Run any Skill in Manus with one click

cursorqb-autopsy

Stars23

Forks2

UpdatedJune 14, 2026 at 09:19

Goal-backed Step 1.5 of the CursorQB planning workflow - an existing-project autopsy. Use after Step 1 (or directly) to inspect an existing/partially built repository and write Planner-docs/Autopsy.md, a 13-section technical feedback report that enriches Step 2 sub-plans. Runs automatically for existing/non-empty repositories and is skipped for empty or nearly empty ones. Launched automatically as a Cursor goal via the define-goal skill; only creates/updates Planner-docs/Autopsy.md.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

alicankiraz1

alicankiraz1/CursorQB

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

File Explorer

2 files

SKILL.md

readonly

More from this repository

same repository

cursorqb-auditor

alicankiraz1/CursorQB

Goal-backed Step 3 of the CursorQB planning workflow - a quality, coverage, consistency, and readiness audit of the Step 2 sub-plans. Use to verify that Planner-docs/Faz-*-Plans/*.md and Sub-Planing-Index.md are faithful to Main-Planing.md, complete, ordered, well-structured, and ready for implementation. Launched automatically as a Cursor goal via the define-goal skill and runs until every phase and sub-plan is inspected; produces only Planner-docs/Sub-Planing-Audit.md and returns PASS / PASS_WITH_WARNINGS / BLOCKED. Safe to run standalone for re-audits.

2026-06-1423

cursorqb-implementer

alicankiraz1/CursorQB

Gated, goal-backed Step 4 of the CursorQB workflow - implement one bounded, reversible, testable slice from an audited plan. Use after the Step 3 audit when the user approves implementation, or via /cursorqb-implement. Runs only when the audit is PASS or PASS_WITH_WARNINGS with no P0/P1 findings; otherwise it stops and recommends repair. Selects a single READY sub-plan, defines the validation command first, makes a minimal change, and verifies before claiming done.

2026-06-1423

cursorqb-planner

alicankiraz1/CursorQB

Guided five-step (1, 1.5, 2, 3, 4), goal-backed project planning orchestrator with a repo-aware intake. Use when the user runs /cursorqb-plan or asks CursorQB to plan a project end to end - master plan, existing-project autopsy, phase decomposition, coverage audit, then optional implementation. Runs a repo-aware Step 1 intake, produces Planner-docs/Main-Planing.md, runs a Step 1.5 autopsy (cursorqb-autopsy) for existing projects, then gates into phase decomposition (cursorqb-subplanner), a coverage/quality audit (cursorqb-auditor), and a gated implementation step (cursorqb-implementer) - launched automatically as Cursor goals via define-goal. Validates each step with the bundled validator.

2026-06-1423

cursorqb-subplanner

alicankiraz1/CursorQB

Goal-backed Step 2 of the CursorQB planning workflow. Use to decompose every main phase in Planner-docs/Main-Planing.md into detailed sub-plans under Planner-docs/Faz-<n>-Plans/ plus Sub-Planing-Index.md. Launched automatically as a Cursor goal via the define-goal skill and runs until ALL phases are covered - it does not stop after one phase. Invoke from cursorqb-planner Gate 1, or directly to (re)generate sub-plans. Only changes files under Planner-docs/.

2026-06-1423

name

cursorqb-autopsy

description

CursorQB Autopsy (Step 1.5, goal-backed)

Inspect an existing or partially built repository in detail and write a single autopsy report that Step 2 uses as supporting feedback. This step never changes source code, never changes Main-Planing.md, and only creates/updates Planner-docs/Autopsy.md. Read the full Step-1.5 spec in autopsy-planner.md (next to this skill) and follow it end to end.

Execution model

In-session, goal-backed. Read the bundled autopsy-planner.md spec and follow it. Register the goal via the Cursor define-goal skill (get_goal then create_goal); if the goal tool is unavailable, proceed under the in-context goal contract - behavior is identical.
Reliability + validator. Resolve the plugin root by walking up to the folder containing .cursor-plugin/plugin.json; read references/workflow-quality.md and follow it. The bundled validator is at <plugin-root>/scripts/validate_planner_docs.py.
Sources of truth (read-only): Planner-docs/Main-Planing.md (primary) plus repository evidence (README, manifests, CI, tests, docs, service/package folders, configs).
Only writable file: Planner-docs/Autopsy.md in the user's active workspace (cwd). Never touch source, Main-Planing.md, or any Step 2/3 file.
Language: the autopsy report is written in English.

When to run vs skip

Run for existing or partially built projects: the repository is not empty and contains meaningful evidence such as README, manifests, source/service/package directories, tests, docs, configs, or CI.
Skip for new or nearly empty repositories: do not create Planner-docs/Autopsy.md; report that Step 1.5 was skipped because there is not enough repository evidence, then stop. Step 2 continues without it.

Goal contract (declare before starting)

Objective: For an existing project, produce Planner-docs/Autopsy.md using the exact 14-heading structure (# Project Autopsy + 13 numbered sections) from autopsy-planner.md, grounded in repository evidence.
Success evidence: Autopsy.md exists with all 14 headings in order, in English, no secrets; git status shows only Planner-docs/Autopsy.md changed; OR Step 1.5 was correctly skipped for an empty repo (no Autopsy.md created).
Scope bounds: only create/update Planner-docs/Autopsy.md. No source/config/test edits. No secrets, tokens, or credentials. No commit, push, or PR.
Stop condition: stop on Success, on a correct skip, or on a blocking read error.

Procedure

Read Main-Planing.md and inspect the repository with the read-only commands listed in autopsy-planner.md.
If evidence is too thin (empty/new repo), skip and report; do not write Autopsy.md.
Otherwise build Autopsy.md incrementally (create the file, then add sections) with all 14 headings, grounded in evidence; redact any secret-like value to <redacted>.
Validate: run python3 <plugin-root>/scripts/validate_planner_docs.py --root . --mode step2 --strict and confirm autopsy_exists=true with no Autopsy.md heading errors (fallback: manually confirm the 14 headings in order). Confirm only Planner-docs/Autopsy.md changed.

Output and handoff

Report: whether Step 1.5 succeeded, was skipped, or was blocked; whether Autopsy.md was created/updated; the highest-priority AUTOPSY-P0/P1 signals; how Step 2 should use the report; and confirmation that only Planner-docs/Autopsy.md changed. Control returns to cursorqb-planner (Gate 1 feedback covers both Main-Planing.md and Autopsy.md); Step 2 (cursorqb-subplanner) reads Autopsy.md as supporting feedback.