refactor: rename skills to verb-first naming convention

.agents/skills/README.md

@@ -9,20 +9,20 @@ A complete skill is a directory with a required `SKILL.md` file and optional bun
 | Skill | Use it for | Notable resources |
 | --- | --- | --- |
 | [`audit-skill-security`](audit-skill-security/SKILL.md) | Auditing third-party or local skills before installing, updating, or trusting them. | [`references/audit-protocol.md`](audit-skill-security/references/audit-protocol.md) |
-| [`codegen-backend`](codegen-backend/SKILL.md) | Production backend code: APIs, services, middleware, workers, persistence, validation, auth, and backend tests. | [`references/`](codegen-backend/references/), [`evals/`](codegen-backend/evals/) |
-| [`codegen-database`](codegen-database/SKILL.md) | Database code: schemas, DDL, OLTP SQL, analytics SQL, migrations, indexes, stored procedures, and dialect-specific scripts. | [`references/`](codegen-database/references/), [`evals/`](codegen-database/evals/) |
-| [`codegen-frontend`](codegen-frontend/SKILL.md) | Production frontend code: components, routes, client state, forms, styling, accessibility, performance, PWA behavior, and visualization. | [`references/`](codegen-frontend/references/), [`evals/`](codegen-frontend/evals/) |
-| [`codegen-test`](codegen-test/SKILL.md) | Automated tests and evals, including E2E, API, integration, performance, AI output, tool-use, RAG, and prompt regression suites. | [`references/`](codegen-test/references/), [`scripts/`](codegen-test/scripts/), [`evals/`](codegen-test/evals/) |
-| [`creator-rule`](creator-rule/SKILL.md) | Writing or improving agent rules, instruction files, `AGENTS.md`, `CLAUDE.md`, Cursor rules, Copilot instructions, and `.agents/rules/*.md`. | [`scripts/`](creator-rule/scripts/), [`evals/`](creator-rule/evals/) |
-| [`creator-skill`](creator-skill/SKILL.md) | Creating, editing, reviewing, evaluating, packaging, optimizing, or improving skills. Start here for skill authoring. | [`references/`](creator-skill/references/), [`scripts/`](creator-skill/scripts/), [`eval-viewer/`](creator-skill/eval-viewer/), [`agents/`](creator-skill/agents/), [`assets/`](creator-skill/assets/), [`evals/`](creator-skill/evals/) |
+| [`build-backend`](build-backend/SKILL.md) | Production backend code: APIs, services, middleware, workers, persistence, validation, auth, and backend tests. | [`references/`](build-backend/references/), [`evals/`](build-backend/evals/) |
+| [`build-database`](build-database/SKILL.md) | Database code: schemas, DDL, OLTP SQL, analytics SQL, migrations, indexes, stored procedures, and dialect-specific scripts. | [`references/`](build-database/references/), [`evals/`](build-database/evals/) |
+| [`build-frontend`](build-frontend/SKILL.md) | Production frontend code: components, routes, client state, forms, styling, accessibility, performance, PWA behavior, and visualization. | [`references/`](build-frontend/references/), [`evals/`](build-frontend/evals/) |
+| [`write-tests`](write-tests/SKILL.md) | Automated tests and evals, including E2E, API, integration, performance, AI output, tool-use, RAG, and prompt regression suites. | [`references/`](write-tests/references/), [`scripts/`](write-tests/scripts/), [`evals/`](write-tests/evals/) |
+| [`create-rule`](create-rule/SKILL.md) | Writing or improving agent rules, instruction files, `AGENTS.md`, `CLAUDE.md`, Cursor rules, Copilot instructions, and `.agents/rules/*.md`. | [`scripts/`](create-rule/scripts/), [`evals/`](create-rule/evals/) |
+| [`create-skill`](create-skill/SKILL.md) | Creating, editing, reviewing, evaluating, packaging, optimizing, or improving skills. Start here for skill authoring. | [`references/`](create-skill/references/), [`scripts/`](create-skill/scripts/), [`eval-viewer/`](create-skill/eval-viewer/), [`agents/`](create-skill/agents/), [`assets/`](create-skill/assets/), [`evals/`](create-skill/evals/) |
 | [`design-api`](design-api/SKILL.md) | Contract-first API design for OpenAPI, AsyncAPI, GraphQL, endpoints, schemas, and request/response shapes. | [`references/`](design-api/references/), [`evals/`](design-api/evals/) |
 | [`explain`](explain/SKILL.md) | Explaining general knowledge, concepts, code, behavior, design, architecture, APIs, data flow, and tradeoffs in simple terms. | [`evals/`](explain/evals/) |
-| [`operator-git`](operator-git/SKILL.md) | Git branch naming, branch actions, commit-message drafting, and committing staged changes. | [`references/`](operator-git/references/), [`evals/`](operator-git/evals/) |
+| [`manage-git`](manage-git/SKILL.md) | Git branch naming, branch actions, commit-message drafting, and committing staged changes. | [`references/`](manage-git/references/), [`evals/`](manage-git/evals/) |
 | [`review-code`](review-code/SKILL.md) | Reviewing code changes, diffs, pull requests, branches, or patches for correctness, regressions, security, performance, and test gaps. | [`references/`](review-code/references/), [`evals/`](review-code/evals/) |
-| [`writer-prd`](writer-prd/SKILL.md) | Product requirements, product briefs, feature requirements, product scope, and launch requirements. | [`references/`](writer-prd/references/), [`evals/`](writer-prd/evals/) |
-| [`writer-spec`](writer-spec/SKILL.md) | Technical specs, design docs, functional and non-functional requirements, data contracts, UI specs, release specs, and handoff docs. | [`references/`](writer-spec/references/), [`evals/`](writer-spec/evals/) |
-| [`writer-tech-docs`](writer-tech-docs/SKILL.md) | READMEs, API docs, endpoint references, routine and on-call runbooks, changelogs, and release notes. | [`references/`](writer-tech-docs/references/), [`evals/`](writer-tech-docs/evals/) |
-| [`writer-user-story`](writer-user-story/SKILL.md) | User stories, acceptance criteria, developer tasks, tickets, story points, and sprint planning breakdowns. | [`references/`](writer-user-story/references/), [`evals/`](writer-user-story/evals/) |
+| [`write-prd`](write-prd/SKILL.md) | Product requirements, product briefs, feature requirements, product scope, and launch requirements. | [`references/`](write-prd/references/), [`evals/`](write-prd/evals/) |
+| [`write-spec`](write-spec/SKILL.md) | Technical specs, design docs, functional and non-functional requirements, data contracts, UI specs, release specs, and handoff docs. | [`references/`](write-spec/references/), [`evals/`](write-spec/evals/) |
+| [`write-tech-docs`](write-tech-docs/SKILL.md) | READMEs, API docs, endpoint references, routine and on-call runbooks, changelogs, and release notes. | [`references/`](write-tech-docs/references/), [`evals/`](write-tech-docs/evals/) |
+| [`write-user-story`](write-user-story/SKILL.md) | User stories, acceptance criteria, developer tasks, tickets, story points, and sprint planning breakdowns. | [`references/`](write-user-story/references/), [`evals/`](write-user-story/evals/) |
 
