Individual skill
writing-for-agents
Use when authoring or restructuring an agent-consumed document, a SKILL.md or skill directory, writing skills, or deciding a skill split-or-monolith disclosure question. Not for prose style: use unslop.
.devin/skills/writing-for-agents/SKILL.md
Source commit b0e8ce89a19fac880251dc3ea1babfeb4503a4fe
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 55
- Repository last updated
- Sep 28, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- odd Repository topic
- odin Repository topic
- outline Repository topic
- outlines Repository topic
- coding-paradigm Repository topic
- outline-driven-development Repository topic
- claude-plugins Repository topic
- codex-cli Repository topic
- gemini-cli-extensions Repository topic
- outline-driven Repository topic
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 11,052 bytesSKILL.mdcore · 11,052 bytesSKILL.mdcore · 11,052 bytesSKILL.mdcore · 11,052 bytesSKILL.mdcore · 11,052 bytesagents/openai.yamlasset · 241 bytesreferences/authoring-levers.mddoc · 6,152 bytesreferences/authoring-procedure.mddoc · 4,522 bytesreferences/skill-mechanics.mddoc · 2,656 bytes
Read excerpt
# Writing for agents
One property decides whether a document works: the agent takes the same process every run. The packaging differs across a skill, an AGENTS.md, and a pointer-reached doc; the writing does not.
## Contract
| Field | Bound contract |
|---|---|
| Trigger | Author, restructure, or review an agent-consumed document; author, refactor, port, or upgrade a SKILL.md, AGENTS.md/CLAUDE.md, or skill directory; or decide whether a skill stays monolith or splits. |
| Authority | Reversible local: writes only the target document, its skill directory, and the repository-owned registration or attribution surfaces those artifacts require; rollback is version control or undo; never publishes, installs, or commits. No remote mutation. |
| Side effect | The target document is edited, split, or pruned; in mode skill, its directory and registration surfaces change. Reviews and disclosure decisions write nothing beyond the decision record. |
| Done | A cold agent routes and executes predictably with no stale duplication. For a skill write, the repository's own gate passes on every changed file. For a disclosure decision, the split-or-monolith verdict is justified with pointer hygiene and an evaluation plan. |
## Inputs