Xpersona
S

Skill Finder (Find ClawHub skills + Search Skills.sh)

CLAWHUB · Unverified

Find, compare, and install agent skills across ClawHub and Skills.sh when the user needs new capabilities, better workflows, stronger tools, or safer alterna... Skill: Skill Finder (Find ClawHub skills + Search Skills.sh) Owner: ivangdavila Summary: Find, compare, and install agent skills across ClawHub and Skills.sh when the user needs new capabilities, better workflows, stronger tools, or safer alterna... Tags: latest:1.1.5 Version history: v1.1.5 | 2026-03-11T18:04:13.041Z | user Broader discovery guidance for finding better, safer, and more relevant skills faster. v1.1.4

62
Rank
84
Safety
15k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 15.3K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s178jdk12x4qj3gs2se3etxf3h83h7ft:skill-finder
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-skill-finder-l-finder-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

144,874 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "Skill Finder (Find ClawHub skills + Search Skills.sh)"
slug: skill-finder
version: "1.1.5"
homepage: https://clawic.com/skills/skill-finder
description: "Find, compare, and install agent skills across ClawHub and Skills.sh when the user needs new capabilities, better workflows, stronger tools, or safer alternatives. Use when (1) they ask how to do something, how to improve or automate it, or what to install; (2) a skill could extend the agent, replace a weak manual approach, or close a capability gap; (3) you need the best-fit option, not just a direct answer."
changelog: "Broader discovery guidance for finding better, safer, and more relevant skills faster."
metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["npx"]},"os":["linux","darwin","win32"],"configPaths":["~/skill-finder/"]}}
---

## When to Use

User asks how to do something, wonders whether a skill exists, wants a new capability, or asks for the best skill for a job. Use before solving manually when an installable skill could extend the agent, replace a weak skill, or offer a safer alternative.

## Architecture

Memory lives in `~/skill-finder/`. If `~/skill-finder/` does not exist or is empty, run `setup.md`.

```
~/skill-finder/
├── memory.md     # Source mode + preferences + liked/passed skills
└── searches.md   # Recent search history (optional)
```

## Migration

If upgrading from a previous version, see `migration.md` for data migration steps.
The agent MUST check for legacy memory structure before proceeding.

## Quick Reference

| Topic | File |
|-------|------|
| Setup | `setup.md` |
| Memory template | `memory-template.md` |
| Search strategies | `search.md` |
| Evaluation criteria | `evaluate.md` |
| Skill categories | `categories.md` |
| Edge cases | `troubleshooting.md` |

## Activation Signals

Activate when the user says things like:
- "How do I do X?"
- "Is there a skill for this?"
- "Can you do this better?"
- "Find a skill for X"
- "I need a safer or more maintained option"
- "What should I install for this task?"

Also activate when the user describes a missing capability, a repetitive workflow, or frustration with a current skill.

## Search Sources

This skill can search two ecosystems:

| Source | Search | Install | Best for |
|--------|--------|---------|----------|
| `ClawHub` | `npx clawhub search "query"` | `npx clawhub install <slug>` | Curated registry search with built-in inspection |
| `Skills.sh` | `npx skills find [query]` | `npx skills add <owner/repo@skill>` | Broad open ecosystem from the `skills` CLI |

Default mode: search **both** sources, then compare results together.

Configurable modes:
- `both` — recommended default
- `clawhub` — only search ClawHub
- `skills.sh` — only search the Skills.sh ecosystem

Store the current mode in `~/skill-finder/memory.md`. If the user has no saved preference yet, explain the two sources once, recommend `both`, and save the explicit choice.

## Security Note

This skill uses `npx clawhub` and `npx 

_meta.json

{
  "ownerId": "kn73vp5rarc3b14rc7wjcw8f8580t5d1",
  "slug": "skill-finder",
  "version": "1.1.5",
  "publishedAt": 1773252253041
}

categories.md

# Skill Categories — Skill Finder

Reference for mapping user needs to search terms.

