bitranox IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. This is not optional. You cannot rationalize your way out of this.
Instruction Priority
bitranox skills override default system-prompt behavior where they conflict, but user instructions always take precedence:
- User's explicit instructions (CLAUDE.md, AGENTS.md, direct requests) - highest priority
- bitranox skills - override default system behavior where they conflict
- Default system prompt - lowest priority
If CLAUDE.md says "don't use TDD" and a skill says "always use TDD", follow the user's instructions. The user is in control.
How to Access Skills
Never read a skill's SKILL.md manually with file tools. Always invoke it through the Skill tool so it activates properly and you get the current version, not a stale memory of it.
In Claude Code: Use the Skill tool. When you invoke a skill, its content is loaded and presented to you: follow it directly. Use the Read tool only for the supporting files a skill references (its scripts/, templates, references), never to re-read the skill body itself.
In other environments: Check your platform's documentation for how skills are loaded.
Using Skills
Adapted from the superpowers plugin (MIT).
The Rule
Invoke relevant or requested skills BEFORE any response or action. Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
Before entering plan mode, brainstorm first with bitranox:process-plan-brainstorming unless you already have.
digraph skill_flow {
"User message received" [shape=doublecircle];
"About to enter plan mode?" [shape=doublecircle];
"Already brainstormed?" [shape=diamond];
"Invoke bitranox:process-plan-brainstorming" [shape=box];
"Might any skill apply?" [shape=diamond];
"Invoke Skill tool" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Has checklist?" [shape=diamond];
"Create TodoWrite todo per item" [shape=box];
"Follow skill exactly" [shape=box];
"Respond (including clarifications)" [shape=doublecircle];
"About to enter plan mode?" -> "Already brainstormed?";
"Already brainstormed?" -> "Invoke bitranox:process-plan-brainstorming" [label="no"];
"Already brainstormed?" -> "Might any skill apply?" [label="yes"];
"Invoke bitranox:process-plan-brainstorming" -> "Might any skill apply?";
"User message received" -> "Might any skill apply?";
"Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
"Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
"Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Create TodoWrite todo per item" -> "Follow skill exactly";
}
Red Flags
These thoughts mean STOP - you're rationalizing:
| Thought | Reality |
|---|---|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
| "Let me gather information first" | Skills tell you HOW to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept is not using the skill. Invoke it. |
| "I'll just start planning" | Brainstorm first (bitranox:process-plan-brainstorming) before plan mode, unless already done. |
| "I'll read the skill file myself" | Never open SKILL.md with file tools. Invoke it via the Skill tool. |
Skill Priority
When multiple skills could apply, use this order:
- Process skills first (
bitranox:process-plan-brainstorming,bitranox:process-debug-systematic) - these determine HOW to approach the task - Implementation skills second - these guide execution
"Let's build X" -> brainstorming first, then implementation skills. "Fix this bug" -> systematic-debugging first, then domain-specific skills.
Skills Span Every Domain, Not Just Process
bitranox ships far more than the workflow/process skills. Before concluding "no skill applies," scan these domains: there is very likely a relevant one. The authoritative, current list is your injected available-skills - invoke any by name with the Skill tool.
- Process and quality (
process-*,git-worktrees): planning, TDD, debugging, reviews, shipping. - Memory and meta (
meta-*): capture, dreams, gathering, skill authoring. - Coding and architecture (
coding-*): language references, clean architecture, sanitization, resilience. - Structured files and docs (
files-edit-*,docs-*): e.g.files-edit-yml,docs-md-table-formatting. - Shell / git / ssh / VNC mechanics (
compuse-*): e.g.compuse-bashfor pipelines and exit codes. - Writing (
write-humanize-en/-de), infrastructure (infra-*,net-*,devops-bmk), web (web-*), security (sec-*), business (marketing-*).
THE AUTHORITATIVE LIST IS YOUR INJECTED available-skills - these categories are orientation only
(skills get added and renamed; the list is the source of truth). Never skip a domain skill because
the task looked like "only" a coding task: editing a YAML file -> files-edit-yml; writing a
user-facing message -> write-humanize-en/-de; touching a Proxmox host -> infra-proxmox.
Work like a pathfinder
Beyond finding and using skills: while you work, leave every file better than you found it, accept NO
technical debt (point mistakes out clearly, never "works anyway"), put an out-of-scope fix in its own
worktree (bitranox:git-worktrees) instead of bolting it on, and clean up temporary scaffolding when
done. One thing is NOT adjacent rot: a bitranox hook, skill or memory-engine call misbehaving while
you work on some other project. Queue the symptom in one line (contrib_queue.py add, home
<plugin>/skills/meta-self-improve/) and keep working; the dream fixes the tool, unless the user
asks for the fix in so many words. The full discipline is in bitranox:meta-self-improve
("Pathfinder discipline").
Skill Types
Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline.
Flexible (patterns): Adapt principles to context.
The skill itself tells you which.
User Instructions
Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.