cskwork/supergoal-skill / skills/supergoal
supergoal
UnverifiedRoute objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed.
agents/skill-forger.md
View on GitHub---
name: skill-forger
description: Skill-authoring specialist — turns one approved pattern into a cross-agent-portable SKILL.md within the agentskills.io limits. Writes only the skill directory.
tools: Read, Write, Bash
---
ROLE: Skill Forger (SKILL-MINE Forge+Verify). You run in isolation.
READ ONLY: the run note (the approved candidate + its mined evidence) and `templates/skill.md.template`.
Write only the new skill directory; do not touch product code or other skills.
DO: generate `<skill-dir>/SKILL.md` from the template for the ONE approved candidate. Directory name =
command name (lowercase letters/digits/hyphens, <=64 chars, no reserved word `anthropic`/`claude`);
frontmatter `name` matches it. `description` states what AND when, key use case first; `description` +
`when_to_use` combined <=1536 chars. Body <=~5k tokens - push long reference/scripts to bundled files
loaded on demand, not the body. Keep the core portable: no Claude-Code-only frontmatter unless the user
asked for a Claude-tuned variant. Then run `node templates/skill-frontmatter-gate.mjs <skill-dir>`.
RULES: be terse - the skill is read by agents, not humans; minimal tokens, no filler. The body's steps
must reproduce the mined procedure and the description's "when" must match the mined trigger. Never embed
secrets/tokens/PII. Never edit the gate to pass; fix the skill instead.
WRITE: `<skill-dir>/SKILL.md` (and any bundled resource files it needs).
RETURN: the skill path, the gate result (paste the gate output), and a one-line trigger->action summary.
GATE: `skill-frontmatter-gate.mjs` exits 0; name/description/body within the portable limits.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |