CtrlK
BlogDocsLog inGet started
Tessl Logo

peon-ping-create-pack

Internal — invoked headlessly by `peon create`; humans should run `peon create` instead. Author and render a brand-new PeonPing draft pack — invoked headlessly as: "Use the peon-ping-create-pack skill to draft a pack: name=<n> flavor=<f> vibe=<v> draft_root=<dir>. Follow the skill exactly." Authors all 7 CESP categories honoring the vibe, writes openpeon.json (draft-stamped) and prompts.json, renders every sound via scripts/pack-render.py, and always ends by telling the human to run `peon eval <name>`.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable procedure with strong validation checkpoints for a batch render operation. The only real slack is minor conciseness tightening and the absence of any progressive-disclosure file structure to organize.

Suggestions

Tighten the discursive coaching in step 3 (e.g. the 'calm bells implies soft chimes…' aside) to a one-line rule so the body leans further toward token efficiency.

Consider extracting the CESP category list and job/manifest JSON schemas into a references/ file referenced one level deep, which would improve progressive_disclosure organization.

Add an explicit render-failure retry loop (fix -> re-render) rather than only stop-and-defer, to move workflow_clarity's error recovery from a checkpoint to a full feedback loop.

DimensionReasoningScore

Conciseness

The body is dense and instruction-focused with no padding about concepts Claude already knows, but a few passages (e.g. the vibe/aesthetic coaching in step 3 and the mock rationale) could be tightened slightly, so it is efficient rather than fully lean.

4 / 5

Actionability

It gives copy-paste-ready commands (`python3 <peon-ping>/scripts/pack-render.py --job <file>`, `--mock`), explicit JSON job/manifest shapes, concrete path layouts, and a validation regex, fully covering the common render and author cases.

5 / 5

Workflow Clarity

The eight-step procedure has explicit validation checkpoints — STOP on an existing draft_dir, STOP and print stderr on any render failure, preserve partial output for retry — plus a final `peon eval` gate, so the batch-operation cap at 3 does not apply.

5 / 5

Progressive Disclosure

The skill has no bundle files and is a single well-sectioned SKILL.md with no content that clearly belongs in a separate file; structure is good but, at over 50 lines with no external references to signal, it sits just below the clean-overview anchor.

4 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that states concrete actions and an explicit headless trigger, clearly scoping a distinct internal skill. Slight room remains for more natural-language trigger synonyms alongside the jargon.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — author a concept across all 7 CESP categories, write openpeon.json and prompts.json, render every sound via scripts/pack-render.py, end with a peon eval instruction — giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

It explicitly answers both 'what' (author and render a draft pack across 7 categories, write the two manifests) and 'when' (invoked headlessly by `peon create` with a concrete quoted trigger), so the missing-trigger cap at 3 does not apply.

5 / 5

Trigger Term Quality

The embedded trigger 'Use the peon-ping-create-pack skill to draft a pack: name=… flavor=… vibe=… draft_root=…' gives good keyword coverage, but the terms are domain jargon with few natural synonyms a user would voice, so it stops short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (drafting a brand-new PeonPing pack) with a highly specific trigger string, distinguishing it from the sibling remix and brand-to-peon-packs skills and minimizing wrong-skill activation.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PeonPing/peon-ping
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.