Cry: Skill Cycle (implement/validate/package)

VerifiedSafe

Shortcut to invoke warrior-claudionor and run the implement → validate → package cycle of an Anthropic Agent Skills project.

Sby Skills Guide Bot
DevelopmentIntermediate
7/24/2026
Claude Code
#skill-cycle#claudionor#skill-authoring#automation#agent-skills

Recommended for

Automated summary

Runs the full implement → validate → package cycle of an Agent Skills project by invoking warrior-claudionor.

Strengths

  • Automates the entire lifecycle of an Agent Skill in a single command, from implementation to distribution.
  • Integrates delegations to Hephaestus (widgets) and Apollo (Python tools/scripts) during implementation.
  • Dry-run mode lets you preview the plan without making any changes.
  • Aborts on validation failures, ensuring only valid packages are produced.

Limitations

  • Requires the project to already exist under paths.skills_root and .ahrena/.directives to be properly configured.
  • Depends on external warriors (claudionor, hephaestus, apollo) being available in the environment.
  • Does not handle initial project scaffolding or setup beyond the implement phase.
When to use it

Use this skill to consistently and efficiently manage the development cycle of an Agent Skills project.

When not to use it

Do not use it for general software development or when you need fine-grained control over each step outside the warrior framework.

Security analysis

Safe
Quality score92/100

The skill is a pure specification file describing a command interface and workflow orchestration. It contains no executable code, no system commands, no network calls, and no instructions that could cause harm. It is entirely descriptive and declarative.

No concerns found

How this analysis is made

Examples

Full cycle for a skill
/cry-skill --mode all --slug scheduled-payments-skill
Validation only
/cry-skill --mode validate --slug scheduled-payments-skill
Dry-run packaging
/cry-skill --mode package --slug scheduled-payments-skill --dry-run

Implementation only (continue where we left off). Shortcut to invoke warrior-claudionor and run the implement → validate → package cycle of an Anthropic Agent Skills project

Cry: Skill Cycle (implement / validate / package)

Prefix: cry- | Type: Recurring Command | Scope: Shortcut to invoke warrior-claudionor and run the implement → validate → package cycle of an Anthropic Agent Skills project

Invocation

/cry-skill --mode <implement|validate|package|all> --slug <name> [--dry-run]

Parameters

| Parameter | Required | Description | Example | |-----------|:--------:|-------------|---------| | --mode | Yes | Cycle phase to run: implement (authoring with delegation), validate (deterministic check), package (build → dist + manifest), or all (chains the three) | --mode all | | --slug | Yes | Project name (identical to the directory name in {paths.skills_root}/) | --slug scheduled-payments-skill | | --dry-run | No | Presents the plan without persisting changes to {paths.skills_build}/, {paths.skills_dist}/, or the project | --dry-run |

If --dry-run is passed with --mode package, the final package is not written — only the report of what would be produced.

What the Command Does

  1. Resolves paths.skills_root/skills_build/skills_dist from .ahrena/.directives
  2. Confirms the project exists at {paths.skills_root}/{slug}/
  3. Invokes warrior-claudionor passing mode, slug, and dry_run
  4. Claudionor dispatches to the kata(s):
    • --mode implement → kata-skill-implement (delegates widgets to Hephaestus, Python tools/scripts to Apollo, authors SKILL.md/references/)
    • --mode validate → kata-skill-validate (checks lex-skill-project-structure)
    • --mode package → kata-skill-validate (precondition) + kata-skill-package (build → dist + manifest validated against lex-skill-package-structure)
    • --mode all → chains the three; aborts on the first error
  5. Reports the final result (produced paths, file count, violations)

Prompt Template

Context:
- mode: {{mode}}             # implement | validate | package | all
- slug: {{slug}}
- dry_run: {{dry_run}}        # default false

Task:
Invoke warrior-claudionor with the parameters above. The warrior:
1. Reads .ahrena/.directives (paths.skills_*) and verifies skills/{slug}/ exists
2. Dispatches to the kata(s) per `mode`
3. In `package` and `all`, aborts if kata-skill-validate returns `error`
4. In `implement`, delegates via Agent to warrior-hephaestus (widgets)
   and warrior-apollo (Python tools/scripts); authors SKILL.md and
   references/ in-house
5. Reports produced paths, file count, and violations by severity

Abort if: slug does not exist under paths.skills_root, mode is invalid,
or .ahrena/.directives is missing.

Output format:
Structured report per phase (implement / validate / package) with
named delegations and final state. On error, identify the kata + the
violated rule and the remediation step.

Sample Invocations

# Full cycle: identifies gaps, implements, validates, and packages
/cry-skill --mode all --slug scheduled-payments-skill

# Deterministic validation only (CI or pre-commit)
/cry-skill --mode validate --slug scheduled-payments-skill

# Packaging only (after manual development)
/cry-skill --mode package --slug scheduled-payments-skill

# Preview of what would be packaged, without writing under .dist/
/cry-skill --mode package --slug scheduled-payments-skill --dry-run

# Implementation only (continue where we left off)
/cry-skill --mode implement --slug scheduled-payments-skill

Expected output (--mode all on success):

🛠  warrior-claudionor — full cycle for 'scheduled-payments-skill'

Phase 1/3 — kata-skill-implement
  Delegations: Hephaestus (widgets), Apollo (tools + scripts)
  Files produced: 4 widgets, 2 handlers, 1 test
  SKILL.md + references/ updated

Phase 2/3 — kata-skill-validate
  ✅ no violations

Phase 3/3 — kata-skill-package
  ✅ package: .dist/scheduled-payments-skill.skill (18 files)

Restrictions

  • The Cry does not modify .ahrena/.directives or framework/
  • The Cry does not act without an existing project at {paths.skills_root}/{slug}/; to create a new one, use cry-new-skill
  • The Cry does not create branches, worktrees, or commits — versioning discipline stays with the user (lex-issue-first, lex-git-worktrees, lex-pr-quality)
  • Human messages in the language set by language.default; technical identifiers (slug, modes, paths) preserved

Difference from Kata

| Aspect | Cry | Kata | |--------|-----|------| | Nature | Shortcut that collects --mode + --slug and dispatches | Complete procedure (validate/package/implement, individually) | | Validation | Parameter shape | Phase logic, including delegations | | Effect | Invokes warrior-claudionor | Reads/writes filesystem, delegates, or runs script |

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/cry-skill-cycle-implement-validate-package-mrwake3r/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/cry-skill-cycle-implement-validate-package-mrwake3r' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/cry-skill-cycle-implement-validate-package-mrwake3r/download' --output '.skill-downloads/cry-skill-cycle-implement-validate-package-mrwake3r/SKILL.md.part' && mv '.skill-downloads/cry-skill-cycle-implement-validate-package-mrwake3r/SKILL.md.part' '.skill-downloads/cry-skill-cycle-implement-validate-package-mrwake3r/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/cry-skill-cycle-implement-validate-package-mrwake3r/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills