Skill Management
- Repo stars 640
- License MIT
- Author updated Live
- Author repo honeclaw
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @B-M-Capital-Research · MIT
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
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。
---
name: Skill Management
description: Design, inspect, create, and update Hone skills using the Claude Code-style runtime contract. Us…
category: design
runtime: no special runtime
---
# Skill Management output preview
## PART A: Task fit
- Use case: Design, inspect, create, and update Hone skills using the Claude Code-style runtime contract. Use this skill when the user asks to add, create, edit, inspect, migrate, or align a Hone skill. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Skill Management (skillmanager) / Frontmatter Contract / How To Inspect Skills” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Design, inspect, create, and update Hone skills using the Claude Code-style runtime contract. Use this skill when the user asks to add, create, edit, inspect, migrate, or align a Hone skill. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Skill Management (skillmanager) / Frontmatter Contract / How To Inspect Skills” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Validate with a small run
Start with a small task and check whether the result follows “Skill Management (skillmanager) / Frontmatter Contract / How To Inspect Skills”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: Skill Management
description: Design, inspect, create, and update Hone skills using the Claude Code-style runtime contract. Us…
category: design
source: B-M-Capital-Research/honeclaw
---
# Skill Management
## When to use
- Design, inspect, create, and update Hone skills using the Claude Code-style runtime contract. Use this skill when the…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Skill Management (skillmanager) / Frontmatter Contract / How To Inspect Skills” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "Skill Management" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Skill Management (skillmanager) / Frontmatter Contract / How To Inspect Skills
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Skill Management (skill_manager)
Use this skill when the user asks to add, create, edit, inspect, migrate, or align a Hone skill.
The runtime contract is now:
- Skills live in
skills/<name>/SKILL.md,data/custom_skills/<name>/SKILL.md, or a closer.hone/skills/<name>/SKILL.md. - The model sees a compact listing first.
- The full skill body is only injected into the current turn when
skill_tool(skill_name="...")or a user slash command like/<skill-name>is invoked. load_skillis only a compatibility shim. Do not teach it as the primary workflow.
Frontmatter Contract
Prefer this frontmatter schema:
---
name: Human readable name
description: One-line description
when_to_use: Brief trigger guidance
allowed-tools:
- skill_tool
user-invocable: true
model: optional model override
effort: optional effort override
context: inline
agent: optional agent hint
paths:
- src/**/*.rs
hooks: {}
arguments: []
script: optional default script path like scripts/run.sh
shell: optional shell hint
---Notes:
allowed-toolsreplaces legacytoolsas the main runtime field.contextshould usually beinline; useforkonly when the skill should run in an isolated child runner.pathshides the skill from the default listing until the active task touches matching files.scriptdeclares the default executable entrypoint inside the skill directory.skill_tool(..., execute_script=true)can run it with${HONE_SKILL_DIR}as cwd.- Keep the Markdown body task-oriented and ready to inject as prompt text.
How To Inspect Skills
When the user asks what skills exist or which skill fits a task:
- Call
discover_skills(query="...")with the user's task or keyword. - Summarize the relevant skills from the returned metadata.
- If one skill should actually be used for the current task, call
skill_tool(skill_name="...")so the full skill prompt is expanded for this turn.
When the user asks to inspect a specific skill in detail:
- Use
discover_skills(query="<skill name>")to confirm the match if needed. - Call
skill_tool(skill_name="<skill id>"). - Explain the resolved metadata and the injected prompt body, not a hand-written summary that drifts from the source.
How To Create Or Update Skills
When the user wants to create or edit a skill:
- Collect the intended skill id, description, trigger conditions, and whether users should be able to invoke it directly with
/<skill-name>. - Write or update the actual
SKILL.mdfile with the new frontmatter schema. - Keep the body concrete: trigger rules, required steps, tool usage expectations, and refusal/verification constraints.
- If you created or changed a skill that should be runnable immediately, validate it by invoking
skill_tool(skill_name="<skill id>")and checking the rendered prompt.
Strict Rules
- Do not teach the deprecated
skill_tool(action="add" | "update" | "remove")CRUD workflow. - Do not rely on
load_skillas the main user-facing path. - If a skill is path-gated, mention that it may stay hidden until matching files are involved.
- If runtime enforcement is not implemented for a field such as
hooksor strict tool scoping, say so plainly instead of pretending it is active.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review