# Send skill-condenser to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skill-condenser",
    "name": "skill-condenser",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/killerapp/skill-condenser",
    "canonicalUrl": "https://clawhub.ai/killerapp/skill-condenser",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/skill-condenser",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-condenser",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "skill-condenser",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-05T04:28:56.451Z",
      "expiresAt": "2026-05-12T04:28:56.451Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-condenser",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-condenser",
        "contentDisposition": "attachment; filename=\"skill-condenser-1.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "skill-condenser"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/skill-condenser"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skill-condenser",
    "downloadUrl": "https://openagent3.xyz/downloads/skill-condenser",
    "agentUrl": "https://openagent3.xyz/skills/skill-condenser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skill-condenser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skill-condenser/agent.md"
  }
}
```
## Documentation

### Skill Condenser

Compress SKILL.md files using CoD with skill-format awareness. Optimized for 2-3 passes (not 5) since skills are structured, not prose.

### When to Use

SKILL.md exceeds 200 lines
Skill contains prose paragraphs instead of bullets
Refactoring verbose documentation to terse style

### Process

Read the skill to condense
Run 2-3 iterations of cod-iteration with skill-format context
Each iteration: extract key entities, compress to bullets/tables
Output: condensed skill maintaining structure

### Iteration 1: Structure Extraction

Pass to cod-iteration:

iteration: 1
target_words: [current_words * 0.6]
format_context: |
  OUTPUT FORMAT: Agent Skills SKILL.md
  - Use ## headers for sections
  - Bullet lists, not prose paragraphs
  - Tables for comparisons/options
  - Code blocks for commands
  - No filler phrases ("this skill helps you...")

text: [FULL SKILL.MD CONTENT]

### Iteration 2: Entity Densification

iteration: 2
target_words: [iteration_1_words]
format_context: |
  SKILL.md TERSE RULES:
  - Each bullet = one fact
  - Combine related bullets with semicolons
  - Remove redundant examples (keep 1 best)
  - Tables compress better than lists for options

text: [ITERATION 1 OUTPUT]
source: [ORIGINAL SKILL.MD]

### Iteration 3 (Optional): Final Polish

Only if still >150 lines:

iteration: 3
target_words: [iteration_2_words]
format_context: |
  FINAL PASS:
  - Move detailed content to references/ links
  - Keep only: Quick Start, Core Pattern, Troubleshooting
  - Each section <20 lines

text: [ITERATION 2 OUTPUT]
source: [ORIGINAL SKILL.MD]

### Expected Output Format

Each iteration returns:

Missing_Entities: "entity1"; "entity2"; "entity3"

Denser_Summary:
---
name: skill-name
description: ...
---
# Skill Name
[Condensed content in proper SKILL.md format]

### Skill-Specific Entities

When condensing skills, prioritize these entity types:

Entity TypeKeepRemoveCommandsdeploy.py --env prodVerbose explanationsOptionsTable rowParagraph per optionErrorsError → FixLong troubleshooting proseExamples1 best exampleMultiple similar examplesPrerequisitesBullet listExplanation of why needed

### Target Compression

OriginalTargetIterations200-300 lines100-1502300-500 lines150-2002-3500+ lines200 + refs3 + refactor

### Example: Compressing Verbose Section

Before (45 words):

## Configuration
The configuration system allows you to customize various aspects of the deployment.
You can set environment variables, adjust timeouts, and configure retry behavior.
Each setting has sensible defaults but can be overridden as needed.

After (18 words):

## Configuration
| Setting | Default | Override |
|---------|---------|----------|
| \`ENV\` | prod | \`--env dev\` |
| \`TIMEOUT\` | 30s | \`--timeout 60\` |
| \`RETRIES\` | 3 | \`--retries 5\` |

### Integration with Progressive Disclosure

If skill is too large after 3 iterations:

Keep in SKILL.md: Overview, Quick Start, Common Errors
Move to references/: API details, advanced config, examples
Update SKILL.md with links: See [advanced config](references/config.md)

### Constraints

Preserve frontmatter exactly (don't condense metadata)
Keep all ## section headers (structure matters)
Don't remove code blocks (commands are entities)
Maintain one concrete example per workflow
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: killerapp
- Version: 1.1.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-05T04:28:56.451Z
- Expires at: 2026-05-12T04:28:56.451Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/skill-condenser)
- [Send to Agent page](https://openagent3.xyz/skills/skill-condenser/agent)
- [JSON manifest](https://openagent3.xyz/skills/skill-condenser/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/skill-condenser/agent.md)
- [Download page](https://openagent3.xyz/downloads/skill-condenser)