Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Generate Code

ASecurity

Hypothesis-driven fix/change workflow — consults the review-current-state factblock, forms an explicit guess at the root cause and fix, then updates code and tests to verify it scientifically. Use when asked to fix a bug, change behavior, or implement something against a specific target, with a documented, hypothesis-driven process rather than an ad hoc edit.

14 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agents

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add bkraad47/fat_llama_fftw --skill generate-code --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Generate Code?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Generate Code
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bkraad47-generate-code/badge)](https://www.skillsdirectory.com/skills/bkraad47-generate-code)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: generate-code
description: Hypothesis-driven fix/change workflow — consults the review-current-state factblock, forms an explicit guess at the root cause and fix, then updates code and tests to verify it scientifically. Use when asked to fix a bug, change behavior, or implement something against a specific target, with a documented, hypothesis-driven process rather than an ad hoc edit.
allowed-tools: Skill, Agent
disable-model-invocation: false
model: fable
---

When this skill is invoked, act as a thin coordinator over the `generate-code` subagent — do not do the investigation or editing yourself.

Before doing anything else, read `.claude/skills/rules/generate-code.md` (target-handling and relaying policy), `.claude/rules/scope-and-safety.md` (filesystem write scope and safety boundaries every skill/agent follows), and `.claude/rules/project-mission.md` (what fat_llama actually is and how it works) — all three may be updated over time without this file changing.

Also read `README.md` at the repo root in full, right now, before Step 1 — it's fat_llama's own description of its purpose and method (iterative soft thresholding of FFT data to upscale compressed audio across supported formats, tested and built primarily against the MP3→FLAC outcome, CPU/FFTW-only, deliberately without AI/ML-based upscaling). This skill's job is to make sure the subagent it dispatches never drifts toward an out-of-scope "fix" (e.g. reaching for a trained/learned model or a CUDA/GPU-accelerated path), so carry this context into the subagent's prompt in Step 2.

`args` names the target: what to look at and what to fix or change. If `args` is empty, ask the user what target to work on before proceeding.

## Logging

Before Step 1, open this run's log file per `.claude/rules/logging.md` (name: `generate-code-<time>-<user>.log`). Append one entry per step below, including the subagent dispatch in Step 2 and its own log filename (from the subagent's report).

## Steps

1. Check whether `docs/CURRENT_STATE.md` exists.
   - If it's missing entirely, invoke the `review-current-state` skill first (via the Skill tool) to generate it — `generate-code` depends on that factblock as its starting map.
   - If it already exists, don't regenerate it automatically; the subagent itself will flag if it looks stale for the files it needs and read source directly in that case.

2. Launch the `generate-code` subagent via the Agent tool with `subagent_type: "generate-code"` and `run_in_background: false` (the caller needs the result in this turn). Give it a self-contained prompt containing the exact target text from `args`, plus the condensed mission context from `.claude/rules/project-mission.md` (mp3→flac is the primary tested outcome among the formats fat_llama supports, via IST on FFT data, CPU/FFTW-only, no AI/ML-based upscaling) — it also reads its own rules file, the mission-context file, and the factblock, so no further context is required beyond that.

3. The subagent's final message is JSON per the contract in `.claude/agents/rules/scientific-coding.md`. Relay it per the relaying policy in `.claude/skills/rules/generate-code.md`.

## Note for coordinator agents

A coordinator does not need this skill at all — it can call the `generate-code` subagent directly via the Agent tool with `subagent_type: "generate-code"`, passing the target in the prompt. This skill exists as the interactive `/generate-code <target>` entry point; the subagent is the reusable unit.

Attribution

bkraad47bkraad47
View sourceMore from bkraad47 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →