CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-memory

使用于 Comet 需要根据有界语义评审包判断是否值得保存个人记忆、候选、更新、遗忘或跳过时。

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./assets/skills-zh/comet-memory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is a tightly written, actionable reviewer contract with a precise JSON output schema, copy-paste examples, a clear numbered decision sequence, and a useful common-errors checklist. Its main weakness is mild cross-section redundancy and externalized validation rather than an internal feedback loop.

Suggestions

De-duplicate the single-scope and skip-is-normal rules so each appears once (e.g., state them in 固定输出 and reference rather than restate in 判断顺序/常见错误) to tighten conciseness.

Add an explicit internal validation/recovery micro-step (e.g., 'before emitting, re-check that actions use one scope and obey budget') to strengthen workflow_clarity toward 5.

Consolidate 常见错误 into the matching 判断顺序/判断示例 entries or trim overlaps to sharpen progressive disclosure.

DimensionReasoningScore

Conciseness

Dense, well-organized instruction with no padding about concepts Claude already knows; minor redundancy where the single-scope and skip-is-normal rules recur across sections, matching 'efficient; minor instances that could be trimmed'.

4 / 5

Actionability

Provides a fully executable output contract: exact JSON field names, literal schema value, a fixed action enum, and two copy-paste-ready JSON examples covering the empty and skip cases.

5 / 5

Workflow Clarity

A numbered 判断顺序 with explicit precedence gives a clear decision sequence plus a 常见错误 checklist; validation/retry is externalized to the host rather than an internal validate-fix-retry loop, so not 5.

4 / 5

Progressive Disclosure

Self-contained body with clear section headers and no nested bundle references (no references/scripts/assets exist); slightly above the simple-skill line with minor overlap between 常见错误 and the judgment rules, matching 'good structure; minor organization gaps'.

4 / 5

Total

17

/

20

Passed

Description

71%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 and clearly niche-scoped with an explicit use-when clause, but its trigger terms lean on internal protocol jargon rather than natural user language, weakening trigger-term quality. It answers both what and when but the 'when' is abstract rather than user-facing.

Suggestions

Add natural-language trigger phrases a user would actually say (e.g., 'remember this', 'forget that preference') alongside the internal protocol terms to improve trigger_term_quality.

Make the 'when' clause more concrete by naming observable user intents rather than only the internal packet mechanism.

Include a short list of concrete observable actions (e.g., 'reviews a bounded memory packet and returns create/update/forget/skip') to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Enumerates concrete decision outcomes (保存/候选/更新/遗忘/跳过) within its niche, matching the 'several specific actions; minor gaps' anchor; not a comprehensive standalone capability list so not 5.

4 / 5

Completeness

Has both a clear 'what' (semantic review deciding save/candidate/update/forget/skip) and an explicit 'when' clause (使用于...时); the 'when' is internal/abstract rather than concrete user triggers, so not 5.

4 / 5

Trigger Term Quality

Contains domain-relevant terms (有界语义评审包, 个人记忆) but they are internal/abstract rather than natural phrases a user would say, with no synonyms; matches 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

Highly niche Comet-specific protocol with distinct internal triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rpamis/comet
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.