skilldrop-cli 0.13.2 → 0.13.4

package/{skills → packs/core/skills}/council-review/reference.md

@@ -68,9 +68,9 @@ When two seats genuinely converge, that's a *stronger* signal — present it as
 ## Relationship to the single-voice skills
 
 The council is heavier than the focused reviewers — use it when the multi-disciplinary tension is the point, not as a default. Rules of thumb:
-- One adversarial pass on just-written code → [`devils-advocate`](../devils-advocate/SKILL.md).
+- One adversarial pass on just-written code → [`devils-advocate`](../../../dev-team/skills/devils-advocate/SKILL.md).
 - One rubric pass on a doc → [`doc-critique`](../doc-critique/SKILL.md).
-- Score named options on weighted criteria → [`tech-comparison-matrix`](../tech-comparison-matrix/SKILL.md).
+- Score named options on weighted criteria → [`tech-comparison-matrix`](../../../solution-architect/skills/tech-comparison-matrix/SKILL.md).
 - A decision/design/change where security, ops, maintainability, delivery, and correctness pull in different directions → **council-review**.
 
 Don't chain these internally (per the repo's no-internal-chaining rule). A human runs the council, then hands a specific finding to `devils-advocate` if they want it drilled.

package/{loops → packs/dev-team/loops}/build/LOOP.md

@@ -16,7 +16,7 @@ one. Every skill named below stays independently installable and runnable on its
 | 1 | `shape` | generate | [`user-story-splitter`](../../skills/user-story-splitter/SKILL.md), [`bug-triage`](../../skills/bug-triage/SKILL.md) | — |
 | 2 | `implement` | generate | [`feature-implement-loop`](../../skills/feature-implement-loop/SKILL.md) | — |
 | 3 | `verify` | verify | [`pre-merge-review`](../../skills/pre-merge-review/SKILL.md) | **G2** mechanical |
-| 4 | `decide` | gate | [`council-review`](../../skills/council-review/SKILL.md) | **G2.1** human |
+| 4 | `decide` | gate | [`council-review`](../../../core/skills/council-review/SKILL.md) | **G2.1** human |
 
 ## How to run this loop
 
@@ -27,7 +27,7 @@ one. Every skill named below stays independently installable and runnable on its
    generate-challenge-gate cycle internally. Do not re-implement its rounds here — this loop's
    `cap` governs returns from G2, not the inner skill's rounds.
 3. **Verify at G2.** Run `pre-merge-review`. Its script decides and its panel explains:
-   `python3 skills/pre-merge-review/scripts/gate.py`. The exit code is the verdict —
+   `python3 packs/dev-team/skills/pre-merge-review/scripts/gate.py`. The exit code is the verdict —
    `READY`, `NOT READY`, or `BLOCKED`.
 4. **Honour the gate.** `NOT READY` returns to `implement`, up to `cap` (3) times. On the
    third return, stop looping and emit `BLOCKED` naming what did not converge. Never edit the
@@ -38,7 +38,7 @@ one. Every skill named below stays independently installable and runnable on its
 
 ## Verdicts
 
-Defined in [`contracts/terminals.json`](../../contracts/terminals.json). G2 emits
+Defined in [`contracts/terminals.json`](../../../../contracts/terminals.json). G2 emits
 `READY` / `NOT READY` / `BLOCKED`. G2.1 emits the council vocabulary. A `revise`-class verdict
 returns to the stage named in `revise_to`; a `redirect`-class verdict leaves the loop.
 

package/{loops → packs/dev-team/loops}/build/loop.json

@@ -27,7 +27,7 @@
       "gate": {
         "id": "G2",
         "kind": "mechanical",
-        "script": "skills/pre-merge-review/scripts/gate.py",
+        "script": "packs/dev-team/skills/pre-merge-review/scripts/gate.py",
         "verdicts": ["READY", "NOT READY", "BLOCKED"],
         "revise_to": "implement"
       }

package/{loops → packs/dev-team/loops}/release/LOOP.md

@@ -17,7 +17,7 @@ being folded into either neighbour.
 | 1 | `plan` | generate | [`migration-plan`](../../skills/migration-plan/SKILL.md) | — |
 | 2 | `ready` | verify | [`launch-readiness`](../../skills/launch-readiness/SKILL.md) | **G2.5** review |
 | 3 | `announce` | generate | [`release-notes`](../../skills/release-notes/SKILL.md) | — |
-| 4 | `go` | gate | [`council-review`](../../skills/council-review/SKILL.md) | **G2.6** human |
+| 4 | `go` | gate | [`council-review`](../../../core/skills/council-review/SKILL.md) | **G2.6** human |
 
