Real Skill packageSource verifiedClawHub registry

agent-instruction-slimming

Reduce an agent instruction file (AGENTS.md, system prompt, rule file) without losing coverage: lever order (remove first, move second, reformat third, rewrite last), verbatim-subset edits with pointer lines, joint marker accounting, and tiering by frequency and reversibility. Use when a rule file has grown too large, when rules are being ignored, or before adding more rules. Tool-agnostic; includes marker counting and subset checking scripts.

Identity and source

Publisher attributioncengcengcai-creatorregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 61% rule confidence
Package forminstruction with code10 recorded files
Canonical sourceClawHub registryclawhub:cengcengcai-creator:agent-instruction-slimming
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 11/8/2026.claude/skills/agent-instruction-slimming

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 11/8/2026.agents/skills/agent-instruction-slimming

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 11/8/2026skills/agent-instruction-slimming

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @cengcengcai-creator/agent-instruction-slimming
clawhub inspect @cengcengcai-creator/agent-instruction-slimming --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
10 / 10 inspected as text
Checked
11/8/2026, 5:59:45 AM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
11/7/2026, 3:23:50 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:0735d096e8f58ab5bf3d7f2a54127a05d5b7328c856d37298d2941d45cbbe16f
Show up to 10 recorded paths
  • examples/moved.md
  • examples/original.md
  • examples/slim.md
  • LICENSE
  • README.md
  • references/verbatim-subset.md
  • scripts/cond_count.py
  • scripts/subset_check.py
  • skill-card.md
  • SKILL.md

Source changelog

Introduces agent-instruction-slimming 1.0.0, a workflow for reducing instruction files while tracking coverage. - Sets a lever order: remove, move, reformat, then rewrite. - Requires verbatim subset edits when relocating content, with pointer lines and subset verification. - Adds joint marker accounting, section-level attribution, and tiering guidance for rule placement. - Includes a step-by-step procedure, scripts for marker counting and subset checking, and limitations on what structural measures can prove.