Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt When submitting a completed documentation release PR, what summary section describes what the software actually does now?
What was checked, without and with the skill Checked Without skill With skill The response includes 'Behavior now documented' as a required component of the output report. Missed Passed
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 29 lines single file
gstack-document-release
Use this skill to keep docs aligned with shipped behavior.
Workflow
Inspect the current diff and identify user-visible changes.
Map affected docs: README files, plugin READMEs, desktop docs, examples, settings, and scripts.
Check for stale commands, paths, model/provider names, environment variables, screenshots, and troubleshooting text.
Update only the docs that are directly affected.
Verify links, commands, and JSON snippets where practical.
Documentation Standard
Prefer Diataxis-style clarity:
Tutorial: first successful path
How-to: task-specific steps
Reference: exact flags, settings, APIs, schemas
Explanation: architecture and tradeoffs
Output
Report:
Docs changed
Behavior now documented
Commands or snippets verified
Known documentation gaps left for later
When it activates Automatically, when a task matches.
Use when behavior, setup, CLI flags, desktop workflow, provider support, or plugin surfaces changed.
Track record Benchmark 19 / 21
test cases passed, vs 16 / 21 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported ling71671 / open-claudecode
plugins/gstack-workflows/skills/gstack-document-release/SKILL.md
View on GitHub ↗ License NOASSERTIONImported 8/3/2026Version v1