 ## How to run this loop
 
@@ -42,7 +42,7 @@ After `PROCEED`, the change is live and the work moves to `operate`. Gaps that G
 
 ## Verdicts
 
-Defined in [`contracts/terminals.json`](../../contracts/terminals.json). G2.5 emits `PROCEED`,
+Defined in [`contracts/terminals.json`](../../../../contracts/terminals.json). G2.5 emits `PROCEED`,
 `PROCEED WITH CONDITIONS`, `REVISE` or `BLOCKED`. G2.6 adds `RECONSIDER`. `PROCEED WITH
 CONDITIONS` at G2.5 is allowed only when the open rows are comms or exposure. A detection or
 response gap is always `REVISE`.

package/packs/dev-team/pack.json

@@ -0,0 +1,22 @@
+{
+  "description": "Build-and-ship: story splitting, implementation with adversarial review, test plans, triage, migrations, launch readiness, release notes, agent-policy files, and code-quality gates.",
+  "display_name": "Dev team",
+  "keywords": ["review", "merge", "testing", "release", "code-quality"],
+  "links": {
+    "documentation": "https://sananthanarayan.github.io/skilldrop/packs/dev-team/"
+  },
+  "maintainers": [
+    {
+      "name": "sananthanarayan"
+    }
+  ],
+  "first-value": {
+    "audience-posture": "technical",
+    "prerequisites": ["A git repository with changes on a branch", "The reviewer subagents, for the full panel: `skilldrop install --panel review` (the Claude plugin includes them)"],
+    "starter-task": "Find out whether your current branch is safe to merge",
+    "starter-prompt": "Is this branch safe to merge? Run a pre-merge review on the current diff.",
+    "verification": "pre-merge-review runs the project's lint, typecheck and tests through its gate script, then the reviewer panel, and ends with READY or NOT READY.",
+    "recovery": "If the gate script cannot find your lint or test commands, tell it what they are. If the panel is skipped, install the reviewer subagents with `skilldrop install --panel review`."
+  },
+  "requires": ["core"]
+}

package/{skills → packs/dev-team/skills}/agents-md-generator/reference.md

@@ -2,7 +2,7 @@
 
 ## Who reads what
 
-Confirmed in the July 2026 survey ([`docs/designs/ide-primitive-coverage.md`](../../docs/designs/ide-primitive-coverage.md)). A root `AGENTS.md` is the broadest single file; satellites are a reach fix for specific tools, not the norm.
+Confirmed in the July 2026 survey ([`docs/designs/ide-primitive-coverage.md`](../../../../docs/designs/ide-primitive-coverage.md)). A root `AGENTS.md` is the broadest single file; satellites are a reach fix for specific tools, not the norm.
 
 | Tool | Reads |
 |---|---|

package/{skills → packs/dev-team/skills}/contribution-wizard/SKILL.md

@@ -94,12 +94,12 @@ Eight eval cases covering: 2 happy-path, 2 minimal/edge input, 2 anti-pattern (t
 One row for the skill table, matching the format of existing rows:
 
 ```
-| [`<skill-name>`](skills/<skill-name>/SKILL.md) | <One sentence describing what the skill does and the output it produces.> |
+| [`<skill-name>`](packs/<pack>/skills/<skill-name>/SKILL.md) | <One sentence describing what the skill does and the output it produces.> |
 ```
 
-#### `packs.json` addition
+#### Pack and outcome
 
-State which pack to add the skill to and the exact line to add to the skills array.
+State which one pack the skill belongs in (`core` only if every role needs it) — its folder goes at `packs/<pack>/skills/<skill-name>/` — and which `outcomes` entry in `catalogue.json` to add it to.
 