## Common Categories

| Category | User Might Say | Search Terms |
|----------|---------------|--------------|
| **Languages** | "help with Python", "write Rust" | python, py, rust, go, typescript, swift |
| **Frameworks** | "React app", "Django project" | react, nextjs, django, rails, flutter |
| **DevOps** | "deploy this", "CI/CD" | docker, kubernetes, deploy, ci-cd, terraform |
| **Testing** | "write tests", "QA" | testing, jest, playwright, e2e, unit-test |
| **Databases** | "SQL help", "store data" | postgres, mysql, redis, mongodb, sql |
| **APIs** | "call this API", "REST" | api, rest, graphql, http, curl |
| **Git** | "commit", "PR review" | git, github, gitlab, pr, code-review |
| **Docs** | "write readme", "documentation" | docs, readme, changelog, markdown |
| **Design** | "UI help", "make it pretty" | ui, ux, design, css, tailwind |
| **AI/ML** | "machine learning", "LLM" | ai, ml, openai, llm, embeddings |
| **Security** | "security audit", "vulnerabilities" | security, audit, owasp, secrets |
| **Productivity** | "automate this", "workflow" | automation, workflow, scripts |
| **Cloud** | "AWS", "cloud deploy" | aws, gcp, azure, cloud, serverless |
| **Mobile** | "iOS app", "Android" | ios, android, mobile, flutter, react-native |

## Search Strategy by Category

### Development (Code)
Start specific, broaden if needed:
1. `"python async"` (specific)
2. `"python"` (broader)
3. `"scripting"` (broadest)

### Infrastructure (DevOps)
Include the action:
1. `"docker deploy"` (action + tool)
2. `"kubernetes helm"` (tool + subtool)
3. `"ci-cd github"` (concept + platform)

### Tooling (CLI/Services)
Try the tool name directly:
1. `"stripe"` (service name)
2. `"payment"` (domain if name fails)

## Domain Combinations

Users often need cross-domain skills:

| Combined Need | Search Terms |
|--------------|--------------|
| "Deploy my React app" | `react deploy`, `nextjs vercel` |
| "Test my API" | `api testing`, `rest test` |
| "Python for data" | `python pandas`, `data analysis` |
| "Secure my app" | `security web`, `owasp` |

## When Category is Unclear

Ask clarifying question:
> "When you say 'help with data', do you mean:
> - Storing data (databases)?
> - Analyzing data (pandas, visualization)?
> - Moving data (ETL, pipelines)?"

Then search the specific subcategory.

evaluate.md

# Skill Evaluation Criteria — Skill Finder

Reference for assessing skill quality before recommending.

## Quick Assessment (From Search Results)

Check these signals immediately:

| Signal | Good | Concerning |
|--------|------|------------|
| Downloads | >500 | <50 |
| Last update | <3 months | >1 year |
| Description | Clear what + when | Vague or generic |
| Author | Multiple skills | Single anonymous |
| Source package | Clear install string | Ambiguous or incomplete install path |

## Detailed Evaluation

### ClawHub Candidates

After `npx clawhub inspect`:

### Structure Quality

✅ **Good signs:**
- SKILL.md under 100 lines
- Auxiliary files for details
- Clear sections (When to Use, Core Rules)
- Progressive disclosure pattern

❌ **Red flags:**
- Wall of text in single file
- No organization
- Explains obvious concepts
- README/CHANGELOG noise

### Instruction Quality

✅ **Good signs:**
- Imperative voice ("Do X", "Check Y")
- Actionable instructions
- Clear triggers (when to activate)
- Examples where helpful

❌ **Red flags:**
- Passive voice ("Users should consider...")
- Theory without actionable guidance
- Vague instructions ("be careful with...")
- Over-explanation of basics

### Skills.sh Candidates

After `npx skills find` returns a candidate:

✅ **Good signs:**
- Clear install string like `owner/repo@skill`
- Recognizable or maintained source repository
- skills.sh page or repo makes the purpose obvious
- The skill feels installable without extra guesswork

❌ **Red flags:**
- Unclear install target
- Repo with weak description or no obvious maintenance
- Name sounds relevant but source package is confusing
- Requires guessing project vs global scope or target agent without user input

### Fit Assessment

Ask yourself:
- Does it solve the **actual** need?
- Is it too broad (generic) or too narrow (edge case)?
- Does it conflict with skills already installed?
- Is it worth the context cost?