 ## Resource Folders
 
@@ -36,17 +36,17 @@ A complete skill is a directory with a required `SKILL.md` file and optional bun
 
 ## Common Entry Points
 
-Use [`creator-skill`](creator-skill/SKILL.md) to create, revise, package, or evaluate skills. Its schema notes live in [`creator-skill/references/schemas.md`](creator-skill/references/schemas.md), and its package command is:
+Use [`create-skill`](create-skill/SKILL.md) to create, revise, package, or evaluate skills. Its schema notes live in [`create-skill/references/schemas.md`](create-skill/references/schemas.md), and its package command is:
 
 ```bash
-cd .agents/skills/creator-skill
-python3 -m scripts.package_skill ../codegen-database /tmp/skills-dist
+cd .agents/skills/create-skill
+python3 -m scripts.package_skill ../build-database /tmp/skills-dist
 ```
 
 Use this validation command when changing an existing skill:
 
 ```bash
-python3 .agents/skills/creator-skill/scripts/quick_validate.py .agents/skills/codegen-database
+python3 .agents/skills/create-skill/scripts/quick_validate.py .agents/skills/build-database
 ```
 
 The key rule is simple: keep `SKILL.md` and any files it references together. If a skill says to read `references/postgres.md`, that file must remain available relative to the skill folder. Tiny rule, large consequences. Filesystems enjoy pettiness.

