@aayushchugh/skills 0.1.4 → 0.1.6

package/README.md

@@ -36,4 +36,5 @@ Replace `no-slop` with any id below.
 - `the-cause` — The cause. Find a bug's root cause from the report, the code path, and the evidence.
 - `go-or-stop` — Go or stop. Decide if a change is ready to ship, with a go or no-go, what to watch, and how to roll back.
 - `the-map` — The map. Map, propose, or improve a system's design like a senior engineer, grounding the recommendation in real usage and activity.
+- `whats-next` — What's next. Answer what's pending, what's next, or the status from the plan this conversation is working on.
 - `which-skill` — Which skill. Pick and run the right skill, or a chain of skills, for a request.

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@aayushchugh/skills",
-	"version": "0.1.4",
+	"version": "0.1.6",
 	"description": "The agent skills I use while building real products.",
 	"author": "Ayush Chugh <hey@ayushchugh.com>",
 	"license": "MIT",

package/skills/cases-to-run/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: cases-to-run
 description: >-
-  List cases to verify by hand, or name the code tests for no-slop when
-  asked. Use when the user asks for test cases or to test a flow. Do not edit
-  code or audit security.
+  Use when asked for test cases, QA coverage, or how to test a flow by hand.
+  Not for writing the test code or a security audit.
 ---
 
 # Cases to run

package/skills/go-or-stop/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: go-or-stop
 description: >-
-  Decide if a change is ready to ship, with a go or no-go, what to watch, and
-  how to roll back. Use when the user asks for a release check. Do not deploy.
+  Use when asked if a change is ready to ship, or for a go or no-go. Not for
+  deploying.
 ---
 
 # Go or stop

package/skills/no-slop/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: no-slop
 description: >-
-  Write the smallest readable code that reuses existing code, installed
-  utilities, and repo patterns, and fixes bugs at the root cause. Use when
-  implementing, fixing, or reviewing code. Do not use for docs.
+  Use when writing or changing code, including a test that was asked for.
+  Not for docs, a review, or a design.
 ---
 
 # No slop

package/skills/one-shape/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: one-shape
 description: >-
-  Audit a repo for duplication, divergent flows, dead code, over-engineering,
-  waste, and standards drift, then apply approved steps. Use when the user
-  asks to refactor or clean up a codebase. Do not audit security.
+  Use when asked to refactor, clean up, or standardize a repo. Not for a
+  security audit or a single pull request.
 ---
 
 # One shape

package/skills/open-doors/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: open-doors
 description: >-
-  Review application code, APIs, dependencies, secrets, and deploy config for
-  injection, web attacks, and DDoS controls. Use when the user asks for a
-  security audit. Never attack a live target.
+  Use when asked for a security audit or a pentest-readiness review. Not for
+  a live attack or a normal code review.
 ---
 
 # Open doors

package/skills/plain-paper/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: plain-paper
 description: >-
-  Write a spec or other documentation from the request, the code, and relevant
-  sources. Use when the user asks for a PRD, spec, flow, API reference,
-  runbook, guide, or README. Do not change code.
+  Use when asked for a PRD, spec, flow, API reference, runbook, guide, or
+  README. Not for code or a system design.
 ---
 
 # Plain paper

package/skills/red-pen/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: red-pen
 description: >-
-  Review a diff or pull request for bugs, regressions, broken callers, missing
-  tests, and unmet requirements. Use when the user asks for a code review. Do
-  not audit security, refactor, or write tests.
+  Use when asked to review a diff, a pull request, or a change. Not for a
+  security audit, a refactor, or writing tests.
 ---
 
 # Red pen

package/skills/the-cause/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: the-cause
 description: >-
-  Find a bug's root cause from the report, the code path, and the evidence.
-  Use when the user asks to diagnose or debug a failure. Do not write the fix
-  or the regression test.
+  Use when asked to diagnose, debug, or find why something fails. Not for
+  writing the fix or the test.
 ---
 
 # The cause

package/skills/the-map/SKILL.md

@@ -1,10 +1,8 @@
 ---
 name: the-map
 description: >-
-  Map, propose, or improve a system's design like a senior engineer,
-  grounding the recommendation in real usage and activity. Use when the user
-  asks for a system design, architecture review, or scale or performance
-  improvement. Do not write code.
+  Use when asked for a system design, an architecture review, or a scale or
+  performance improvement. Not for writing code or a PRD.
 ---
 
 # The map

package/skills/whats-next/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: whats-next
+description: >-
+  Use when asked what's pending, what's next, or the status of the current
+  work. Not for starting the work or changing the plan.
+---
+
+# What's next
+
+## Scope
+
+Read the plan. Do not edit it. Do not start the next todo unless asked.
+
+Answer only from the plan this conversation is implementing. Do not invent a task from memory, git, or an older plan.
+
+## Before writing
+
+Ask every blocking question in one turn. Never invent a fact. Put an unknown under Open questions and name what it blocks. Replies are 1–2 lines. Write a paragraph only when the user asks.
+
+## The plan
+
+Read the plan attached to this chat. Ignore an older plan on disk.
+
+Its todos are the only source. Each todo is `pending`, `in_progress`, or `completed`.
+
+- **What's next:** the `in_progress` todo, or the first `pending` todo when nothing is in progress. One line: that todo, and whether it has not been started or is in progress. A todo waiting on the user is not next. Say what it is waiting on.
+- **What's pending:** every todo that is not `completed`, in the plan's order.
+- **Status:** one line for done, one line for in progress, one line for still pending.
+
+When every todo is `completed`, say the plan is done. Do not pick a new task.
+
+If this conversation has no plan, say so.
+
+## Replies
+
+Name the plan. Answer only the question asked. "What's next" is one todo. "What's pending" is the open list. "Status" is the three lines. Do not dump the whole plan.

package/skills/which-skill/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: which-skill
 description: >-
-  Pick and run the right skill, or a chain of skills, for a request. Use when
-  unsure which skill applies or when a task spans several steps.
+  Use when a request could match more than one skill, or needs several skills
+  in a row.
 ---
 
 # Which skill
@@ -30,6 +30,7 @@ Read the chosen skill and follow it. Do not restate its rules here.
 | Diagnose or debug a failure | `the-cause` |
 | Release check or go / no-go | `go-or-stop` |
 | System design, architecture review, or scale/performance improvement | `the-map` |
+| What's pending, what's next, or the status of the current plan | `whats-next` |
 
 Run one skill when one fits. Say which skill or chain you picked in one line. Ask one question when two skills fit equally.