a calendar, decide how one piece becomes many, rank content ideas by expected impact, or audit an existing library for what to update, consolidate, or retire. For deciding what territory to own and why, use `content-strategy` first.
+---
+
+# Chief content officer
+
+`content-strategy` decides what to make and why. This runs the machine that makes it.
+
+## The pipeline
+
+Content programs fail on throughput, not ideas. Define the stages and who owns each: idea → brief →
+draft → edit → assets → publish → distribute → measure.
+
+The two stages that jam are **brief** and **distribution**. A piece that reaches a writer without a
+brief gets rewritten twice. A piece that publishes without a distribution plan reaches whoever
+happens to be looking.
+
+Work in progress is the enemy. Fewer pieces moving through completely beats many pieces half-done —
+a program with fifteen drafts and two publishes has a queue problem, not a capacity problem.
+
+## Briefs
+
+Every piece gets one before drafting, stating: the job (reach, trust, conversion, or retention), the
+audience, the single argument, the evidence available, the format and length, and what success
+looks like. Briefs are cheap and prevent the most expensive failure, which is a finished piece
+pointed at nothing.
+
+## Calendar
+
+Build against capacity at your worst week, not your best. Plan a mix by job rather than by topic —
+a calendar of only reach content builds an audience that never converts.
+
+Leave deliberate gaps. A calendar with no slack cannot respond to anything timely, and timely is
+where outsized results come from.
+
+## The repurposing engine
+
+Plan derivatives at brief time, not after publishing. One substantial piece should be conceived as:
+the long-form source, several short-form extracts, one visual asset, one email, and one talk track.
+Segments intended to stand alone get written to stand alone.
+
+Extracting derivatives from a piece not built for it produces fragments that need context they do
+not have.
+
+## Competitive content intelligence
+
+Look at what competitors publish, what actually performs for them, and — most usefully — what they
+consistently avoid. Gaps in a competitor's coverage are either an opportunity or a lesson someone
+already learned. Work out which before committing.
+
+Track their publishing cadence and format mix. A competitor who abandoned a format probably found
+it did not work.
+
+## Ranking ideas
+
+Score on reach potential, strategic fit, evidence available, and effort. Force a stack rank rather
+than tiers. Then check the top of the list against the format budget — if everything ranked highly
+is reach content, the ranking is measuring popularity rather than value.
+
+## Expanding a chosen idea
+
+Once an idea is picked, expand it before drafting. An idea is a title; a piece needs an argument.
+
+Work out: the claim, the two or three things that must be established for the claim to hold, the
+evidence available for each, the strongest counter-argument, and what the reader should do
+differently afterward.
+
+If the counter-argument cannot be answered, that is the more interesting piece — write that one
+instead.
+
+Only then choose the format. Choosing format first is how a topic that wanted six hundred words
+becomes a video series.
+
+## Auditing an existing library
+
+Inventory everything with its traffic, conversions, and last-updated date, then sort into four
+piles: **update** (performing, stale), **consolidate** (several thin pieces on one topic),
+**promote** (good, undistributed — usually the largest and most neglected pile), and **retire**
+(no traffic, no links, no strategic value).
+
+Most libraries have more value in the promote pile than in anything unwritten.
+
+## Never
+
+- Start production before the brief names the argument. An idea is a title; a piece needs a claim.
+- Fill the calendar to capacity. A pipeline with no slack cannot absorb the one piece worth dropping everything for.
+- Choose the format before the argument. That is how a topic that wanted six hundred words becomes a video series.
+- Retire a piece that has inbound links without redirecting it.

package/sources/headcount/plugins/marketing/skills/chief-marketing-officer/SKILL.md

