CtrlK
BlogDocsLog inGet started
Tessl Logo

dsh-config-sync

把 DSH(DeepSeek Harness)的用户配置(~/.dsh 下的 AGENTS.md、settings.yaml 及可选 profiles/预设)打包成脱敏骨架并在设备间安全同步恢复,提供只读审计、显式应用与 SHA-256 校验,绝不携带凭据和运行态。用于复现 DSH 环境、跨设备迁移偏好与模型路由配置。

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is dsh-config-sync in ooooooooooooooooooop/agent-tools

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with strong, validated workflows and concrete operational detail. Its main weakness is progressive disclosure: the provided reference and script bundles are not navigated to from the body.

Suggestions

Link references/manifest.md from the 纳入与排除清单 section (e.g. 'See [manifest.md](references/manifest.md) for the full include/exclude and scan rules') and keep the inline table as a summary rather than a duplicate.

Reference scripts/sync_dsh_config.py in the 打包/恢复 sections with an example invocation (e.g. `python scripts/sync_dsh_config.py export --template`) so the modes map to an executable entry point.

Move the detailed 敏感扫描规则 out of the body into manifest.md, leaving only the PASS/FAIL/PARTIAL decision rules inline, to reduce duplication and tighten conciseness.

DimensionReasoningScore

Conciseness

The body is operational and dense with no concept padding, but the include/exclude table and scan rules duplicate content already in references/manifest.md, leaving minor trimmable redundancy.

4 / 5

Actionability

Concrete flags (--with-optional, --template), placeholder syntax, exact paths, and check/apply/export modes give mostly executable guidance; the gap is that the implementing scripts/sync_dsh_config.py is never referenced or shown.

4 / 5

Workflow Clarity

Export (7 steps) and restore (4 steps) are clearly sequenced with explicit validation checkpoints — sensitive scan that FAILs and stops, read-only check before apply, and post-apply SHA-256 — plus a feedback loop and an evidence checklist.

5 / 5

Progressive Disclosure

Bundle files exist (references/manifest.md, scripts/sync_dsh_config.py) but are never linked or signaled from the body, and include/exclude content that already lives in manifest.md is duplicated inline.

3 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and cleanly separates what from when, with an explicit trigger clause and a well-bounded niche. Its only weakness is slightly limited trigger-term variety.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 打包成脱敏骨架、安全同步恢复、只读审计、显式应用、SHA-256 校验、绝不携带凭据和运行态 — covering the domain comprehensively rather than in the abstract.

5 / 5

Completeness

Explicitly states both what the skill does (pack/sync/restore/audit/verify) and when to use it via the 用于复现…迁移… clause, satisfying both halves with concrete triggers.

5 / 5

Trigger Term Quality

Natural user phrases appear (复现 DSH 环境、跨设备迁移偏好与模型路由配置), but coverage lacks synonyms and file-extension variants a user might also say.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (DSH config only) and explicitly excludes the skills-stack domain, minimizing overlap with sibling skills like environment-bootstrap.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
ooooooooooooooooooop/personal-ai
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.