cli-anything-hermes
Use when the user wants Hermes Agent to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository. Adapts the CLI-Anything methodology to Hermes without changing the generated Python harness format.
What this skill does
# CLI-Anything for Hermes Agent
Use this skill when the user wants Hermes Agent to act like the `CLI-Anything` builder.
Before implementation, use the full methodology source of truth when available:
1. If this skill is being used from inside the `CLI-Anything` repository, read `../cli-anything-plugin/HARNESS.md` first.
2. If that local file is unavailable, clone or download `cli-anything-plugin` from `https://github.com/HKUDS/CLI-Anything/tree/main/cli-anything-plugin`, then use `HARNESS.md` and the resources around it from that folder.
3. Only if both local and network retrieval fail, follow the condensed rules below.
## Inputs
Accept either:
- A local source path such as `./gimp` or `/path/to/software`
- A GitHub repository URL
Derive the software name from the local directory name after cloning if needed.
## Hermes Tool Bindings
Hermes agents build harnesses by combining these built-in tools:
| Tool | Role in Harness Workflow |
|------|--------------------------|
| `terminal` | Run shell commands, install packages, execute CLI tools, run tests |
| `execute_code` | Generate and write Python files (Click CLI, backend modules, tests) |
| `delegate_task` | Parallelize analysis or generation subtasks |
| `read_file` / `write_file` | Read and write harness source files |
| `patch` | Make targeted edits to generated code |
Consult the [Hermes Agent documentation](https://github.com/NousResearch/hermes-agent) for the exact tool invocation syntax.
## Modes
### Build
Use when the user wants a new harness.
Produce this structure:
```text
<software>/
└── agent-harness/
├── <SOFTWARE>.md
├── setup.py
└── cli_anything/
└── <software>/
├── README.md
├── __init__.py
├── __main__.py
├── <software>_cli.py
├── core/
├── utils/
└── tests/
```
Implement a stateful Click CLI with:
- one-shot subcommands
- REPL mode as the default when no subcommand is given
- `--json` machine-readable output
- session state with undo/redo where the target software supports it
### Refine
Use when the harness already exists.
First inventory current commands and tests, then do gap analysis against the target software. Prefer:
- high-impact missing features
- easy wrappers around existing backend APIs or CLIs
- additions that compose well with existing commands
Do not remove existing commands unless the user explicitly asks for a breaking change.
### Test
Plan tests before writing them. Keep both:
- `test_core.py` for unit coverage
- `test_full_e2e.py` for workflow and backend validation
When possible, test the installed command via subprocess using `cli-anything-<software>` rather than only module imports.
### Validate
Check that the harness:
- uses the `cli_anything.<software>` namespace package layout
- has an installable `setup.py` entry point
- supports JSON output
- has a REPL default path
- documents usage and tests
## Backend Rules
Prefer the real software backend over reimplementation. Wrap the actual executable or scripting interface in `utils/<software>_backend.py` when possible. Use synthetic reimplementation only when the project explicitly requires it or no viable native backend exists.
## Packaging Rules
- Use `find_namespace_packages(include=["cli_anything.*"])`
- Keep `cli_anything/` as a namespace package without a top-level `__init__.py`
- Expose `cli-anything-<software>` through `console_scripts`
## Workflow
1. Acquire the source tree locally (clone or use existing path).
2. Analyze architecture, data model, existing CLIs, and GUI-to-API mappings.
3. Design command groups and state model.
4. Implement the harness.
5. Write `TEST.md`, then tests, then run them.
6. Update README usage docs.
7. Verify local installation with `pip install -e .`
## Existing Harnesses (Reference)
For an up-to-date list of supported harnesses and their backend patterns, see [`registry.json`](../registry.json) at the repository root.
## Output Expectations
When reporting progress or final results, include:
- target software and source path
- files added or changed
- validation commands run
- open risks or backend limitations
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.