.agents/skills/codegen-backend/SKILL.md → .agents/skills/build-backend/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: codegen-backend
+name: build-backend
 description: Build or modify backend implementation. Use for API routes, services, middleware, workers, persistence, validation, authorization, configuration, observability, and backend behavior tests.
 license: MIT
 version: 1.1.0
@@ -12,7 +12,7 @@ metadata:
   catalog: software-team-roles
 ---
 
-# codegen-backend
+# build-backend
 
 Implement backend code for APIs, services, workers, persistence, middleware, validation, authorization, configuration, observability, and behavior tests. Use this as a router: identify the backend language from the request and repository, read exactly one language reference, and read at most one framework reference when the framework signal is explicit or unambiguous.
 

.agents/skills/codegen-backend/evals/evals.json → .agents/skills/build-backend/evals/evals.json

@@ -1,5 +1,5 @@
 {
-  "skill_name": "codegen-backend",
+  "skill_name": "build-backend",
   "evals": [
     {
       "id": 1,

.agents/skills/codegen-database/SKILL.md → .agents/skills/build-database/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: codegen-database
+name: build-database
 description: >
   Generate or modify database code: schemas, DDL, SQL queries, migrations, analytics SQL,
   indexes, stored procedures, and dialect-specific database scripts.
@@ -14,9 +14,9 @@ metadata:
   catalog: software-team-roles
 ---
 
-# codegen-database
+# build-database
 
-Generate production-ready database code for schemas, DDL, OLTP queries, analytics SQL, migrations, indexes, stored procedures, and dialect-specific scripts. Use this as a router: classify the database artifact first, detect the dialect from context or repository evidence, then read only the relevant references.
+Generate production-ready database code for schemas, DDL, OLTP queries, analytics SQL, migrations, indexes, stored procedures, and dialect-specific scripts. Use this as a router: classify-content the database artifact first, detect the dialect from context or repository evidence, then read only the relevant references.
 
 ## Variant Detection
 
@@ -26,7 +26,7 @@ Generate production-ready database code for schemas, DDL, OLTP queries, analytic
 - **Migrations:** Requests for up/down migrations, Flyway, Liquibase, Rails/ActiveRecord migrations, Alembic, Prisma migrations, rollback, data backfills, or deployment-safe DDL route to `references/migration.md`.
 - **OLTP SQL:** Requests for queries, DML, views, indexes, transactions, upserts, stored procedures, or query optimization route to `references/common.md`, then the dialect reference.
 - **Analytics SQL:** Requests for warehouses, metrics, cohorts, funnels, retention, partitioned fact tables, dbt-like transformations, BigQuery, Snowflake, or ClickHouse route to `references/analytics.md`, then any matching warehouse reference.
-- **Adjacent skills:** Use `report-db-health` for database health findings from existing telemetry. Use `strategy-backup` for backup and recovery policy. Use `writer-spec` for data contracts when the output is prose rather than executable database code.
+- **Adjacent skills:** Use `report-db-health` for database health findings from existing telemetry. Use `plan-backup` for backup and recovery policy. Use `write-spec` for data contracts when the output is prose rather than executable database code.
 - **Ambiguity:** If the artifact type or database remains genuinely ambiguous after inspecting context, ask one short question naming the likely choices.
 
 ## Dialect Routing
@@ -57,7 +57,7 @@ If the user asks for portable SQL, use `references/common.md` and avoid dialect-
 - **Use parameters:** Never generate SQL that interpolates user input into executable statements. Use the placeholder style for the target dialect or framework.
 - **Index deliberately:** Tie each recommended index to a query, constraint, or access pattern. Avoid adding write-costly indexes without a reason.
 - **Handle concurrency:** Use transactions, locks, isolation levels, uniqueness, idempotency keys, or retry notes when the database operation can race.
-- **Respect dialect limits:** Do not mix syntax across engines. If the dialect is unknown and syntax materially differs, ask once instead of producing decorative nonsense in SQL clothing.
+- **Respect dialect limits:** Do not mix syntax across engines. If the dialect is unknown and syntax materially differs, ask-questions once instead of producing decorative nonsense in SQL clothing.
 - **Verify locally:** Run the narrowest relevant migration check, SQL parser, formatter, test, or application test available. If no database is available, state what was reviewed statically.
 
