CtrlK
BlogDocsLog inGet started
Tessl Logo

publish-and-reuse

Personal AI Infrastructure 多设备生命周期同步总入口:一句“同步一下我的 Personal AI”自动判断 PULL/MERGE/NO ACTION/REVIEW/BLOCKED(AUTO_SYNC),覆盖 agent-tools、personal-ai-state(curated + Dynamic Memory 合并)、项目仓库、runtime refresh 与新设备 Fresh Restore;同时保留 DSH 四层环境上传/更新/体检/复现作为子步骤。只自动处理确定安全的变更,冲突与 dirty 一律留给人工;commit/push 受 canonical ownership lease 与 receipt 约束。

55

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/publish-and-reuse/SKILL.md

The canonical home for this skill is publish-and-reuse in ooooooooooooooooooop/agent-tools

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-structured overview with concrete commands, an explicit sequenced workflow, validation/rollback checkpoints, and a clearly signaled one-level-deep reference. Its main weakness is moderate verbosity from inlined DSH detail and a long safety-rules list that duplicates the reference.

Suggestions

Trim the inlined 'DSH 四层子流程' section to a one-line pointer; the full `sync_skills.py` command and subflow detail belong in the reference.

Reduce the 12 safety rules to the few not already enforced by the orchestrator, pointing to the reference's SYNC_OWNERSHIP_MATRIX for the full set.

Convert the prose workflow sequence into numbered steps so the validation and rollback checkpoints are visually distinct.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes Claude's competence (no basic-concept padding), but the inlined DSH 四层 subflow section and the 12-rule safety list duplicate material in the reference and could be tightened.

3 / 5

Actionability

Provides concrete, executable commands — `personal_ai_sync.py check/sync/restore`, the full `sync_skills.py` invocation with destinations, and `validate_repo.py --strict` — with only minor gaps in the prose-described internal sequence.

4 / 5

Workflow Clarity

The orchestration sequence (fetch → classify → action plan → safe actions → aic apply → derived refresh → validate → checkpoint) is explicit with validation and snapshot/post-diff/rollback feedback loops present, so the destructive-skill cap does not apply; minor gap is that the sequence is one prose line rather than numbered steps.

4 / 5

Progressive Disclosure

SKILL.md stays an overview and points one level deep to the verified `references/personal-ai-lifecycle-sync.md` (297 lines), clearly signaled with '先读它再执行非常规场景'; minor gap is that docs/publishing.md and docs/sync-ongoing.md are referenced but not in the bundle.

4 / 5

Total

15

/

20

Passed

Description

58%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 conveys a clear, specific niche and concrete capabilities but is dense with internal jargon and lacks an explicit trigger-guidance clause. It reads as comprehensive yet slightly over-claimed, with the "when" only weakly embedded.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g. 'Use when the user says 同步一下我的 Personal AI or asks to sync, upload, check, or restore their Personal AI environment across devices').

Surface natural synonyms and variations in the description itself (同步 / 更新 / 上传环境 / 环境体检 / 新设备复现) instead of relying on the separate triggers field.

Trim internal terminology (AUTO_SYNC, canonical ownership lease, DSH 四层, MemoryProvider contracts) from the description to reduce the over-claim feel and improve readability.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — auto-classify PULL/MERGE/NO ACTION/REVIEW/BLOCKED, cover agent-tools/personal-ai-state/projects/runtime refresh/Fresh Restore, plus DSH upload/update/checkup/reproduce as substeps — giving broad coverage, though heavy internal jargon slightly muddies a few actions.

4 / 5

Completeness

The "what" is clear and detailed, but "when" is only weakly implied via the embedded phrase rather than an explicit "Use when..." clause, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Embeds one natural phrase users would say ("同步一下我的 Personal AI"), but the description itself carries no synonyms or common variations (同步/更新/上传/体检/复现), which live only in the separate triggers field.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Personal AI Infrastructure multi-device lifecycle sync) with distinct triggers; minor overlap risk only with declared dependencies dsh-config-sync and environment-bootstrap.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

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.