assets
Soft authoring conventions for skill assets as reusable, just-in-time procedural rulebooks.
- License 许可
- MPL-2.0
- 所属仓库
- itlackey/akm
- 最近更新
- 2026-11-12
- Stars
- ★ 70
- Forks
- 4
01 前言 Front Matter
- type
- fact
- updated
- 1785196800000
- category
- convention
- description
- Soft authoring conventions for skill assets as reusable, just-in-time procedural rulebooks.
- when_to_use
- Surfaced to authoring agents when they write or revise a skill asset.
02 资源文件 8
- 参考文档agent.md2.3 KB
- 参考文档command.md2.2 KB
- 参考文档fact.md2.7 KB
- 参考文档knowledge.md2.9 KB
- 参考文档lesson.md2.4 KB
- 参考文档memory.md2.3 KB
- 参考文档script.md2.4 KB
- 参考文档workflow.md2.2 KB
03 SKILL.md 正文
<!-- SOFT guidance only — advice, not a contract. Nothing here is enforced by the proposal gate; validator-rejecting HARD rules live in src/core/authoring-rules.ts and remain the sole enforced source. Editing or deleting this file cannot weaken the gate. Tune the guidance below to match how your stash wants this asset type maintained. -->
Skill authoring conventions
A skill is a reusable, self-contained capability stored as skills/<name>/SKILL.md. Treat it like a compact operating manual that an agent can load just-in-time, follow without rediscovering the process, and improve when repeated use exposes gaps.
Purpose
Use a skill when the stash needs reusable procedural guidance for a recurring class of work. A good skill reduces repeated reasoning cost: future agents should not have to reconstruct the same method from raw context.
Authoring strategy
- Make the dispatch signal clear. The description should let a dispatcher decide whether to load the skill without reading the whole body.
- Open with the outcome the skill helps produce.
- State when to use it, when not to use it, and what inputs the agent should gather before acting.
- Structure the body as a rulebook: principles first, then procedure, then checks.
- Use short sections and ordered steps where sequence matters.
- Match the level of detail to how fragile the task is: open-ended work gets high-level heuristics and room to reason, while fragile or consistency-critical steps get exact, unambiguous instructions.
- Keep the body lean and move bulky background into companion knowledge docs referenced one level deep, so the skill loads cheaply and stays scannable.
- Include failure modes and verification steps. A skill should tell the agent how to know the work is complete.
- Keep one skill focused on one capability. Split unrelated concerns into separate skills and cross-reference them.
Maintenance strategy
- Update the skill when session logs, feedback, or rejected proposals reveal repeatable confusion.
- Add companion knowledge docs when the skill needs background material that would bloat the main procedure.
- Promote durable recurring corrections into the skill; leave one-off observations in memories or lessons.
- Prefer small edits that preserve the skill’s operational shape over broad rewrites that erase tested guidance.
Placement & linking
- Skills are reuse-born: place
skills/<domain>/<name>/SKILL.mdunder a stable domain prefix fromfacts/conventions/domains(skills/testing/flaky-test-triage) so any project finds and reuses it instead of duplicating the procedure.
04 同仓库更多 Skills
svelte-components
Build reusable Svelte components with best practices for composition and state management
k8s-deploy
Deploy and manage applications on Kubernetes clusters with kubectl and Helm
docker-homelab
Manage Docker containers, images, and networks in a homelab environment
code-review-skill
Review code for quality issues, bugs, and adherence to best practices
hello-world
Trivial demonstration skill that prints a greeting
all-types-skill
Minimal skill fixture used by the all-types parity stash