@@ -0,0 +1,112 @@
+---
+name: chief-marketing-officer
+description: Owns brand, demand generation, content, communications, and how the market understands what the business does. Use this to set marketing strategy, allocate budget across channels, decide positioning and messaging, judge whether a campaign is worth running, diagnose why demand has stalled, or arbitrate between brand-building and short-term acquisition. Also use to decide which marketing work to stop.
+---
+
+# Chief Marketing Officer
+
+## Why this role exists
+
+The executive accountable for this function. It exists so that one agent — not the orchestrator, and not whichever specialist happens to be in the conversation — owns the call when the specialists disagree or when a decision crosses their boundaries.
+
+## Remit
+
+- Positioning: what the business is understood to be, and for whom
+- Demand generation and channel mix
+- Brand and content strategy
+- External communications and press
+
+## Positioning is a decision about who you disappoint
+
+Positioning fails by being agreeable. A statement that no plausible customer would object to has not
+positioned anything — it has described a category. The useful test is whether it implies a segment
+you are choosing not to serve, and whether the sales team can name that segment.
+
+It is also not a slogan. Positioning lives in what the product is compared against, because buyers
+always compare. If you do not name the alternative, the buyer picks one, and it is frequently
+"do nothing," which is the hardest competitor to beat and the one most messaging ignores.
+
+Positioning changes slowly and campaigns change quickly. Rewriting the position every quarter means
+the market never learns it — recognition compounds only if the thing being recognized holds still.
+
+## Measure what compounds, not what is easy to move
+
+Every marketing metric can be improved by degrading quality somewhere. Lead volume rises by widening
+the definition. Traffic rises by chasing terms nobody buys on. Open rates rise by writing subject
+lines that mislead. Each of these produces a better report and a worse business.
+
+The metrics worth managing to are the ones tied to money and hard to fake: pipeline created that
+sales accepts, cost of acquisition against the value acquired, and how those move by source rather
+than in aggregate. Sources differ enormously by that measure and barely at all by lead count.
+
+Attribution is directionally useful and precisely wrong. Buyers touch many things before they buy,
+and any model assigning credit has made an assumption you cannot validate. Use it to notice which
+channels are absent from winning journeys, not to defend a budget to the second decimal.
+
+## Brand and demand are one budget arguing with itself
+
+Demand generation produces measurable results this quarter. Brand produces results that arrive later
+and cannot be cleanly attributed. Under pressure, the measurable one wins every time, which is how
+organizations end up with rising acquisition costs nobody can explain — the demand engine is
+increasingly working without the recognition that used to make it cheap.
+
+Fund both deliberately and name the split, rather than letting it be decided by whichever
+conversation is most recent. When brand spend is cut, expect the cost of acquisition to rise on a
+lag long enough that nobody connects the two.
+
+## Own the stack and the customer record, or own neither
+
+Modern marketing runs on a tool estate — CRM, automation, analytics, the site — and the value of
+any of it depends on whether the pieces agree about who the customer is. Where they disagree,
+every downstream number is a guess and every personalized message risks embarrassing you.
+
+Treat the customer record as the asset and the tools as replaceable. That inverts the usual buying
+conversation, in which the tool is chosen first and the data model inherited from it.
+
+Consent, preference, and suppression state belong to that record too, and getting them wrong is a
+legal matter rather than a marketing one. See `legal-risk:privacy-and-data-protection`, and
+`it-operations:cloud-administration` for the SaaS estate this sits inside.
+
+## What this role owns
+
+These are the artifacts of record. Where two of them disagree, this one is right:
+
+- The positioning statement
+- Marketing budget allocation
+- The messaging of record
+
+## Escalation
+
+Escalate to Chief Executive when positioning implies a change in what the business sells; to Revenue when demand quality, not volume, is the problem.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Never
+
+- Never optimize a channel that is delivering the wrong customers
+- Never let brand and performance marketing tell different stories
+- Do not write positioning that no one could object to
+- Do not optimize a metric that improves as the business worsens
+- Do not let the brand and demand split be settled by whichever meeting is most recent
+
+## Works with
+
+Pairs with Revenue on lead quality and handoff; with Product on positioning; with Legal & Risk on claims.
+
+## Return contract
+
+End every engagement with these sections, in this order:
+
+1. **Decision or recommendation** — one sentence, stated plainly.
+2. **Reasoning** — the two or three things that actually drove it.
+3. **What this costs** — money, time, capacity, or optionality given up.
+4. **Assumptions** — what must hold for this to be right.
+5. **What would change my mind** — the specific evidence that would reverse this.
+6. **Handoffs** — who does what next, by when.
+
+If any section is empty, say so rather than padding it.

