practice-cognition

触发：当你提出了方案、假设或判断，需要通过实践验证、试错迭代或复盘升级认知时调用；常见信号包括 experiment、prototype、validate、iterate、feedback loop。 English: Trigger when an idea, hypothesis, or plan must be tested in practice and improved through iteration. Use this skill to move from action to understanding and back to action in a spiral learning loop.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/practice-cognition/SKILL.md

Quality

Content

70%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 instruction skill with a clear sequenced workflow, explicit feedback loops, and actionable stage-by-stage guidance. Its main weaknesses are verbosity from philosophical padding and a dangling reference to a non-existent original-texts.md file.

Suggestions

Trim or move the repeated Mao quotations and restated epistemological rationale into a separate reference so the main body stays lean and assumes Claude's existing understanding of iteration and validation.

Either create the referenced original-texts.md in a references/ bundle or remove the '详细原著依据见 original-texts.md' pointer so there is no dangling reference.

Consider condensing the two overlapping tables ('两种错误倾向' and '常见错误') that restate the same dogmatism/empiricism distinction.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but the extensive philosophical framing (Mao quotes on every step, restated rationale like '调查得到的判断，必须回到实践中经受检验') explains conceptual background Claude already grasps and could be tightened.	3 / 5
Actionability	As an instruction-only meta-reasoning skill it gives concrete stage actions ('写出"我的假说是：……"', '运行/执行，观察结果 vs 预期') and explicit do/don't tables, making the guidance mostly executable with only minor gaps.	4 / 5
Workflow Clarity	A clear 5-step sequence is paired with an operating-procedure table mapping each stage to required and forbidden actions, plus an explicit loop-termination condition and a built-in feedback loop (step 4 assesses success/failure/partial and routes back to step 1).	5 / 5
Progressive Disclosure	Content is well-organized into clear sections, but the single external reference ('详细原著依据见 original-texts.md') is a dangling pointer — no such bundle file exists — so the reference is not actually backed by the bundle.	3 / 5
	Total	15 / 20 Passed

Description

78%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 clearly states both what the skill does and when to trigger it, with concrete trigger terms and a mostly-distinct niche. It is slightly held back by abstract process-actions rather than concrete tool actions.

Dimension	Reasoning	Score
Specificity	Names the domain (practice-validated cognition) and a couple of concrete process-actions ('tested in practice', 'improved through iteration'), but the actions are abstract cognitive processes rather than the concrete tool actions seen in stronger examples; coverage is not comprehensive.	3 / 5
Completeness	Explicitly answers both 'what' (move from action to understanding and back in a spiral learning loop, test and improve through iteration) and 'when' ('Trigger when an idea, hypothesis, or plan must be tested in practice') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Provides a natural 'Trigger when' / 'Use this skill' clause plus relevant keywords (experiment, prototype, validate, iterate, feedback loop), giving good coverage, though a few natural synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	Has a fairly distinct niche framed around practice-validation and spiral iteration with its own trigger signal, though conceptually it can still overlap with general iteration/validation skills.	4 / 5
	Total	16 / 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: HughYau/qiushi-skill
Path: skills/practice-cognition/SKILL.md
Commit: cbe6b08

Reviewed: ~18 hours 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.