Skip to content
Skills Library
Programming · Review & audit

cli-for-agents

/cli-for-agents

Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI: use control-cli.

Licence
Apache-2.0
Last repository change
28.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 28.09.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI: use control-cli.

Original author description

Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI: use control-cli.

How it works

  1. Contract
  2. Inputs
  3. Procedure
  4. Failure and recovery
  5. Output
Original SKILL.md headings · 37 lines, 644 words
SKILL.md preview
---
name: cli-for-agents
description: 'Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI: use control-cli.'
---

# CLI for agents

## Contract

| Field | Bound contract |
|---|---|
| Trigger | Human asks to build or review a CLI intended for coding agents |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Advice or review only. |
| Side effect | Chat output only: design advice or review findings. |
| Done | A report returned that prescribes flag-driven, pipeline-safe, idempotent CLI design. |

## Inputs

- A CLI to review, or a build request describing the CLI's purpose and target agent runtime. Either is sufficient; both may be supplied.
- Optional: existing command surface, flag set, exit-code map, or invocation examples. When absent, state the assumption and review against the design rules below.

## Procedure

1. Bound scope: confirm whether this is a build (propose a design) or a review (judge an existing CLI). Do not mutate the CLI or any file; produce advice only. Done when: build or review intent is confirmed and stated in the report.
2. Enumerate the command surface the agent will invoke: subcommands, flags, positional args, stdin, stdout, stderr, and exit codes. Done when: the full surface is listed or the missing surface is named.
3. Check flag-driven control: every behavioral switch is a flag or subcommand, not an interactive prompt that blocks on a TTY. Flag names are stable, long-form, and discoverable via `--help`. Reject hidden modes toggled only by interactive input. Done when: every switch is a flag or subcommand, or each violation is recorded.
4. Check pipeline safety: output meant for machine consumption goes to stdout as plain, parseable text; human diagnostics go to stderr. The CLI never hangs waiting on a TTY when stdin is not a terminal. Exit codes are explicit and documented: 0 success, non-zero for distinct failure classes. Done when: stdout/stderr split and exit-code map are verified, or violations are recorded.
5. Check idempotence: re-running the same invocation with the same inputs produces the same result and side effects, or fails loudly with a non-zero exit when the operation is not safely repeatable. Done when: each state-changing command declares idempotence or names what makes a repeat unsafe.
6. Check agent ergonomics: deterministic output ordering, no color or progress decoration on stdout unless explicitly flagged on, machine-readable `--json` or equivalent where the agent parses output, and a single canonical invocation form per action. Done when: all four ergonomics rules pass or each violation is recorded.
7. For a build request, propose the command surface, flag set, exit-code map, and stdout/stderr contract that satisfy rules 3-6. For a review, record each violation against the rule it breaks and prescribe the fix. Done when: the proposed surface or the per-violation fix list is complete.
8. Stop at the report. Do not edit the CLI, run it, or widen scope into implementation, testing, or packaging. Done when: the report is returned and no file was mutated.

## Failure and recovery
- Ambiguous build-vs-review intent: ask once for the missing input; if unresolved, default to review when a CLI is supplied and build when only a purpose is supplied, and state the assumption in the report.
- Missing command surface for a review: state that the surface could not be enumerated and limit findings to the rules checkable from what was supplied; do not invent a surface.
- Contradictory requirements (e.g., a required interactive prompt): report the contradiction and the rule it violates; do not silently relax a rule to make the CLI pass.
- No partial mutation: this skill never changes files, so there is no rollback. A blocked review returns the findings gathered so far plus the named blocker, never a clean bill of health.

## Output
Chat report: command surface → per-rule verdicts (flag-driven, pipeline-safe, idempotent, ergonomic) → prescribed fixes or proposed surface, flag set, exit-code map, stdout/stderr contract. Chat output only.
Files in this package (2)
  • SKILL.md 4 KB
  • agents/openai.yaml 1 KB

Versions

RepositoryScoreLicence
This page · OutlineDriven/outline-driven-development100Apache-2.0
heyAyushh/stacc100MIT
pproenca/dot-skills100MIT
v1truv1us/ai-eng-system100MIT
v1truv1us/ai-eng-system100MIT

Database snapshot: 13.11.2026 · package version 6917c0965288 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90control-cli
    Use when asked to reproduce, profile, or verify CLI/TUI behavior. Produces a deterministic transcript or profile proof with session cleanup. Not for CLI design advice, use cli-for-agents.
  • 100cli-design
    AI 友善的 CLI 設計與稽核(判準取自 Cloudflare `cf` CLI)。 Use when 新寫 CLI、新增或改動命令與旗標、稽核既有 CLI 對 agent 友不友善。 NOT for CLI 壞掉找原因(diagnose)、shell script 的 sudo/trap 安全、只是用某支 CLI 完成任務。
  • 100control-cli
    Build a local harness to drive, inspect, and profile an interactive CLI or TUI. Use for CLI UX checks, startup regressions, hangs, or prompt-flow verification.
  • 100cli-review-runner
    Black-box CLI grading harness — runs a test suite against a target CLI and reports per-rule pass/fail from the cli-for-agents 45-rule catalog. Use when reviewing, auditing, or grading a command-line tool for agent-friendliness. Trigger even if the user doesn't explicitly say…
  • 100agents-md
    Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.
  • 96tm-cli
    Use if and only if you use tm-cli (the Telemetry Machine CLI).

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.