 ### Step 3 — Install check reminder
 
@@ -107,11 +107,11 @@ After generating, tell the author:
 
 ```
 Next steps:
-1. mkdir skills/<skill-name> && cd skills/<skill-name>
+1. mkdir -p packs/<pack>/skills/<skill-name> && cd packs/<pack>/skills/<skill-name>
 2. Drop in manifest.json, SKILL.md, and evals/cases.json
 3. python3 validate.py    # must pass before opening a PR
 4. Add the README row to the correct section
-5. Add the skill to packs.json under the right pack
+5. Add the skill to an outcome in catalogue.json
 6. If the skill has a how-to guide, add it to guides/how-to/ and guides/README.md
 ```
 

package/{skills → packs/dev-team/skills}/contribution-wizard/manifest.json

@@ -1,6 +1,6 @@
 {
   "name": "contribution-wizard",
-  "version": "1.0.0",
+  "version": "1.0.1",
   "description": "Guides an author through creating a new skilldrop skill from scratch — generates the manifest, SKILL.md, eval cases, and README entry from a plain-language description of the skill's purpose. Use when authoring a new skill for this repo or a private fork, ensuring a new skill meets the schema and validation requirements before submission.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },

package/{skills → packs/dev-team/skills}/devils-advocate/SKILL.md

@@ -7,7 +7,7 @@ description: Adversarial review of just-generated code, run *after* an agent (or
 
 You play the role of a **senior engineer in code review who is trying to find what the implementation missed**. Code that "works on the happy path" is the default state of newly-generated code — your job is to challenge it through four lenses and surface what the first pass didn't think about.
 
-This skill is the **code counterpart to [`doc-critique`](../doc-critique/SKILL.md)** — same adversarial framing, applied to code instead of artifacts.
+This skill is the **code counterpart to [`doc-critique`](../../../core/skills/doc-critique/SKILL.md)** — same adversarial framing, applied to code instead of artifacts.
 
 ## When this skill runs
 

package/{skills → packs/dev-team/skills}/pre-merge-review/SKILL.md

@@ -29,7 +29,7 @@ Two gates, and they are different kinds. The mechanical gate is **not a judgment
    - **`NOT READY`** — the gate is RED, **or** any blocker/major stands. List every blocking item (gate failures first, then blocker/major findings) and what must change. 🟨 minor / ⚪ nit are listed but never block.
    - **`BLOCKED`** — the gate couldn't run (unknown commands, no test setup). Name what's missing.
 
-5. **Escalate design disagreements — don't adjudicate them.** If the panel surfaces a genuine *tradeoff* dispute (not a bug — "should this be a queue or a cron?"), the verdict still gates on gate+blocker/major, but **offer [`council-review`](../council-review/SKILL.md)** for the open decision rather than settling a design debate here.
+5. **Escalate design disagreements — don't adjudicate them.** If the panel surfaces a genuine *tradeoff* dispute (not a bug — "should this be a queue or a cron?"), the verdict still gates on gate+blocker/major, but **offer [`council-review`](../../../core/skills/council-review/SKILL.md)** for the open decision rather than settling a design debate here.
 
 6. **Report.** Lead with the verdict. Then: the gate results table (command → PASS/FAIL), the merged panel findings by severity, and a **must-fix** list for `NOT READY`.
 

package/{loops → packs/product-manager/loops}/discover/LOOP.md

@@ -14,9 +14,9 @@ script: no check can tell you that you solved the wrong problem well.
 | # | Stage | Type | Skills | Gate |
 |---|---|---|---|---|
 | 1 | `gather` | generate | [`requirements-interview`](../../skills/requirements-interview/SKILL.md), [`user-journey-map`](../../skills/user-journey-map/SKILL.md), [`strategy-analysis`](../../skills/strategy-analysis/SKILL.md) | — |
-| 2 | `structure` | generate | [`brief-intake`](../../skills/brief-intake/SKILL.md) | — |
+| 2 | `structure` | generate | [`brief-intake`](../../../core/skills/brief-intake/SKILL.md) | — |
 | 3 | `specify` | generate | [`prd-draft`](../../skills/prd-draft/SKILL.md) | — |
-| 4 | `ratify` | gate | [`doc-critique`](../../skills/doc-critique/SKILL.md) | **G0** human |
+| 4 | `ratify` | gate | [`doc-critique`](../../../core/skills/doc-critique/SKILL.md) | **G0** human |
 
 ## How to run this loop
 
@@ -36,7 +36,7 @@ script: no check can tell you that you solved the wrong problem well.
 
