createcli

Other Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: | Use when this capability is needed. | Task | Stack | Reason | |------|-------|--------| | Files, glob, regex, JSON piping | ba…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Stack choice”, “Anatomy (TypeScript default)”, “Anatomy (bash)”, “Rules”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name createcli directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Stack choice / Anatomy (TypeScript default) / Anatomy (bash)” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

CreateCLI

Role: quick CLI authoring for ~/.claude/scripts/.

Stack choice

Task	Stack	Reason
Files, glob, regex, JSON piping	bash	Fastest if < 50 lines
Anything complex, types, JSON handling	TypeScript (bun)	Default
Data-heavy operations, ML libraries	Python (uv)	Library access

Anatomy (TypeScript default)

#!/usr/bin/env bun
/**
 * [scriptname] — [short description]
 *
 * Usage: [scriptname] [args] [flags]
 *
 * Created: 2026-MM-DD via createcli skill
 */

import { parseArgs } from 'util';

const { values, positionals } = parseArgs({
  args: process.argv.slice(2),
  options: {
    'dry-run': { type: 'boolean', default: true },  // destructive: default ON
    'verbose': { type: 'boolean', short: 'v' },
    'help': { type: 'boolean', short: 'h' },
  },
  allowPositionals: true,
});

if (values.help) {
  console.log(`[scriptname] — [description]

Usage:
  [scriptname] [args]

Flags:
  --dry-run     Show what would happen without doing it (default: ON for destructive)
  --verbose     More detailed output
  --help        This text
`);
  process.exit(0);
}

// ... core logic

Anatomy (bash)

#!/usr/bin/env bash
set -euo pipefail

usage() {
  cat <<EOF
[scriptname] — [description]

Usage: [scriptname] [args]

Flags:
  -n, --dry-run    Show what would happen
  -v, --verbose    More detailed output
  -h, --help       This text
EOF
}

DRY_RUN=true  # destructive default
while [[ $# -gt 0 ]]; do
  case "$1" in
    -n|--dry-run) DRY_RUN=true; shift ;;
    --no-dry-run) DRY_RUN=false; shift ;;
    -v|--verbose) VERBOSE=true; shift ;;
    -h|--help) usage; exit 0 ;;
    *) ARGS+=("$1"); shift ;;
  esac
done

# core logic

Rules

Destructive = dry-run default ON. Must use explicit --no-dry-run to execute.
Log to ~/.claude/logs/[scriptname].jsonl for an audit trail when relevant (file-modifying, network-fetching, API calls).
chmod +x after Write — exec bit must be set.
--help is mandatory — show it even when no args.
Never hardcode credentials — read from ~/.claude/.env.
Output in markdown if the script produces a text report (not tabular).

Workflow

1. The user describes: "I need a script that [X]"
2. Choose stack (bash/TS/Python) per the table above
3. Create the anatomy template
4. Implement core logic
5. chmod +x ~/.claude/scripts/[scriptname]
6. Test: ./scripts/[scriptname] --help
7. Test: ./scripts/[scriptname] --dry-run [args]
8. Report to user: what the script does + examples

Version history

v3.0 (2026-05-02): initial public release.

Source: carlheath/ogmios — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Other
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: macOS · Linux · Windows
Runtime requirements: Python
Detected file/system behavior: Read-only
Write / modify
Shell exec
Env read
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview createcli.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# CreateCLI

**Role:** quick CLI authoring for `~/.claude/scripts/`.

## Stack choice

| Task | Stack | Reason |
|------|-------|--------|
| Files, glob, regex, JSON piping | bash | Fastest if < 50 lines |
| Anything complex, types, JSON handling | TypeScript (bun) | Default |
| Data-heavy operations, ML libraries | Python (uv) | Library access |

## Anatomy (TypeScript default)

```typescript
#!/usr/bin/env bun
/**
 * [scriptname] — [short description]
 *
 * Usage: [scriptname] [args] [flags]
 *
 * Created: 2026-MM-DD via createcli skill
 */

import { parseArgs } from 'util';

const { values, positionals } = parseArgs({
  args: process.argv.slice(2),
  options: {
    'dry-run': { type: 'boolean', default: true },  // destructive: default ON
    'verbose': { type: 'boolean', short: 'v' },
    'help': { type: 'boolean', short: 'h' },
  },
  allowPositionals: true,
});

if (values.help) {
  console.log(`[scriptname] — [description]

Usage:
  [scriptname] [args]

Flags:
  --dry-run     Show what would happen without doing it (default: ON for destructive)
  --verbose     More detailed output
  --help        This text
`);
  process.exit(0);
}

// ... core logic
```

## Anatomy (bash)

```bash
#!/usr/bin/env bash
set -euo pipefail

usage() {
  cat <<EOF
[scriptname] — [description]

Usage: [scriptname] [args]

Flags:
  -n, --dry-run    Show what would happen
  -v, --verbose    More detailed output
  -h, --help       This text
EOF
}

DRY_RUN=true  # destructive default
while [[ $# -gt 0 ]]; do
  case "$1" in
    -n|--dry-run) DRY_RUN=true; shift ;;
    --no-dry-run) DRY_RUN=false; shift ;;
    -v|--verbose) VERBOSE=true; shift ;;
    -h|--help) usage; exit 0 ;;
    *) ARGS+=("$1"); shift ;;
  esac
done

# core logic
```

## Rules

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Stack choice → Anatomy (TypeScript default) → Anatomy (bash) → Rules → Workflow → Version history
terms    -> Role · Destructive = dry-run default ON. · Log to ~/.claude/logs/[scriptname].jsonl · chmod +x · --help is mandatory · Never hardcode credentials · Output in markdown
files/cmd -> ~/.claude/scripts/ · --no-dry-run · ~/.claude/logs/[scriptname].jsonl · chmod +x · --help · ~/.claude/.env
body sha256 -> 2ca416a45bf7