kild-cli

kild-cli is an Agent task delegation & fan-out skill for AI agents, published by Wirasm in the kild repository on GitHub. Skillspace rates kild-cli D (55/100) and it passed the safety scan; the rating is based on static analysis only.

Drive the kild CLI to run pi coding agents as one-shot tasks and to manage the projects and agents they use. `kild run` spawns an AI coding agent (pi), drives it to completion in a directory, and returns its result — text, tools used, and token/cost stats — as JSON. USE THIS SKILL when you need to: - Delegate a self-contained task to a sub-agent: "use kild to ...", "spawn an agent to ...", "run a kild agent", "have a kild agent do ..." - Run a task with a specialized agent (a planner, reviewer, ...) in a project - Manage kild projects: "list/add/remove kild projects" - List or inspect kild agents (named system prompts) kild is CLI-first and scriptable. Read commands print to stdout (pass `--json` for machine-readable output); progress and errors go to stderr; a non-zero exit code means failure. Parse stdout, check the exit code. Prerequisite: `pi` must be on PATH and authenticated. This skill drives the kild engine CLI: from `engine/`, run `bun run cli -- <args>` (or the linked `kild`…

Grade
D
Quality
55 / 100
Safety
Passed
GitHub stars
62

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.