selectess/fde-consultants-protocoles / template-skill
template-skill
VerifiedA minimal template for creating a new FDE Consultant Skill (Apache-2.0). Use as starting point for any new skill.
My Skill Name
Use this as a starting point for any new FDE Consultant Skill. Copy this folder, rename it, and customize the content.
Description
[1 paragraph: what this skill does, when to use it, what problem it solves]
When to use this skill
Activate this skill when the user:
- [Trigger 1: explicit mention of the skill name]
- [Trigger 2: task matches the skill's domain]
- [Trigger 3: project type matches the skill's target]
What this skill produces
[1 paragraph: what artifacts the skill generates, what quality bar]
Operating Principles (subset relevant to this skill)
- [Principle 1 — pick from skill/SKILL.md 14 OP]
- [Principle 2]
- [Principle 3]
Anti-Patterns to avoid
- [Anti-pattern 1]
- [Anti-pattern 2]
- [Anti-pattern 3]
Workflow
- Stage 1 — Scoping: [what to do]
- Stage 2 — Prototyping: [what to do]
- Stage 3 — Production: [what to do]
- Stage 4 — Feedback: [what to do, end with FDE Assurance Score]
Examples
Example 1: [use case]
[input -> output]
Example 2: [use case]
[input -> output]
Templates
This skill uses these templates (in skill/templates/):
scoping-report.md— Stage 1 outputprototype-spec.md— Stage 2 outputproduction-handoff.md— Stage 3 outputproductization-memo.md— Stage 4 output
Tools (Python)
This skill uses these scripts (in skill/scripts/):
decompose_problem.py— validate 6-Qroi_calculator.py— compute ROIscientific_search.py— held-out promotion gateevals_runner.py— 6-trait scoringontology_extractor.py— Palantir-style ontology
References (loaded on demand)
In skill/references/:
fde-methodology.md— core methodologyfde-trust-score.md— FDE Assurance Score formulafde-skeptical-deployment.md— gate protocol
FDE Assurance Score
This template applies its own FDE Assurance Score:
| Component | Max | Actual |
|---|---|---|
| Claim (falsifiable) | 25 | 25 (a template by definition is verifiable) |
| Contradiction (failure modes) | 25 | 20 (acknowledged: customization risk) |
| Evidence trail | 30 | 25 (cross-references to canonical docs) |
| Anti-patterns clean | 20 | 18 (no fake metrics) |
| TOTAL | 100 | 88/100 → Certified |
Note: When you customize this template, recompute your FDE Assurance Score with your actual evidence.
License
Apache-2.0.
Maintainer
[Your name / contact]
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: 468k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |