Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

doctor

Étoiles0

Forks2

Mis à jour15 juillet 2026 à 07:11

Use before any kagura-engineer run/review, or when the harness reports a blocked environment — diagnoses the local setup (git, selected brain CLI, gh, ollama, memory backend, and gh-issue-driven plugin) by shelling out to `kagura-engineer doctor` and reports what must be fixed.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

kagura-ai

kagura-ai/kagura-engineer

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	doctor
description	Use before any kagura-engineer run/review, or when the harness reports a blocked environment — diagnoses the local setup (git, selected brain CLI, gh, ollama, memory backend, and gh-issue-driven plugin) by shelling out to `kagura-engineer doctor` and reports what must be fixed.

kagura-engineer: doctor

Thin wrapper around the kagura-engineer doctor CLI verb. It is the precondition gate that the run / review skills run before doing any work — and you can invoke it on its own to check the environment.

Announce: "Using the kagura-engineer:doctor skill to check the harness environment."

Usage: kagura-engineer:doctor — no arguments. Pass --config <path> only if repo.yaml is not in the current directory.

This skill reimplements nothing. It shells out to the installed CLI and surfaces the result. If kagura-engineer is not on PATH, tell the user to install it (uv tool install kagura-engineer or pip install kagura-engineer) and stop.

Steps

Discover config. The CLI reads repo.yaml from the current directory by default. If the user named a different file, pass it through with --config. There is no search path — repo.yaml must be in CWD or given explicitly.
Run the check (machine-readable):
```
kagura-engineer doctor --json
```
Capture stdout (a single JSON document) and the exit code.

Interpret the exit-code contract:

Exit	`overall`	Meaning
0	`ok` / `warn`	Safe to proceed. `warn` items are advisory (e.g. missing ollama model, cloud credential unverified).
1	`fail`	Must stop. At least one blocking check failed.
A missing or invalid `repo.yaml` is represented as a synthetic `config`
failure alongside the config-free checks, so it exits `1` rather than `2`.

Surface the result. Print the per-check name / status / detail / fix_hint table from the JSON. Lead with the blocking (fail) checks.
Hand off. If overall == "fail", suggest kagura-engineer:setup to repair the environment, then re-run this skill. If overall is ok/warn, the caller may proceed to kagura-engineer:run or kagura-engineer:review.

Plus depuis ce dépôt

même dépôt

setup

kagura-ai/kagura-engineer

Use when kagura-engineer:doctor reports a blocked or failing environment — scaffolds missing config, installs and authenticates harness prerequisites, and generates Memory Cloud MCP config by shelling out to `kagura-engineer setup`, then re-checks with doctor.

2026-07-160

eval

kagura-ai/kagura-engineer

Use to measure whether memory grounding actually improves PR quality — shells out to `kagura-engineer eval` with one or more issue numbers, running the SAME fixed issue set in two arms (recall ON vs OFF) and printing an A/B table. HARNESS — high cost; it runs the full loop twice per issue and mutates the repo. Confirm with the user before launching.

2026-07-150

review

kagura-ai/kagura-engineer

Use to review a git ref, branch, or PR with the local kagura-engineer reviewer — shells out to `kagura-engineer review [target]`, returning a structured verdict and findings. With `--fix` it is a HARNESS that edits files and commits; without `--fix` it is read-only.

2026-07-150

run

kagura-ai/kagura-engineer

Use to drive a single GitHub issue to a pull request with the kagura-engineer harness — shells out to `kagura-engineer run` with an issue number (guard → recall → worktree → start → implement → ship → persist). HARNESS — this mutates the repo, creates a PR, and spends model budget; confirm with the user before launching.

2026-07-150

init

kagura-ai/kagura-engineer

Use to bootstrap a fresh checkout for the kagura-engineer harness — scaffolds a commented repo.yaml template and adds it to .gitignore by shelling out to `kagura-engineer init`. Run this before setup/run/review when no repo.yaml exists yet. Idempotent and never overwrites.

2026-06-160

name	doctor
description	Use before any kagura-engineer run/review, or when the harness reports a blocked environment — diagnoses the local setup (git, selected brain CLI, gh, ollama, memory backend, and gh-issue-driven plugin) by shelling out to `kagura-engineer doctor` and reports what must be fixed.

kagura-engineer: doctor

Announce: "Using the kagura-engineer:doctor skill to check the harness environment."

Usage: kagura-engineer:doctor — no arguments. Pass --config <path> only if repo.yaml is not in the current directory.

Steps

Discover config. The CLI reads repo.yaml from the current directory by default. If the user named a different file, pass it through with --config. There is no search path — repo.yaml must be in CWD or given explicitly.
Run the check (machine-readable):
```
kagura-engineer doctor --json
```
Capture stdout (a single JSON document) and the exit code.

Interpret the exit-code contract:

Exit	`overall`	Meaning
0	`ok` / `warn`	Safe to proceed. `warn` items are advisory (e.g. missing ollama model, cloud credential unverified).
1	`fail`	Must stop. At least one blocking check failed.
A missing or invalid `repo.yaml` is represented as a synthetic `config`
failure alongside the config-free checks, so it exits `1` rather than `2`.

Surface the result. Print the per-check name / status / detail / fix_hint table from the JSON. Lead with the blocking (fail) checks.
Hand off. If overall == "fail", suggest kagura-engineer:setup to repair the environment, then re-run this skill. If overall is ok/warn, the caller may proceed to kagura-engineer:run or kagura-engineer:review.