 ## Implementation Flow

.agents/skills/codegen-database/evals/evals.json → .agents/skills/build-database/evals/evals.json

@@ -1,5 +1,5 @@
 {
-  "skill_name": "codegen-database",
+  "skill_name": "build-database",
   "evals": [
     {
       "id": 1,

.agents/skills/codegen-database/references/common.md → .agents/skills/build-database/references/common.md

@@ -12,7 +12,7 @@ Identify the dialect from context. Check in this order:
 2. File extensions or migration tool conventions (`.sql`, Flyway prefix `V1__`, Liquibase)
 3. Code imports (`pg`, `mysql2`, `sqlite3`, `pyodbc`)
 4. Infrastructure mentions ("RDS Postgres", "Azure SQL", etc.)
-5. If genuinely ambiguous: ask once — "Which database are you using? (PostgreSQL, MySQL, MSSQL, SQLite, Oracle)"
+5. If genuinely ambiguous: ask-questions once — "Which database are you using? (PostgreSQL, MySQL, MSSQL, SQLite, Oracle)"
 
 Once identified, load the dialect-specific reference for syntax details:
 

.agents/skills/codegen-frontend/SKILL.md → .agents/skills/build-frontend/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: codegen-frontend
+name: build-frontend
 description: Generate production-ready frontend code. Use for components, pages, routes, client state, forms, styling, accessibility, performance, PWA behavior, and data visualization.
 license: MIT
 version: 1.1.0
@@ -12,7 +12,7 @@ metadata:
   catalog: software-team-roles
 ---
 
-# codegen-frontend
+# build-frontend
 
 Implement production frontend work by routing to the smallest relevant reference set, matching the repository's existing architecture, and verifying the user-facing behavior.
 
@@ -23,7 +23,7 @@ Implement production frontend work by routing to the smallest relevant reference
 - **User signals:** Look for framework names, route or page names, component libraries, state libraries, CSS systems, test tools, file paths, file extensions, and requested user-facing behavior.
 - **Repository signals:** Inspect `package.json`, lockfiles, framework configs, `tsconfig.json`, source folders, imports, routing structure, design tokens, Storybook, test setup, and CI jobs before choosing an implementation path.
 - **Frontend scope:** Use this skill for components, pages, layouts, routes, loaders/actions, forms, stores, queries, charts, responsive styling, accessibility fixes, PWA behavior, and frontend performance work.
-- **Route away:** Use `codegen-test` for test-only work, `design-api` for API contract design, `codegen-backend` for backend implementation, and `writer-spec` or a design skill for UI/UX specification when no code is requested.
+- **Route away:** Use `write-tests` for test-only work, `design-api` for API contract design, `build-backend` for backend implementation, and `write-spec` or a design skill for UI/UX specification when no code is requested.
 - **Clarify rarely:** If the framework, styling system, or target surface remains genuinely ambiguous after inspection, ask one short question naming the likely options.
 
 ## Reference Routing

.agents/skills/codegen-frontend/evals/evals.json → .agents/skills/build-frontend/evals/evals.json

@@ -1,5 +1,5 @@
 {
-  "skill_name": "codegen-frontend",
+  "skill_name": "build-frontend",
   "evals": [
     {
       "id": 1,

.agents/skills/creator-rule/SKILL.md → .agents/skills/create-rule/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: creator-rule
+name: create-rule
 description: Use when writing or improving CLI-agent rules, custom instruction files, AGENTS.md, CLAUDE.md, Cursor rules, Copilot instructions, or modular `.agents/rules/*.md` files.
 license: MIT
 version: 1.2.0
@@ -12,7 +12,7 @@ metadata:
   catalog: utility
 ---
 
-# creator-rule
+# create-rule
 
 Write agent rules as durable operating instructions: concise, scoped, concrete, and easy for another agent to apply without guessing.
 

.agents/skills/creator-rule/evals/evals.json → .agents/skills/create-rule/evals/evals.json

@@ -1,5 +1,5 @@
 {
-  "skill_name": "creator-rule",
+  "skill_name": "create-rule",
   "evals": [
     {
       "id": 1,

.agents/skills/creator-rule/scripts/grade_rule_output.py → .agents/skills/create-rule/scripts/grade_rule_output.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Heuristic grader for creator-rule output-quality evals.
+"""Heuristic grader for create-rule output-quality evals.
 
 This script is intentionally deterministic. It does not replace human review or
 model grading; it catches common failures cheaply: vague rules, missing scoped
@@ -25,7 +25,7 @@
 ]
 
 IMPERATIVE_RE = re.compile(
-    r"\b(use|run|never|do not|don't|ask|include|update|avoid|prefer|keep|"
+    r"\b(use|run|never|do not|don't|ask-questions|include|update|avoid|prefer|keep|"
     r"write|add|check|verify|redact|report|call out|do)\b",
     re.IGNORECASE,
 )
@@ -164,7 +164,7 @@ def grade(eval_item: dict, output: str) -> dict:
 
 
 def main() -> int:
-    parser = argparse.ArgumentParser(description="Grade one creator-rule eval output")
+    parser = argparse.ArgumentParser(description="Grade one create-rule eval output")
     parser.add_argument("--eval-id", type=int, required=True, help="Eval id from evals/evals.json")
     parser.add_argument("--output", required=True, help="Path to the generated rule output")
     parser.add_argument(

.agents/skills/creator-rule/scripts/run_trigger_eval.py → .agents/skills/create-rule/scripts/run_trigger_eval.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Run creator-rule trigger evals.
+"""Run create-rule trigger evals.
 
 By default this uses a transparent lexical router so the eval set can run
 offline in CI. Pass --agent-command to test a real CLI/router. The command can
@@ -30,7 +30,7 @@
 
 NEGATIVE_PATTERNS = [
     r"\b(review this pull request|fix the failing|generate SQL|release notes|user story|technical spec)\b",
-    r"\b(explain|summarize)\b.*\b(AGENTS\.md|README|coding standards)\b",
+    r"\b(explain-topic|summarize)\b.*\b(AGENTS\.md|README|coding standards)\b",
 ]
 
 
@@ -120,9 +120,9 @@ def agent_router(command_template: str, query: str, skill_name: str, description
 
 
 def main() -> int:
-    parser = argparse.ArgumentParser(description="Run creator-rule trigger evals")
+    parser = argparse.ArgumentParser(description="Run create-rule trigger evals")
     parser.add_argument("--eval-set", default=None, help="Path to trigger-evals.json")
-    parser.add_argument("--skill-path", default=None, help="Path to creator-rule skill root")
+    parser.add_argument("--skill-path", default=None, help="Path to create-rule skill root")
     parser.add_argument("--agent-command", default=None, help="Optional CLI command template for real routing judgment")
     parser.add_argument("--timeout", type=int, default=30)
     parser.add_argument("--trials", type=int, default=1, help="Number of repeated runs per query")

.agents/skills/creator-rule/scripts/validate_evals.py → .agents/skills/create-rule/scripts/validate_evals.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Validate creator-rule eval files."""
+"""Validate create-rule eval files."""
 
 from __future__ import annotations
 
@@ -26,8 +26,8 @@ def validate_task_evals(path: Path) -> list[str]:
     errors: list[str] = []
     data = load_json(path)
 
-    if data.get("skill_name") != "creator-rule":
-        errors.append("evals.json skill_name must be creator-rule")
+    if data.get("skill_name") != "create-rule":
+        errors.append("evals.json skill_name must be create-rule")
 
     evals = data.get("evals")
     if not isinstance(evals, list) or not evals:
@@ -113,7 +113,7 @@ def main() -> int:
             print(f"ERROR: {error}", file=sys.stderr)
         return 1
 
-    print("creator-rule eval files are valid")
+    print("create-rule eval files are valid")
     return 0
 
 

.agents/skills/creator-rule/scripts/validate_rule.py → .agents/skills/create-rule/scripts/validate_rule.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Validate creator-rule skill packaging."""
+"""Validate create-rule skill packaging."""
 
 from __future__ import annotations
 
@@ -101,7 +101,7 @@ def main() -> int:
             print(f"ERROR: {error}", file=sys.stderr)
         return 1
 
-    print("creator-rule skill is valid")
+    print("create-rule skill is valid")
     return 0
 
 

.agents/skills/creator-skill/SKILL.md → .agents/skills/create-skill/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: creator-skill
+name: create-skill
 description: Use when creating, editing, reviewing, evaluating, packaging, optimizing or improving skills.
 license: Apache-2.0
 version: 1.1.3
@@ -12,7 +12,7 @@ metadata:
   catalog: utility
 ---
 
-# creator-skill
+# create-skill
 
 Create new skills, review and improve existing skills, evaluate outputs, optimize trigger descriptions, and package final skill folders.