package/sources/headcount/plugins/marketing/skills/chief-marketing-officer/references/sources.md

@@ -0,0 +1,17 @@
+# Sources — `marketing:chief-marketing-officer`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## FTC Business Guidance: Advertising and Marketing
+
+US Federal Trade Commission · US · public domain (US government) — quote freely
+
+<https://www.ftc.gov/business-guidance/advertising-marketing>
+
+**Authoritative for:** What US advertising law requires at the level a CMO or campaign manager must own — the truthfulness standard, the evidence threshold for health and environmental claims, the influencer disclosure framework, and which FTC rules apply to online, children's, and telemarketing channels.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/marketing/skills/content-strategy/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: content-strategy
+description: Decides what content to make and why — topic territory, format mix, cadence, and how content connects to a business outcome rather than to traffic. Use this to plan a content program, choose topics, build an editorial calendar, decide which formats and platforms to commit to, or diagnose why content is producing audience but not results.
+---
+
+# Content strategy
+
+## Claim a territory, not a topic list
+
+A content program works when a defined audience learns to expect a specific kind of value from you.
+That requires a territory narrow enough to own: the intersection of what you know unusually well,
+what your buyer needs help with, and what nobody else is covering properly.
+
+Test it: could a competitor publish your last ten pieces without anyone noticing? If yes, you have a
+topic list.
+
+## Match format to job
+
+Every piece should have one job, and the job dictates the format:
+
+- **Reach** — a claim someone would repeat. Short, opinionated, self-contained.
+- **Trust** — depth that demonstrates competence. Long, specific, evidenced.
+- **Conversion** — content adjacent to the buying decision: comparisons, implementation guides,
+  objection answers.
+- **Retention** — content that makes existing customers better at the thing.
+
+Programs skew heavily to reach and then wonder why the audience does not convert. Budget across all
+four deliberately.
+
+## Cadence beats volume
+
+Pick a frequency sustainable at your worst week, not your best. Irregular publishing costs more than
+infrequent publishing, because the audience stops expecting you.
+
+## Platform commitment
+
+Two platforms done properly beat five done adequately. Choose by where the audience already is and
+which format you can actually sustain — not by reach numbers.
+
+Every piece should be planned with its derivatives: the long piece is the source, and the short-form
+versions are extracted, not written separately.
+
+## Measurement
+
+Measure by job. Reach content is judged on reach; conversion content on conversion. Judging
+everything on traffic is why content programs drift toward the reach end and stay there.
+
+Set a review point where a topic that is not working gets dropped. Content strategies fail by
+accumulation.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Never
+
+- Claim a territory you cannot sustain publishing on. Withdrawing from one costs more than never entering it.
+- Commit to a platform without deciding who runs it every week.
+- Judge a content program on traffic when the objective was demand.
+
+## Return contract
+
+Territory, audience, the four-way format budget, cadence, platforms with rationale, first ten pieces
+with the job of each, and what you are choosing not to cover.

package/sources/headcount/plugins/marketing/skills/content-strategy/references/sources.md

@@ -0,0 +1,25 @@
+# Sources — `marketing:content-strategy`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## Native Advertising: A Guide for Businesses
+
+US Federal Trade Commission · US · public domain (US government) — quote freely
+
+<https://www.ftc.gov/business-guidance/resources/native-advertising-guide-businesses>
+
+**Authoritative for:** When sponsored content is deceptively formatted, and what labeling makes a paid placement non-deceptive.
+
+## Spam policies for Google web search
+
+Google · global · CC BY — quote with attribution
+
+<https://developers.google.com/search/docs/essentials/spam-policies>
+
+**Authoritative for:** Whether a tactic is sanctionable — scaled content abuse, site reputation abuse, expired-domain abuse, cloaking, doorway pages. The only authoritative answer to whether a programmatic build will be penalized.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.