ancient-chinese-calendar-determination

Use when establishing an agricultural calendar or determining equinoxes and solstices. Guides celestial observation at four cardinal stations to fix seasonal timing using star positions and daylight measurement.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 compact, well-organized procedural skill with concrete named entities and an explicit validation section. It would benefit from interleaving validation checkpoints and trimming observational flavor notes, but is otherwise strong.

Suggestions

Interleave validation checkpoints within the steps (e.g., after each station observation) and add a brief feedback loop for what to do when a station reports an unexpected star or day-length.

Trim the descriptive 'Observe:' flavor notes (e.g., 'people wear less clothing, animals shed fur') to tighten token efficiency unless they are operationally meaningful.

Add concrete measurement specifics (e.g., how equal day-night is determined, how the 366-day count is reconciled) to lift actionability from mostly-executable to fully executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and well-structured without explaining concepts Claude already knows, though the per-station 'Observe:' flavor notes ('people wear less clothing, animals shed fur') are minor padding that could be trimmed.	4 / 5
Actionability	Provides concrete, specific guidance (named officials, named locations, named mid-heaven stars Niao/Huo/Xu/Mao, equal day-night test, 366-day year with leap months) that is actionable for an instruction-only skill, with only minor gaps in measurement detail.	4 / 5
Workflow Clarity	A clear six-step sequence is paired with an explicit Validation section listing verification checks; it falls short of 5 because validation is a trailing block rather than interleaved checkpoints with feedback loops for error recovery.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references, and content is organized into clearly labeled sections (Overview, Steps, Expected Outcomes, Validation), satisfying the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

87%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 well-crafted: it explicitly states both the capability and the trigger conditions using concrete, domain-specific language. It is concise, distinctive, and uses appropriate third-person voice.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Guides celestial observation at four cardinal stations to fix seasonal timing using star positions and daylight measurement'), but the actions are woven into a single descriptive sentence rather than a comprehensive enumerated list.	4 / 5
Completeness	Explicitly answers both what ('Guides celestial observation at four cardinal stations to fix seasonal timing...') and when ('Use when establishing an agricultural calendar or determining equinoxes and solstices') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger terms users would say ('agricultural calendar', 'equinoxes and solstices') with good coverage, though a few synonymous phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ancient Chinese calendar determination via cardinal-station celestial observation) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: baojie/shiji-kb
Path: kg/ontology/ontology-v1/skus/procedural/skill_001/SKILL.md
Commit: 6b836e3

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

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.