Ponytail Lazy Developer Mode
DietrichGebert/ponytail
Makes the agent pick the laziest solution that works: skip unneeded work, reuse what exists, prefer the standard library and platform features, and keep diffs small.
Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation.
Install Skill Distiller
$ npx skills add Mathews-Tom/armory --skill skill-distiller -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Mathews-Tom/armory skill-distiller --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-distiller .claude/skills/skill-distiller && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-distiller" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distiller into .claude/skills/skill-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-distiller", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distillerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Mathews-Tom/armory --skill skill-distiller -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Mathews-Tom/armory skill-distiller --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-distiller .agents/skills/skill-distiller && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-distiller" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distiller into .agents/skills/skill-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-distiller", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Mathews-Tom/armory --skill skill-distiller -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Mathews-Tom/armory skill-distiller --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-distiller .cursor/skills/skill-distiller && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-distiller" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distiller into .cursor/skills/skill-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-distiller", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Mathews-Tom/armory.git --path skills/skill-distiller--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Mathews-Tom/armory --skill skill-distiller -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Mathews-Tom/armory skill-distiller --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-distiller .gemini/skills/skill-distiller && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-distiller" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distiller into .gemini/skills/skill-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-distiller", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Mathews-Tom/armory skill-distillerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Mathews-Tom/armory --skill skill-distiller -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-distiller .github/skills/skill-distiller && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-distiller" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distiller into .github/skills/skill-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-distiller", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Mathews-Tom/armory --skill skill-distiller -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Mathews-Tom/armory skill-distiller --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-distiller .opencode/skills/skill-distiller && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-distiller" agent skill from https://github.com/Mathews-Tom/armory/tree/main/skills/skill-distiller into .opencode/skills/skill-distiller/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-distiller", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-distiller- GitHub stars
- 329
- Token cost
- ~2k tokens
- SKILL.md length
- 726 words
- Files
- 3 (incl. references)
- Skills in repo
- 80
- Repo updated
- First seen
- Licence
- MIT
At a glance
Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation.
- Works in 6 steps: Complexity Analysis → Trace Collection → Pattern Extraction → …
- : distill this skill
- SKILL.md covers Reference Files, Prerequisites, Workflow and Error Handling, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Skill Distiller is an agent skill from Mathews-Tom/armory. Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation. Triggers on: "distill this skill", "make this skill work on Haiku", "cross-model optimization", "optimize skill for cost". NOT for code simplification, use code-refiner.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `evals/cases.yaml` and `references/distillation-patterns.md`).
It sits in Development, covering Code simplification. The repository describes itself as: Curated, production-grade skills for AI coding agents. Battle-tested workflows for developers who use AI seriously. The licence is MIT.
When your agent uses it
- : distill this skill
- Make this skill work on Haiku
- Cross-model optimization
- Optimize skill for cost
Example prompts
- “distill this skill”
- “make this skill work on Haiku”
- “cross-model optimization”
- “/skill-distiller”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4594fb7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skill Distiller loads about 2k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 726 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Mathews-Tom/armory at commit 4594fb7, republished under its MIT licence (© Mathews-Tom). 726 words, ~2,045 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-distiller/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- skill-distiller
- description
- Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation. Triggers on: "distill this skill", "make this skill work on Haiku", "cross-model optimization", "optimize skill for cost". NOT for code simplification, use code-refiner.
- metadata.version
- 1.0.1
- metadata.category
- development
- metadata.tags
- distillation, cross-model, optimization, haiku, deterministic
- metadata.difficulty
- advanced
- metadata.phase
- build
Skill Distiller
Transform skills authored for high-capability models (Opus) into deterministic workflows that execute reliably on lower-cost models (Sonnet, Haiku). The core insight from EvoSkills: skills encode reusable task structure, not model-specific artifacts. A skill evolved on Opus transfers with +35-45pp gains to other models — but only when the instructions are sufficiently deterministic that lower-capability models can follow them without improvising.
Reference Files
| File | Contents | Load When |
|---|---|---|
references/distillation-patterns.md | Pattern catalog for converting reasoning to rules | Always |
Prerequisites
- The source skill must exist and pass
package-evaluatorat >= 70% - Access to both the source model (Opus) and target model (Haiku/Sonnet) for validation
- The
surrogate-verifierskill for cross-model assertion checking
Workflow
Phase 1: Complexity Analysis
Score each section of the source SKILL.md for reasoning difficulty:
| Complexity Signal | Score | Distillation Action |
|---|---|---|
| Decision tree with 3+ branches | HIGH | Convert to explicit if/then lookup table |
| "Use judgment" or "consider context" | HIGH | Replace with concrete heuristic rules |
| Multi-step inference chain | HIGH | Break into numbered atomic steps |
| Reference to domain expertise | MED | Add explicit reference file with knowledge |
| Clear enumerated steps | LOW | Keep as-is |
| Concrete examples with expected output | LOW | Keep as-is |
Produce a complexity map: section name -> complexity score -> planned action.
