ponytail

External agent skill (MIT, github.com/DietrichGebert/ponytail). Forces the laziest solution that actually works: question whether the task needs to exist at all (YAGNI), reuse what is already in the codebase, reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Climb the ladder on every coding task — writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Supports intensity levels: lite, full (default), ultra. Never cut validation, error handling, security, or accessibility.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ponytail/SKILL.md

Quality

Content

75%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.

The body is a well-structured, actionable coding-philosophy skill with a concrete ladder, clear intensity levels, and real examples; it assumes Claude's intelligence and stays mostly lean. Its main weaknesses are a redundant duplicated frontmatter block and validation feedback loops that are implied rather than explicit.

Suggestions

Remove or de-duplicate the inner frontmatter block (lines 9-26) — it repeats the description and adds token cost without new guidance for the body.

Make the validation feedback loop explicit in the self-check section (e.g., 'run the check -> if it fails, fix the logic -> re-run') to push workflow clarity higher.

Trim the hardware/calibration aside unless it earns its place for the core coding audience; it reads as tangential to the ladder.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — the ladder, rules, and intensity table are tight and punchy, with most tokens earning their place. Not a 5 because of the duplicated inner frontmatter block (lines 9-26) and a few personality-prose passages ('been paged at 3am', the hardware/calibration digression) that could be trimmed.	4 / 5
Actionability	Concrete executable guidance throughout: the seven-rung ladder, the `ponytail:` comment convention with a real example (`# ponytail: global lock, per-account locks if throughput matters`), and the lru_cache example shown at all three intensity levels with copy-pasteable code. Not a 5 because some guidance stays at the principle level rather than giving runnable snippets for the common cases.	4 / 5
Workflow Clarity	Clear sequence — 'Stop at the first rung that holds' rungs 1-7 — with explicit checkpoints: 'trace the real flow end to end, then climb', 'grep every caller' for bug fixes, and the ONE-runnable self-check. Not a 5 because the validation feedback loop (check -> fix -> re-check) is implied rather than spelled out as an explicit retry cycle.	4 / 5
Progressive Disclosure	No bundle files exist, and the single SKILL.md is well-organized into clearly headed sections (Persistence, The ladder, Rules, Output, Intensity, When NOT to be lazy, Boundaries) with no nested references. Not a 5 because the body exceeds 50 lines and contains an odd duplicated frontmatter block, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

52%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.

The description explains what the skill does with strong, concrete specificity, but its trigger guidance and 'when to use' framing are weak — the natural trigger phrases exist only in the body's duplicate frontmatter, not in the canonical frontmatter description. Distinctiveness is undercut by an over-broad 'every coding task' scope.

Suggestions

Move the explicit trigger phrases ('be lazy', 'lazy mode', 'simplest solution', 'minimal solution', 'yagni', 'do less', 'shortest path') into the frontmatter description via a 'Use when...' clause so the canonical field carries its own trigger guidance.

Tighten 'on every coding task' to a more specific trigger condition (e.g., 'Use when the user wants the minimal/simpler solution or complains about over-engineering, bloat, or boilerplate') to reduce overlap with general coding skills.

Keep the concrete action list and intensity levels — they are the strongest part of the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the coding domain — 'question whether the task needs to exist at all (YAGNI)', 'reuse what is already in the codebase', 'reach for the standard library before custom code', 'native platform features before dependencies', 'one line before fifty', plus the full task list (writing, adding, refactoring, fixing, reviewing, designing, choosing libraries). Comprehensive coverage of what the skill does; not the level below (4) because the action set is broad and specific rather than having minor gaps.	5 / 5
Completeness	Clearly answers 'what' (forces the minimal working solution, climbs a ladder of reuse) but 'when' is only weakly implied via 'on every coding task' with no explicit 'Use when...' trigger clause; per the guideline a missing explicit trigger clause caps completeness at 3. Not a 4 because there is no concrete trigger phrase guidance.	3 / 5
Trigger Term Quality	Only 'YAGNI' and 'laziest solution' read as natural user phrasing; the explicit natural trigger list ('be lazy', 'lazy mode', 'simplest solution', etc.) lives in the body's duplicate frontmatter, not in this field. Not a 3 because common synonyms and the phrases users would actually say are absent from the frontmatter description itself.	2 / 5
Distinctiveness Conflict Risk	The lazy-minimalism framing is a recognizable niche, but 'Climb the ladder on every coding task' is so broad it would overlap with most general coding skills, raising conflict risk. Not a 4 because the every-coding-task scope keeps meaningful overlap with sibling skills.	3 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: diegosouzapw/OmniRoute
Path: skills/ponytail/SKILL.md
Commit: c3945a7

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.