🎩 You're Invited:Meet the Socket team at Black Hat in Las Vegas, August 3-6.RSVP →
Sign In

create-adsk

Package Overview
Maintainers
1
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

create-adsk - npm Package Compare versions

Source code not available
We could not scan this package. Some page functionalities have been disabled
Comparing version
0.3.3
 to
0.3.4
+36
kit-snapshot/.cursor/commands/run-skill-evals.md
# /run-skill-evals
Run with-skill vs without-skill output evals for a skill (Tier 2 style). Soft quality signal — not a merge gate.
## Skill / playbook
Follow **`skills/skill-optimizer`** → `references/eval-loop.md` (or `.agents/skills/skill-optimizer` in adopter apps). Full runbook: `docs/evaluating-skills.md`.
## Usage
```
/run-skill-evals
/run-skill-evals skills/spec-driven-workflow
/run-skill-evals .agents/skills/my-company-skill
```
## When to use
- You **changed** a skill’s behavior or description, or switched models
- You are shipping a **company** skill and need with/without evidence before commit
**Do not** re-benchmark every PR. For stock first-party skills, trust published numbers in `docs/evals/SCORECARD.md` unless the above applies.
## Behavior
1. Locate the target skill (ask if unclear). Prefer kit `skills/<name>` or adopter `.agents/skills/<name>`.
2. Confirm `evals/evals.json` exists (and ideally `evals/trigger/eval_queries.json`). If missing, stop and point to `/optimize-skill` first.
3. **Package cases** (pick one):
- **This kit repo:** run `./scripts/run-skill-evals-soft.sh --skill <name>` → work under `.adsk-tier2-out/<name>/`.
- **Adopter app (no kit scripts):** read prompts from `.agents/skills/<name>/evals/evals.json` directly; create a gitignored workspace (e.g. `.adsk-tier2-out/<name>/`) with `with_skill/` and `without_skill/` arms per case.
4. For **each** eval case, in a **clean** context:
- **with_skill** — skill available; paste the prompt; save output
- **without_skill** — same prompt without the skill (or prior version); save output
5. Grade each assertion PASS/FAIL with evidence into `grading.json` (or equivalent). Prefer mechanical checks when possible.
6. Summarize pass-rate Δ (and token/time Δ if available). For kit first-party skills, offer a SCORECARD paste row; for company skills, report in-chat / PR notes (do not invent kit SCORECARD edits unless asked).
7. Reminder: Tier 1 (`./scripts/check-skills-ci.sh` in the kit) only checks harness shape — it does not replace this loop.
+6
-5
kit-snapshot/.cursor/commands/implement-spec.md

@@ -17,6 +17,7 @@ # /implement-spec

1. Read the spec or plan; follow the plan step-by-step when present.
2. Implement with tests mapped to requirements (or justify non-behavioral exceptions).
3. Update plan todo status as steps complete (Cursor Plan YAML `todos` and/or portable checklist — see `references/cursor-adapter.md` / `artifact-homes.md`).
4. Run project verify commands; fix failures before claiming done.
5. Suggest `/review` when implementation is complete.
1. **Clear** (Medium+): confirm exploration is persisted in the living spec/plan; start this session lean — see skill gated procedure.
2. Read the spec or plan; follow the plan step-by-step when present.
3. Implement with tests mapped to requirements (or justify non-behavioral exceptions).
4. Update plan todo status as steps complete (Cursor Plan YAML `todos` and/or portable checklist — see `references/cursor-adapter.md` / `artifact-homes.md`).
5. **Fail-closed verify:** run `project-cmds` / project verify; fix failures before claiming done. If verify is missing, refuse “done” and point to `/quick-start` — do not invent a silent pass.
6. Suggest `/review` when implementation is complete.
+1
-1
kit-snapshot/.cursor/commands/optimize-skill.md

@@ -22,2 +22,2 @@ # /optimize-skill

3. Apply lean edits; move kit-meta/rationale into `references/` with hard when-to-load conditions.
4. Report what changed and any remaining eval gaps.
4. Report what changed and any remaining eval gaps. For a full with/without output pass, hand off to `/run-skill-evals`.
+5
-4
kit-snapshot/.cursor/commands/plan-impl.md

@@ -18,7 +18,8 @@ # /plan-impl

1. Read the spec; if open questions or unconfirmed assumptions remain, resolve those before planning.
2. Break work into ordered, verifiable tasks (files, tests, risks). Prefer tasks that map to `REQ-XXX` and stay within a focused file set.
3. **Resolve the plan path** via the skill. As a Cursor `/` command, default to `.cursor/plans/{feature-name}.plan.md` unless the project already uses `docs/plans/` or the user overrides the path.
4. Write the plan with **trackable todos** (Cursor: non-empty frontmatter `todos`; never body-only REQ tables with empty Plan UI todos).
5. Suggest `/implement-spec` only after the user approves the plan (medium+).
2. Break work into ordered, verifiable tasks (files, tests, risks). Prefer tasks that map to `REQ-XXX` and stay within a focused file set. Prefer splitting **build** from **verify/review** so QA can run in parallel with the next slice.
3. **Tracer gate** (Large, and Medium when architecture/integration is ambiguous): include a thin vertical slice + one verify before multi-phase implement, or “N/A — architecture proven” with justification — see skill / `problem-size-guide.md`.
4. **Resolve the plan path** via the skill. As a Cursor `/` command, default to `.cursor/plans/{feature-name}.plan.md` unless the project already uses `docs/plans/` or the user overrides the path.
5. Write the plan with **trackable todos** (Cursor: non-empty frontmatter `todos`; never body-only REQ tables with empty Plan UI todos).
6. Suggest `/implement-spec` only after the user approves the plan (medium+).
Keep this command thin — planning depth lives in the skill / recommended upstream.
+6
-2
kit-snapshot/.cursor/commands/quick-start.md

@@ -19,3 +19,7 @@ # /quick-start

2. Detect artifact homes (Cursor `.cursor/...` vs portable `docs/...`) via `references/artifact-homes.md`; when Cursor wiring is present, update or propose `.cursor/rules/project/` and `project-cmds` with real verify commands.
3. Guide next steps: greenfield → `/draft-spec`; brownfield → `/extract-spec`.
4. Confirm ADSK skills are discoverable under `.agents/skills/`. If missing, point to `docs/using-adsk.md` (`npx skills add rhyanvargas/agentic-development-starter-kit`).
3. Confirm ADSK skills are discoverable under `.agents/skills/`. If missing, point to `docs/using-adsk.md` (`npx skills add rhyanvargas/agentic-development-starter-kit`).
4. End with a short **where truth lives** checklist (all four required):
- Spec/plan artifact home (resolved path)
- Verify commands location (`project-cmds` or portable equivalent)
- Skills discovery path (`.agents/skills/`)
- Next command: greenfield → `/draft-spec`; brownfield → `/extract-spec`
+1
-0
kit-snapshot/.cursor/rules/project-cmds/RULE.md

@@ -26,2 +26,3 @@ ---

# Skill Tier 2 fixtures:./scripts/run-skill-evals-soft.sh --self-test
# Skill Tier 2 agent loop (Cursor): /run-skill-evals # with/without; not a CI gate
# Dependency audit: npm ci && npm audit --audit-level=high

@@ -28,0 +29,0 @@ # create-adsk snapshot: ./scripts/prepare-create-adsk-snapshot.sh

+1
-1
kit-snapshot/.cursor/rules/skill-authoring/RULE.md

@@ -18,3 +18,3 @@ ---

3. Write `description` as what + when; add near-miss “Do not use for…” when adjacent skills share keywords.
4. Add/update `evals/trigger/eval_queries.json` (~20 queries, include near-misses) and behavior `evals/evals.json` when instructions change.
4. Add/update `evals/trigger/eval_queries.json` (~20 queries, include near-misses) and behavior `evals/evals.json` when instructions change. For a with/without pass, use `/run-skill-evals`.
5. Run `npx --yes skills-ref validate <skill-dir>` before claiming done.

@@ -21,0 +21,0 @@ 

+1
-1
package.json
{
"name": "create-adsk",
"version": "0.3.3",
"version": "0.3.4",
"description": "Adopt the Agentic Development Starter Kit as a versioned profile (skills + Cursor wiring).",

@@ -5,0 +5,0 @@ "type": "module",

kit-snapshot/KIT_REF

Sorry, the diff of this file is not supported yet