skill-usage

Other Community

Repo stars 551
Author repo a-evolve

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: How to discover, load, and effectively use skills to solve SkillBench tasks. Skills are modular instruction packages placed in t…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Skill locations”, “Skill structure”, “How to use skills”, “Common skill patterns”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name skill-usage directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Skill locations / Skill structure / How to use skills” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Skill Usage Guide

Skills are modular instruction packages placed in the container to help you solve tasks. Using them effectively is the single most important factor for success.

Skill locations

Skills are copied to multiple well-known paths inside the container:

/root/.agents/skills/
/root/.claude/skills/
/root/.codex/skills/

All paths contain the same skills. Use whichever is available.

Skill structure

Each skill is a folder:

skill-name/
├── SKILL.md        # Main instructions (YAML frontmatter + markdown body)
├── scripts/        # Optional helper scripts (Python, Bash)
└── references/     # Optional reference documentation

How to use skills

Always list skills first — call list_skills at the start of every task
Load relevant skills — if a skill name matches the task domain, call load_skill with the skill name
Follow skill instructions — skills contain domain-specific procedures, parameter values, or code patterns that are essential
Run helper scripts — if the skill has scripts/, execute them (they often automate tedious steps)
Consult references — check references/ for API docs or formula sheets

Common skill patterns

Data format skills (e.g., xlsx, csv): Teach how to read/write specific formats
Domain skills (e.g., pid-control, seismic): Contain domain formulas and constants
Tool skills (e.g., libreoffice, ffmpeg): Show correct CLI flags and workflows
Framework skills (e.g., react, spring-boot): Guide migration or debugging patterns

Anti-patterns

Do NOT ignore skills — they exist specifically for the task at hand
Do NOT reinvent what a skill script already automates
Do NOT skip reading the full SKILL.md — summaries miss critical details

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Other
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @A-EVO-Lab · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Python
Detected file/system behavior: Read-only
Write / modify
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview skill-usage.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Skill Usage Guide

Skills are modular instruction packages placed in the container to help you solve tasks. Using them effectively is the single most important factor for success.

## Skill locations

Skills are copied to multiple well-known paths inside the container:

- `/root/.agents/skills/`
- `/root/.claude/skills/`
- `/root/.codex/skills/`

All paths contain the same skills. Use whichever is available.

## Skill structure

Each skill is a folder:

```
skill-name/
├── SKILL.md        # Main instructions (YAML frontmatter + markdown body)
├── scripts/        # Optional helper scripts (Python, Bash)
└── references/     # Optional reference documentation
```

## How to use skills

1. **Always list skills first** — call `list_skills` at the start of every task
2. **Load relevant skills** — if a skill name matches the task domain, call `load_skill` with the skill name
3. **Follow skill instructions** — skills contain domain-specific procedures, parameter values, or code patterns that are essential
4. **Run helper scripts** — if the skill has `scripts/`, execute them (they often automate tedious steps)
5. **Consult references** — check `references/` for API docs or formula sheets

## Common skill patterns

- **Data format skills** (e.g., xlsx, csv): Teach how to read/write specific formats
- **Domain skills** (e.g., pid-control, seismic): Contain domain formulas and constants
- **Tool skills** (e.g., libreoffice, ffmpeg): Show correct CLI flags and workflows
- **Framework skills** (e.g., react, spring-boot): Guide migration or debugging patterns

## Anti-patterns

- Do NOT ignore skills — they exist specifically for the task at hand
- Do NOT reinvent what a skill script already automates
- Do NOT skip reading the full SKILL.md — summaries miss critical details

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Skill locations → Skill structure → How to use skills → Common skill patterns → Anti-patterns
terms    -> Always list skills first · Load relevant skills · Follow skill instructions · Run helper scripts · Consult references · Data format skills · Domain skills · Tool skills
files/cmd -> /root/.agents/skills/ · /root/.claude/skills/ · /root/.codex/skills/ · listskills · loadskill · scripts/ · references/
body sha256 -> df67a3446ce3