 ## Verdicts
 
-Defined in [`contracts/terminals.json`](../../contracts/terminals.json). G0 emits `PROCEED`,
+Defined in [`contracts/terminals.json`](../../../../contracts/terminals.json). G0 emits `PROCEED`,
 `PROCEED WITH CONDITIONS`, `REVISE`, `RECONSIDER`, or `BLOCKED`. `RECONSIDER` leaves the loop:
 the problem itself is wrong, and no amount of re-briefing fixes that.
 

package/packs/product-manager/pack.json

@@ -0,0 +1,22 @@
+{
+  "description": "Direction to requirements: PR/FAQs, strategy frameworks, OKRs, business cases, interviews, PRDs, journey maps, and success measurement.",
+  "display_name": "Product manager",
+  "keywords": ["prfaq", "prd", "strategy", "okr", "discovery"],
+  "links": {
+    "documentation": "https://sananthanarayan.github.io/skilldrop/packs/product-manager/"
+  },
+  "maintainers": [
+    {
+      "name": "sananthanarayan"
+    }
+  ],
+  "first-value": {
+    "audience-posture": "non-technical",
+    "prerequisites": [],
+    "starter-task": "Pressure-test a product idea before anyone builds it",
+    "starter-prompt": "Write a PR/FAQ for a feature that lets customers pause their subscription for up to three months instead of cancelling.",
+    "verification": "prfaq returns a launch press release, a customer FAQ and an internal FAQ that names the hard questions.",
+    "recovery": "If prfaq does not activate, ask for it by name (\"use prfaq\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
+  },
+  "requires": ["core"]
+}

package/{loops → packs/solution-architect/loops}/design/LOOP.md

@@ -17,7 +17,7 @@ a script, and why the decision is recorded only *after* the panel agrees.
 | 1 | `constrain` | generate | [`nfr-spec`](../../skills/nfr-spec/SKILL.md) | — |
 | 2 | `shape` | generate | [`design-doc`](../../skills/design-doc/SKILL.md), [`architecture-diagrams`](../../skills/architecture-diagrams/SKILL.md) | — |
 | 3 | `threat` | verify | [`threat-model`](../../skills/threat-model/SKILL.md) | — |
-| 4 | `ratify` | gate | [`council-review`](../../skills/council-review/SKILL.md) | **G1** review |
+| 4 | `ratify` | gate | [`council-review`](../../../core/skills/council-review/SKILL.md) | **G1** review |
 | 5 | `record` | generate | [`adr-generator`](../../skills/adr-generator/SKILL.md) | — |
 
 ## How to run this loop
@@ -37,7 +37,7 @@ a script, and why the decision is recorded only *after* the panel agrees.
 
 ## Verdicts
 
-Defined in [`contracts/terminals.json`](../../contracts/terminals.json). `PROCEED WITH
+Defined in [`contracts/terminals.json`](../../../../contracts/terminals.json). `PROCEED WITH
 CONDITIONS` is the common outcome and the most abused: the conditions are part of the
 decision, and `record` must carry them into the ADR.
 

package/packs/solution-architect/pack.json

@@ -0,0 +1,22 @@
+{
+  "description": "Design-phase artifacts: diagrams, decision records, design docs, contracts, schemas, threat models, and the reviews that gate them.",
+  "display_name": "Solution architect",
+  "keywords": ["architecture", "adr", "design-doc", "threat-model", "diagrams"],
+  "links": {
+    "documentation": "https://sananthanarayan.github.io/skilldrop/packs/solution-architect/"
+  },
+  "maintainers": [
+    {
+      "name": "sananthanarayan"
+    }
+  ],
+  "first-value": {
+    "audience-posture": "technical",
+    "prerequisites": [],
+    "starter-task": "Record an architecture decision your team already made",
+    "starter-prompt": "Write an ADR: we're moving our session store from Redis to DynamoDB. We considered staying on Redis, DynamoDB, and Postgres; we chose DynamoDB for managed scaling and lower ops load.",
+    "verification": "adr-generator returns an ADR with context, the options considered with their trade-offs, the decision, and its consequences.",
+    "recovery": "If adr-generator does not activate, ask for it by name (\"use adr-generator\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
+  },
+  "requires": ["core"]
+}

package/{loops → packs/sre-oncall/loops}/operate/LOOP.md

@@ -38,7 +38,7 @@ starts at `instrument`. Do not replay earlier stages for their own sake.
 
 ## Verdicts
 
-Defined in [`contracts/terminals.json`](../../contracts/terminals.json). G3 emits `PROCEED`,
+Defined in [`contracts/terminals.json`](../../../../contracts/terminals.json). G3 emits `PROCEED`,
 `PROCEED WITH CONDITIONS`, `REVISE`, or `BLOCKED`. `PROCEED WITH CONDITIONS` means the
 incident is closed but named follow-ups are outstanding — they travel with the postmortem.
 

package/packs/sre-oncall/pack.json

@@ -0,0 +1,22 @@
+{
+  "description": "Operate the service: runbooks, observability design, incident communications, postmortems, and capacity/cost models.",
+  "display_name": "SRE / on-call",
+  "keywords": ["runbook", "incident", "postmortem", "observability", "slo"],
+  "links": {
+    "documentation": "https://sananthanarayan.github.io/skilldrop/packs/sre-oncall/"
+  },
+  "maintainers": [
+    {
+      "name": "sananthanarayan"
+    }
+  ],
+  "first-value": {
+    "audience-posture": "technical",
+    "prerequisites": [],
+    "starter-task": "Write the runbook an on-call engineer can follow at 3am",
+    "starter-prompt": "Write a runbook for our payments-api service: it runs in the Kubernetes namespace payments, depends on Postgres and Stripe, and pages the payments on-call rotation.",
+    "verification": "runbook-generator returns a runbook with rollback commands, the common incidents and what to do for each, and an escalation path. Facts you did not give it are marked missing, not invented.",
+    "recovery": "If runbook-generator does not activate, ask for it by name (\"use runbook-generator\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
+  },
+  "requires": ["core"]
+}

package/packs/stakeholder-comms/pack.json

@@ -0,0 +1,22 @@
+{
+  "description": "Non-technical audiences: audience profiling, deck outlines and real .pptx decks, exec summaries, decision logs, and guides.",
+  "display_name": "Stakeholder comms",
+  "keywords": ["exec-summary", "deck", "audience", "decision-log"],
+  "links": {
+    "documentation": "https://sananthanarayan.github.io/skilldrop/packs/stakeholder-comms/"
+  },
+  "maintainers": [
+    {
+      "name": "sananthanarayan"
+    }
+  ],
+  "first-value": {
+    "audience-posture": "non-technical",
+    "prerequisites": [],
+    "starter-task": "Turn a long document into a one-page summary for leadership",
+    "starter-prompt": "Turn this design doc into a one-page executive summary for our steering committee: <paste the doc>.",
+    "verification": "exec-summary returns a one-page summary that a time-poor reader can act on in 30 seconds, written without jargon.",
+    "recovery": "If exec-summary does not activate, ask for it by name (\"use exec-summary\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
+  },
+  "requires": ["core"]
+}

package/{skills → packs/stakeholder-comms/skills}/deck-builder/SKILL.md

@@ -144,7 +144,7 @@ A generated deck is a strong first draft. Always tell the user to:
 - Review the speaker notes — the agent wrote them, and they get read aloud
 - Replace any placeholder box with the real diagram
 - Do one audience pass: read every slide title in order, does the *narrative* land for that audience?
-- Run [`doc-critique`](../doc-critique/SKILL.md) against the deck rubric before it goes out
+- Run [`doc-critique`](../../../core/skills/doc-critique/SKILL.md) against the deck rubric before it goes out
 
 ## Useful references
 

package/profiles.json

@@ -0,0 +1,24 @@
+{
+  "$comment": "Named install presets — one command installs a bundle of packs, agents, and loops. A profile is an install recipe, not a skill: nothing moves into profiles/, and a skill can belong to any number of profiles. validate.py enforces that every pack, agent, and loop named here exists. Rationale: docs/rfcs/ (RFC to be written). A role pack already brings `core` through `requires` (RFC-0033), so profiles never need to list it beside one.",
+  "version": "0.1.0",
+  "profiles": {
+    "starter": {
+      "description": "Everything a new team member needs on day one: the dev-team pack plus the review panel that gates it.",
+      "packs": ["dev-team"],
+      "agents": ["devils-advocate", "security-reviewer", "code-quality"],
+      "loops": ["build"]
+    },
+    "architect": {
+      "description": "Design-phase setup: the solution-architect pack and the loops that run it end to end.",
+      "packs": ["solution-architect"],
+      "agents": [],
+      "loops": ["design", "ship-a-draft"]
+    },
+    "full": {
+      "description": "The complete catalogue: every pack, every reviewer agent, every loop.",
+      "packs": ["core", "solution-architect", "product-manager", "dev-team", "sre-oncall", "stakeholder-comms", "ai-engineering", "claude-api"],
+      "agents": ["devils-advocate", "security-reviewer", "code-quality"],
+      "loops": ["discover", "design", "build", "release", "operate", "ship-a-draft"]
+    }
+  }
+}

