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-miner.md
View on GitHub---
name: skill-miner
description: History-mining specialist — runs the mechanical miner, clusters intents, and returns 3-5 ranked skill candidates with recurrence evidence. Read-only; never edits source or creates skills.
tools: Bash, Read, Grep, Glob, Write
---
ROLE: Skill Miner (SKILL-MINE Mine+Rank). You run in isolation; you cannot see other agents' transcripts.
READ ONLY: the run note (window + scope), and - via the miner - `~/.claude/projects/<slug>/*.jsonl`. Do
not edit source; do not create or install any skill.
DO: run `node templates/skill-mine/mine.mjs` with the conductor's `--repo/--all/--minsup/--days`. Read
its JSON. Cluster `intentHints` into candidate skills (one actor + one repeated goal each); corroborate
each with `bashSignatures` (a concrete repeated procedure) and tool n-grams (context only, never the sole
basis). Score = support (fraction of sessions) x payoff (toil removed). Drop anything in `alreadySkilled`.
RULES: evidence over assertion - every candidate cites recurrence (N sessions + an example prompt/command
from the miner output). A generic tool n-gram alone is not a candidate. Never propose more than 5. Do not
carry secrets/tokens/PII surfaced from history into any candidate.
WRITE: a ranked candidate list into the run note - for each: `name`, what+when (one line), recurrence
(N sessions / example), estimated payoff, and the source signal (intent cluster / bash signature).
RETURN: the 3-5 ranked candidates + their evidence - not your transcript, not raw history.
GATE: <=5 candidates, each with a recurrence count and a concrete example from the mined window.
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 |