agent tooling by majiayu000
Agent Output Formats Skill majiayu000/agent-output-formats
Standardized output formats for research, planning, implementation, and review agents.
What it changes View full report → Passed 22 of 22 test cases with the skill, and 10 of 22 without it.
Without skill 45%
With skill 100%
Checks it passed that the model alone missed and 26 more in the full report
12 fixed10 passed either way0 still failing0 broke
Pass-rate lift +55 pp
Tokens +59%
Agent turns 0%
Response time -37% Model gemini-3.6-flashMeasured 8/18/2026 v1 22 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/majiayu000-agent-output-formats/SKILL.md https://app.decimal.ai/s/majiayu000-agent-output-formats/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-agent-output-formats, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/majiayu000-agent-output-formats/ and pins it in .decimal/skills.lock
$ decimalai skills add majiayu000-agent-output-formatsCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/majiayu000-agent-output-formats/SKILL.md https://app.decimal.ai/s/majiayu000-agent-output-formats/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Formulate the final review verdict header for a code security audit where minor non-blocking issues were found.
What was checked, without and with the skill Checked Without skill With skill Uses the standard status flag indicating APPROVED WITH CHANGES
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 377 lines single file
Agent Output Formats Skill
Standardized output formats for all agent types to ensure consistent communication and parsing across the autonomous development workflow.
When This Skill Activates
Generating agent outputs
Parsing agent responses
Formatting research findings
Creating planning documents
Reporting implementation results
Writing code reviews
Keywords: "output", "format", "research", "planning", "implementation", "review"
Research Agent Output Format
Research agents (e.g., researcher, issue-creator, brownfield-analyzer) should structure outputs with these sections:
Template
## Patterns Found
[List of discovered patterns with examples]
- **Pattern Name**: Description
- Example: Code snippet or reference
- Use case: When to apply this pattern
## Best Practices
[Industry best practices and recommendations]
- **Practice Name**: Description
- Benefit: Why this matters
- Implementation: How to apply
## Security Considerations
Track record Benchmark 22 / 22
test cases passed, vs 10 / 22 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 majiayu000 / claude-skill-registry
skills/agent/agent-output-formats/SKILL.md
View on GitHub ↗ License MITImported 8/3/2026Version v1