Phase 2: Trace Collection
Execute the source skill with Opus on 5 representative tasks:
- Select tasks from
evals/cases.yaml(positive cases) or generate new ones - For each task, capture the full execution trace:
- Tool calls made (which tools, in what order)
- Intermediate reasoning visible in output
- Final output structure and content
- Time taken and token usage
- Store traces as structured data for pattern extraction
Phase 3: Pattern Extraction
From the collected traces, extract deterministic patterns:
- Decision paths — For each HIGH-complexity section, find the actual decisions Opus made across the 5 tasks. If Opus chose the same path in 4/5 cases, that path becomes the default rule
- Lookup tables — Where Opus applied domain knowledge, build explicit lookup tables (e.g., "if input contains SQL, use these patterns; if input contains Python, use those")
- Concrete examples — Extract representative input/output pairs from traces to serve as few-shot examples in the distilled skill
- Tool sequences — Identify the common tool invocation pattern and make it explicit ("Step 1: Read the file. Step 2: Grep for pattern X. Step 3: Write output.")
Show full SKILL.md (351 more words)Show less
Phase 4: Distilled Rewrite
Rewrite the SKILL.md applying all distillation actions from Phase 1:
| Source Pattern | Distilled Replacement |
|---|---|
| "Analyze the code and determine..." | "Check for these 5 specific patterns: [list]" |
| "Use appropriate formatting" | "Output as a markdown table with columns: [A, B, C]" |
| "Consider the context to decide..." | "If [condition A]: do X. If [condition B]: do Y. Default: Z" |
| "Apply best practices for..." | Reference file with explicit best practices enumerated |
| Multi-paragraph reasoning instruction | Numbered step list with single-sentence steps |
Rules for the rewrite:
- Every instruction must be actionable by a model with no domain expertise
- No step should require inference — each step's input and output must be explicit
- Replace all "consider", "analyze", "determine" verbs with "check", "count", "list", "output"
- Add concrete examples for any step that could be ambiguous
- Keep the SKILL.md under 500 lines (distillation should reduce, not expand)
Phase 5: Target Model Validation
Run the distilled skill on the target model (Haiku or Sonnet):
- Execute the same 5 tasks from Phase 2 with the distilled skill loaded
- Use the
surrogate-verifierto generate assertions for each task output - Compare pass rates:
| Metric | Source (Opus + original) | Target (Haiku + distilled) | Delta |
|---|---|---|---|
| Assertions passed | N/M | N/M | ± |
| Weighted score | X.XX | X.XX | ± |
| Output completeness | % | % | ± |
| Format compliance | % | % | ± |
- If target model score < 80% of source model score, iterate:
- Identify which assertions the target model fails
- Add more explicit instructions for those specific failure points
- Re-run validation (max 3 iterations)
Phase 6: Cross-Model Report
Produce the final comparison:
# Skill Distillation Report: <skill-name>
## Complexity Reduction
- Sections distilled: N/M (HIGH → LOW)
- Instruction word count: original X → distilled Y (Z% reduction)
- Decision points replaced with lookup tables: N
## Cross-Model Performance
| Model | Assertions Passed | Weighted Score | Format Compliance |
|---------|-------------------|----------------|-------------------|
| Opus | 7/7 | 1.00 | 100% |
| Sonnet | 6/7 | 0.92 | 100% |
| Haiku | 5/7 | 0.85 | 85% |
## Changes Made
1. [Section] "Analyze complexity" → explicit 5-item checklist
2. [Section] "Apply formatting" → fixed markdown table template
...
## Recommendation
[SHIP | ITERATE | MANUAL_REVIEW_NEEDED]Error Handling
| Error | Resolution |
|---|---|
| Source skill scores below 70% | Refuse distillation; recommend evolution via test-engineer |
| No execution traces available | Generate synthetic tasks and collect traces before proceeding |
| Target model fails all assertions | Skill may be too complex for target model; report with detail |
| Distilled skill longer than source | Review distillation; patterns may need consolidation |
Limitations
- Cannot distill skills that rely on open-ended adaptive reasoning at many decision points or multi-turn reasoning
- Visual/interactive skills (HTML generation, browser automation) may not distill well
- Distillation optimizes for determinism, not creativity — skills requiring open-ended generation (writing, brainstorming) are poor candidates
- Trace collection requires actual model execution, incurring API costs
© Mathews-Tom, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/skill-distiller of Mathews-Tom/armory.
