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

85%

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

77%

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, actionable thinking-method skill with a clear sequenced workflow, decision branching, and concrete operating templates. Its weaknesses are conciseness (literary epigraphs and conceptual redundancy) and a broken one-level reference to a missing original-texts.md file.

Suggestions

Trim the repeated Mao-quotation epigraphs and merge the overlapping '两种错误倾向' and '常见错误' sections to cut tokens without losing the operational guidance.

Either create the referenced original-texts.md under references/ or remove the '见 original-texts.md' pointer so the body has no dangling reference.

Consider moving the long quotation-based material into original-texts.md and keeping SKILL.md as a lean overview with a well-signaled one-level reference, which would raise the progressive_disclosure score.

Dimension	Reasoning	Score
Conciseness	The operational core (操作规程, 方法流程, decision tables) is lean, but repeated Mao-quotation epigraphs and overlapping conceptual sections (两种错误倾向 vs 常见错误) pad the content with framing Claude largely already knows, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	The 操作规程 section gives copy-paste-ready templates — mandatory stage declarations ('我目前处于：…阶段'), a concrete per-stage action table ('运行/执行，观察结果 vs 预期'), and a fill-in termination condition ('当 [具体条件] 时…') — matching the fully-executable/specific-examples anchor for an instruction skill.	3 / 3
Workflow Clarity	A clear five-step sequence (感性→理性→实践验证→评估→螺旋上升) with explicit success/failure/partial-success branching, an implicit feedback loop (failure returns to step 1), and a mandatory termination-condition checkpoint; the simple-skill and instruction-skill notes permit a 3 even without an artifact-validation step.	3 / 3
Progressive Disclosure	Sections are well-organized and the single external reference ('详细原著依据见 original-texts.md') is one level deep, but that referenced file does not exist (no references/ directory) and most reference-worthy material stays inline, fitting the 'structure present but references not cleanly resolved' anchor rather than the clean one-level-deep level.	2 / 3
	Total	10 / 12 Passed

Description

92%

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 strong: it clearly states both what the skill does and when to invoke it, with concrete natural trigger terms and third-person voice. The main weakness is moderate conflict risk, since its iteration/validation triggers are fairly generic and overlap with adjacent methodology skills.

Suggestions

Sharpen distinctiveness by naming what this skill does NOT cover (e.g., explicitly contrast with investigation-first and feedback-loop-as-coding-pattern) so the description alone disambiguates from sibling skills.

Consider adding a one-line concrete domain example (e.g., 'Use after proposing a design to decide whether to build a prototype before committing') to make the niche less abstract.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (practice-based epistemology) and multiple concrete actions/triggers — 'test in practice', 'improved through iteration', 'experiment, prototype, validate, iterate, feedback loop' — matching the 'lists multiple specific concrete actions' anchor rather than the 'some actions' level below.	3 / 3
Completeness	Explicitly answers both 'what' ('move from action to understanding and back to action in a spiral learning loop') and 'when' (an explicit 'Trigger when...'/'Use this skill' clause with common signals), satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Provides natural trigger signals users would actually say ('experiment', 'prototype', 'validate', 'iterate', 'feedback loop') plus an explicit 'Trigger when an idea, hypothesis, or plan must be tested in practice and improved through iteration', meeting the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The practice/iteration niche is somewhat specific, but trigger terms like 'validate', 'iterate', and 'experiment' are generic across engineering work and overlap with sibling skills (investigation-first, contradiction-analysis) referenced in the body, so it could still trigger for the wrong skill.	2 / 3
	Total	11 / 12 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: 6710791

Reviewed: 6 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.