Skills for Real Engineers. Straight from my .agents directory.
deliver
Agent skill fromsno-ai/sno-station-skills
Carry out a released charter to a proven result: plan only as much as the work needs, do the work through the project's own workers, prove every success check with a recorded real run, get one independent review, and close honestly. Invoke explicitly as `$deliver <charter>` (Codex) or `/deliver <charter>` (Claude, Cursor), or the way your agent invokes a skill, or when a dispatch names you the executor of a charter.
How to install deliver
npx skills add sno-ai/sno-station-skills# or add only this skill to Claude Code: copy the folder
skills/T-delegation-and-work-orders/deliver/skill/
# into
~/.claude/skills/skill/ (all projects)
.claude/skills/skill/ (one project)
1# deliver23Carry out the named charter. Its `## Success checks` are the definition of done; nothing else4is. Read the whole charter and the existing work first. The owner (whoever owns the work,5often the user) can override this skill and any plan an agent wrote. Any kind of project uses6it: for code and tests also read `references/proof.md`.78Prerequisites: `sno deliver-proof` needs bash 4+ and GNU coreutils (Linux) and prints one message9and stops when they are missing; its selftest also needs python3. On macOS, install bash 4+ and10GNU coreutils (for example with Homebrew) and put them first on PATH. If `sno deliver-proof` is not11available, run `scripts/deliver-proof` from this skill's folder instead.1213## Keep the work useful1415- Before adding a prerequisite, test, record or approval step, name the requested result it16 proves and what changes if it fails. If nothing changes, leave it out.17- Check an uncertain fact by reading or calling what exists. If checking needs something built18 first, building it is the first task, not a permission gate.19- Records, telemetry, formatting, identifiers, checksums and review sign-offs never block the20 work. Log the failed action, its place and the actual error, and continue. Do not turn such21 a failure into an assertion, a silent return or a swallowed error. If the main operation22 fails, say so with its cause; never report success. Stop only what cannot proceed and keep23 independent work moving.24…
Excerpt shown under the repository's Apache-2.0 license.
More skills in sno-station-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
