skill-improver
- Repo stars 3,249
- License Apache-2.0
- Author updated Live
- Author repo gentle-ai
- Domain
- Security
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @Gentleman-Programming · Apache-2.0
- 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-improver
description: Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existin…
category: security
runtime: no special runtime
---
# skill-improver output preview
## PART A: Task fit
- Use case: Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills. Use this skill when asked to audit, refactor, normalize, or improve existing SKILL.md files. Use skill-creator instead when creating a brand-new skill from a reusable pattern. runs entirely locally. Works with Claude Code, Cursor, Cline and ….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Activation Contract / Hard Rules / Decision Gates” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills. Use this skill when asked to audit, refactor, normalize, or improve existing SKILL.md files. Use skill-creator instead when creating a brand-new skill from a reusable pattern. runs entirely locally. Works with Claude Code, Cursor, Cline and …”.
- **02** When the source has headings, the agent prioritizes “Activation Contract / Hard Rules / Decision Gates” 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 “Activation Contract / Hard Rules / Decision Gates”. 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-improver
description: Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existin…
category: security
source: Gentleman-Programming/gentle-ai
---
# skill-improver
## When to use
- Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills. Us…
- 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 “Activation Contract / Hard Rules / Decision Gates” 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-improver" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Activation Contract / Hard Rules / Decision Gates
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
}Activation Contract
Use this skill when asked to audit, refactor, normalize, or improve existing SKILL.md files. Use skill-creator instead when creating a brand-new skill from a reusable pattern.
Hard Rules
- Treat
docs/skill-style-guide.mdas the normative style contract when it exists. - Treat
SKILL.mdas the source of truth; preserve author intent, critical rules, activation semantics, and output requirements. - Use
.atl/skill-registry.mdas an index of skill names, triggers, scopes, and exact paths; do not expect generated summaries. - Default to audit-only. Modify files only when the user explicitly asks to apply improvements.
- Never delete meaningful content silently; move long explanation, examples, templates, or schemas into local
references/orassets/. - Do not invent triggers, policies, or domain rules. Mark ambiguous cases for human review.
Decision Gates
| Situation | Action |
|---|---|
| Missing or invalid frontmatter | Fix name, quoted one-line description, license, and metadata |
| Skill reads like tutorial docs | Convert to runtime instructions and move background to references/ |
| Body exceeds budget | Preserve rules, move examples/background to supporting files |
| Branching logic hidden in prose | Convert to a compact decision table |
| Rules conflict or intent is unclear | Report the issue; do not rewrite that rule automatically |
Execution Steps
- Read
docs/skill-style-guide.md; if unavailable, enforce the core LLM-first structure: frontmatter, Activation Contract, Hard Rules, Decision Gates, Execution Steps, Output Contract, References. - Read
.atl/skill-registry.md; use listed paths to select skills. If missing, scan known skill directories for*/SKILL.md. - For each selected skill, audit metadata, trigger clarity, section order, body budget, actionability, decision gates, output contract, and local references.
- Return an audit report grouped by skill with severity and exact proposed changes.
- In apply mode, edit only safe issues, preserve content, create supporting files when needed, then rerun or request
gentle-ai skill-registry refresh.
Output Contract
Return:
- Skills audited and paths used.
- Issues found, grouped by severity.
- Files changed, if apply mode was requested.
- Registry refresh recommendation when skill metadata or paths changed.
- Ambiguities that need human review.
References
docs/skill-style-guide.md— normative LLM-first skill style guide for this repo.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review