package/packs.json

@@ -1,229 +0,0 @@
-{
-  "$comment": "Virtual skill packs — role-based bundles for one-command install. Packs are METADATA ONLY: skills stay in flat skills/<name> folders (golden rule: skills are discovered by path), every skill and every loop belongs to exactly one pack (RFC-0033 — the shape a later physical packs/<name>/ layout needs), and a pack may `requires` the `core` pack, which every installer then installs with it. validate.py enforces all of this. Install a pack with `python3 pack.py <pack> --install`; see README. Rationale: docs/rfcs/0001-skill-packs.md. `outcomes` (RFC-0026) is the second browse axis: packs say WHO needs a skill, outcomes say WHY someone opens the catalogue. It is the README's nine categories restated as seven outcomes and made machine-readable so the site cannot drift from them. Outcomes are a browse aid only — not an install unit — and validate.py enforces the same two-way check packs get.",
-  "version": "0.2.0",
-  "packs": {
-    "core": {
-      "description": "The cross-role toolkit every pack builds on: structured intake, document critique, the review council, and output hygiene, plus the ship-a-draft wrapper. Installed automatically with every role pack.",
-      "loops": ["ship-a-draft"],
-      "skills": [
-        "brief-intake",
-        "doc-critique",
-        "output-hygiene",
-        "council-review"
-      ]
-    },
-    "solution-architect": {
-      "description": "Design-phase artifacts: diagrams, decision records, design docs, contracts, schemas, threat models, and the reviews that gate them.",
-      "requires": ["core"],
-      "loops": ["design"],
-      "skills": [
-        "architecture-diagrams",
-        "reverse-architecture",
-        "figma-diagrams",
-        "adr-generator",
-        "design-doc",
-        "tech-comparison-matrix",
-        "threat-model",
-        "api-contract-draft",
-        "data-contract",
-        "db-schema-design",
-        "nfr-spec"
-      ]
-    },
-    "product-manager": {
-      "description": "Direction to requirements: PR/FAQs, strategy frameworks, OKRs, business cases, interviews, PRDs, journey maps, and success measurement.",
-      "requires": ["core"],
-      "loops": ["discover"],
-      "skills": [
-        "prfaq",
-        "strategy-analysis",
-        "okr-cascade",
-        "business-case",
-        "requirements-interview",
-        "prd-draft",
-        "user-journey-map",
-        "success-metrics"
-      ]
-    },
-    "dev-team": {
-      "description": "Build-and-ship: story splitting, implementation with adversarial review, test plans, triage, migrations, launch readiness, release notes, agent-policy files, and code-quality gates.",
-      "requires": ["core"],
-      "loops": ["build", "release"],
-      "skills": [
-        "agents-md-generator",
-        "user-story-splitter",
-        "feature-implement-loop",
-        "pre-merge-review",
-        "devils-advocate",
-        "test-plan-generator",
-        "bug-triage",
-        "migration-plan",
-        "release-notes",
-        "sonar-onboard",
-        "sonar-review",
-        "accessibility-audit",
-        "contribution-wizard",
-        "launch-readiness"
-      ]
-    },
-    "sre-oncall": {
-      "description": "Operate the service: runbooks, observability design, incident communications, postmortems, and capacity/cost models.",
-      "requires": ["core"],
-      "loops": ["operate"],
-      "skills": [
-        "runbook-generator",
-        "observability-plan",
-        "incident-comms",
-        "postmortem-generator",
-        "capacity-cost-model"
-      ]
-    },
-    "stakeholder-comms": {
-      "description": "Non-technical audiences: audience profiling, deck outlines and real .pptx decks, exec summaries, decision logs, and guides.",
-      "requires": ["core"],
-      "loops": [],
-      "skills": [
-        "audience-profile",
-        "slide-outliner",
-        "deck-builder",
-        "exec-summary",
-        "decision-log",
-        "guide-builder"
-      ]
-    },
-    "ai-engineering": {
-      "description": "Adopt and build AI systems: readiness assessment, use-case triage, rollout and acceptable-use policy, plus agent loop design, subagent orchestration, spend budgets, agent security review, eval harnesses, and AI-usage reporting.",
-      "requires": ["core"],
-      "loops": [],
-      "skills": [
-        "agent-loop-design",
-        "subagent-design",
-        "agent-budget",
-        "agent-threat-model",
-        "llm-eval-harness",
-        "ai-usage-report",
-        "ai-readiness-assessment",
-        "ai-use-case-triage",
-        "ai-adoption-rollout",
-        "ai-usage-policy",
-        "agent-adoption-stage"
-      ]
-    },
-    "claude-api": {
-      "description": "Skills for teams building on the Anthropic API — prompt caching, token budgeting, eval generation for skills, and tool-use schema writing.",
-      "loops": [],
-      "skills": [
-        "prompt-caching-advisor",
-        "token-budget-estimator",
-        "eval-harness-generator",
-        "tool-use-schema-writer"
-      ]
-    }
-  },
-  "outcomes": {
-    "decide-what-to-build": {
-      "description": "Turn a direction into a committed, measurable plan: press releases, strategy frameworks, OKRs, business cases, requirements, PRDs, and the metrics that will say whether it worked.",
-      "skills": [
-        "prfaq",
-        "strategy-analysis",
-        "okr-cascade",
-        "business-case",
-        "capacity-cost-model",
-        "requirements-interview",
-        "prd-draft",
-        "nfr-spec",
-        "success-metrics",
-        "user-story-splitter",
-        "user-journey-map"
-      ]
-    },
-    "design-the-system": {
-      "description": "Commit the shape before the code: decision records, design docs, diagrams, contracts, schemas, migration and threat models, and the design of any agentic parts.",
-      "skills": [
-        "adr-generator",
-        "design-doc",
-        "architecture-diagrams",
-        "reverse-architecture",
-        "figma-diagrams",
-        "api-contract-draft",
-        "db-schema-design",
-        "data-contract",
-        "tech-comparison-matrix",
-        "threat-model",
-        "agent-threat-model",
-        "migration-plan",
-        "agent-loop-design",
-        "subagent-design",
-        "agent-budget"
-      ]
-    },
-    "build-and-review-software": {
-      "description": "The loop around the code itself: supervised implementation, adversarial review panels, test plans, triage, accessibility and static-analysis passes, and the policy files agents read.",
-      "skills": [
-        "feature-implement-loop",
-        "pre-merge-review",
-        "devils-advocate",
-        "council-review",
-        "accessibility-audit",
-        "sonar-onboard",
-        "sonar-review",
-        "test-plan-generator",
-        "bug-triage",
-        "agents-md-generator",
-        "llm-eval-harness",
-        "eval-harness-generator",
-        "contribution-wizard"
-      ]
-    },
-    "build-on-the-claude-api": {
-      "description": "Skills for teams building directly on the Anthropic API — prompt caching strategy, token budgeting, eval generation, and tool-use schema writing.",
-      "skills": [
-        "prompt-caching-advisor",
-        "token-budget-estimator",
-        "eval-harness-generator",
-        "tool-use-schema-writer"
-      ]
-    },
-    "run-and-recover-the-service": {
-      "description": "Operate what shipped: runbooks, observability design, release notes, incident communication, and the postmortem that closes the loop.",
-      "skills": [
-        "runbook-generator",
-        "observability-plan",
-        "release-notes",
-        "incident-comms",
-        "postmortem-generator",
-        "launch-readiness"
-      ]
-    },
-    "explain-it-to-decision-makers": {
-      "description": "Get a non-technical audience to a decision: audience profiling, deck outlines and real decks, exec summaries, decision logs, and how-to guides.",
-      "skills": [
-        "audience-profile",
-        "slide-outliner",
-        "deck-builder",
-        "exec-summary",
-        "decision-log",
-        "guide-builder"
-      ]
-    },
-    "govern-ai-use": {
-      "description": "Adopt AI deliberately and prove what it is doing: readiness assessment, use-case triage, rollout plans, acceptable-use policy, adoption staging, and usage reporting.",
-      "skills": [
-        "ai-readiness-assessment",
-        "ai-use-case-triage",
-        "ai-adoption-rollout",
-        "ai-usage-policy",
-        "agent-adoption-stage",
-        "ai-usage-report"
-      ]
-    },
-    "get-a-draft-ready-to-ship": {
-      "description": "The passes either side of a generator: collect a messy input into a structured brief, critique the argument, and strip the machine artifacts before it leaves the building.",
-      "skills": [
-        "brief-intake",
-        "doc-critique",
-        "output-hygiene"
-      ]
-    }
-  }
-}