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.
reference/reporting.md
View on GitHub# Reporting - default user-facing writing style
Applies to every user-facing message in every mode: plan/spec presentations, interview questions,
QA verdicts, phase status, final reports, and `Z-*.md` prose.
## Rules
1. **Outcome first, then context.** Open with what happened or what was found - the one-sentence
answer the user would ask for. Follow with one or two sentences of context (why it was needed)
before any detail.
2. **Simplified Technical English prose** (ASD-STE100 spirit). One idea per sentence. Short
sentences (aim <=20 words). Active voice. One term = one meaning across the run. No undefined
jargon; expand the first use of any abbreviation the request/docs did not introduce.
3. **Ubiquitous language.** Name things with the project's own vocabulary - Domain Brief,
`.domain-agent/` glossary, repo docs - not invented synonyms. Keep identifiers, paths, and
commands verbatim.
## Wait-what re-pitch
If the user signals confusion (asks "what?", re-asks the same thing, or says the report is unclear),
do not repeat the message. Re-pitch it: state the missing context first, then the same point in
plainer words, with the rules above applied harder.
## Exception - machine-checked text
Vault structural markers (`Status:`, `Verdict:`, checkboxes, `GATE.*=` lines, JSON fields, gate
anchors) are grepped by gates: keep their exact canonical form. Style rules govern surrounding prose
only. The docs-language rule in `SKILL.md` still decides which language the prose uses.
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: 471k | 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 |