- SKILL.md
- evals/cases.yaml
- references/distillation-patterns.md
Open the folder on GitHubat commit 4594fb7
Compare with similar skills
Skill Distiller next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Distiller this skillMathews-Tom/armory | 329 | — | ~2k | Automated safety check: Pass | MIT | |
| Ponytail Lazy Developer ModeDietrichGebert/ponytail | 160k | 1 repos | ~873 | Automated safety check: Pass | MIT | |
| Ponytail Reviewkortix-ai/suna | 20k | 4 repos | ~593 | Automated safety check: Pass | Custom licence | |
| PonytailDavidObando/gsharp | 565 | 7 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Code Simplification for ego-litecitrolabs/ego-lite | 17k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Refactor Pass for Simplicitystar-history/star-history | 9.6k | 1 repos | ~168 | Automated safety check: Pass | MIT |
Similar skills
Ponytail Review
kortix-ai/suna
Code review focused exclusively on over-engineering. An agent skill from kortix-ai/suna.
Ponytail
DavidObando/gsharp
Forces the laziest solution that actually works, simplest, shortest, most minimal.
Code Simplification for ego-lite
citrolabs/ego-lite
Finds and implements evidence-backed simplifications in the ego-lite repository, such as dead code, duplicated state and speculative abstractions, without hiding behavior changes.
Refactor Pass for Simplicity
star-history/star-history
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal…
RTK Rust Code Simplifier
rtk-ai/rtk
Reviews RTK's Rust code for over-engineering and verbose patterns, applying idioms like iterator chains and early returns while protecting a specific list of constraints from being simplified away.
More from Mathews-Tom/armory
All 80 skills in this repoArchitecture Reviewer
Mathews-Tom/armory
Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports.
Concept To Image
Mathews-Tom/armory
Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG.
Watch
Mathews-Tom/armory
A skill your agent uses when analyzing an existing video URL or local recording: "watch this video", "analyze youtube video", "summarize this video", "youtube transcript", "find this moment", "what…
Code Refiner
Mathews-Tom/armory
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust.
Concept To Video
Mathews-Tom/armory
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition.
Decision Map
Mathews-Tom/armory
Maps the unresolved architecture, policy, and scope decisions that must be answered before planning can start: one durable decision ticket per question on the issue tracker, typed and blocker-linked…
Related
Categories
Questions about Skill Distiller
What does Skill Distiller do?
Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation. Skill Distiller is an agent skill from Mathews-Tom/armory. Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation.
When should I use Skill Distiller?
Skill Distiller fits situations like: : distill this skill; make this skill work on Haiku; cross-model optimization; optimize skill for cost.
How do I install Skill Distiller in Claude Code?
Run `npx skills add Mathews-Tom/armory --skill skill-distiller -a claude-code`. Or copy the skill folder (skills/skill-distiller in Mathews-Tom/armory) into .claude/skills/skill-distiller in your project. Claude Code loads it when a task matches its description.
How do I install Skill Distiller in Codex?
Run `npx skills add Mathews-Tom/armory --skill skill-distiller -a codex`. Or copy the skill folder (skills/skill-distiller in Mathews-Tom/armory) into .agents/skills/skill-distiller in your project. Codex loads it when a task matches its description.
Can I use Skill Distiller in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Mathews-Tom/armory --skill skill-distiller -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-distiller, .gemini/skills/skill-distiller, .github/skills/skill-distiller and .opencode/skills/skill-distiller in your project.
What does Skill Distiller need to run?
SKILL.md names no scripts, command-line tools or credentials: Skill Distiller is instructions for the agent only.
Does Skill Distiller access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skill Distiller safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Skill Distiller use?
Skill Distiller is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skill Distiller use?
About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.
What are the alternatives to Skill Distiller?
Skills that share tags, products or a category with Skill Distiller: Ponytail Lazy Developer Mode (DietrichGebert/ponytail, 160k stars), Ponytail Review (kortix-ai/suna, 20k stars), Ponytail (DavidObando/gsharp, 565 stars) and Code Simplification for ego-lite (citrolabs/ego-lite, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Distiller?
Mathews-Tom (a GitHub user) maintains it in Mathews-Tom/armory, which has 329 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on October 6, 2026.
Source: Mathews-Tom/armory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.