## Scoring (Mental Model)

Rate 1-5 on each:

| Dimension | Question |
|-----------|----------|
| **Relevance** | How well does it match the specific need? |
| **Quality** | How well is the skill built? |
| **Maintenance** | Is it actively maintained? |
| **Value** | Is it worth the context tokens? |

**Recommend if:** All scores ≥3

## Reporting to User

### When Recommending
> "Found `skill-name` — [what it does in one line]. [Quality note]. Want me to install it?"

Example:
> "Found `stripe` — handles payment integration with webhooks and subscriptions. 4k downloads, updated last week. Want me to install it?"

For `Skills.sh`:
> "Found `owner/repo@skill-name` on Skills.sh — [what it does]. Install command is `npx skills add owner/repo@skill-name`. Want me to install it?"

### When Hesitant
> "Found `skill-name` but [concern]. [Alternative or ask if want anyway]."

Example:
> "Found `old-pdf-tool` but it hasn't been updated in 8 months. There's a newer `pdf-toolkit` with similar features — want that instead?"

### When No Good Options
> "Searc

memory-template.md

# Memory Template — Skill Finder

Create `~/skill-finder/memory.md` with this structure:

```markdown
# Skill Finder Memory

## Status
status: ongoing
last: YYYY-MM-DD
sources: both
integration: proactive

## Preferences
<!-- Explicit quality values stated by user -->
<!-- Examples: "prefers minimal", "wants well-maintained", "okay with experimental" -->

## Source Policy
<!-- Default source mode: both, clawhub, or skills.sh -->
<!-- Example: both -->
<!-- Install scope for `npx skills add`: ask, project, or global -->

## Liked
<!-- Skills user explicitly praised, with their reason -->
<!-- Format: source:identifier — "what they said they liked" -->
<!-- Examples: clawhub:skill-manager — "clear and safe" -->
<!--           skills.sh:vercel-labs/agent-skills@frontend-design — "great for UI work" -->

## Passed
<!-- Skills user explicitly declined, with their reason -->
<!-- Format: source:identifier — "what they said was wrong" -->

## Domains
<!-- Areas user works in (helps narrow searches) -->

---
*Updated: YYYY-MM-DD*
```

## Status Values

| Value | Meaning |
|-------|---------|
| `ongoing` | Still learning preferences |
| `established` | Has enough preference data |

## What to Store

### Source Policy (from explicit statements)
- "Search both" → `sources: both`
- "Only use ClawHub" → `sources: clawhub`
- "Only use Skills.sh" → `sources: skills.sh`
- "Prefer project installs" → add under `## Source Policy`
- "Prefer global installs" → add under `## Source Policy`

### Preferences (from explicit statements)
- "I prefer minimal skills" → add verbatim
- "I want well-maintained only" → add verbatim
- "I don't mind experimental" → add verbatim

### Liked (from explicit praise)
- User says "this skill is great because X" → `source:identifier — "X"`
- User expresses satisfaction → `source:identifier — "reason"`

### Passed (from explicit rejection)
- User declines with reason → `source:identifier — "reason"`
- User uninstalls and explains → `source:identifier — "reason"`

## What NOT to Store

- Silent installations (no comment = no data)
- Inferred preferences from behavior patterns
- Anything not explicitly stated by user

## Using Memory

When multiple skills match a search:
1. **Check source mode** — Search `both`, `clawhub`, or `skills.sh` accordingly
2. **Check Passed** — exclude similar
3. **Check Liked** — favor similar qualities
4. **Apply Preferences** — filter accordingly

## Maintenance

Keep under 50 lines. When exceeded:
- Archive old Liked/Passed entries
- Keep most recent Preferences

Sponsored

Ads related to Skill Finder (Find ClawHub skills + Search Skills.sh) and adjacent AI workflows.