返回技能列表

conscientiousness

pjt222
更新于 2 days ago
7 次查看
17
2
17
在 GitHub 上查看
其他ai

关于

This skill systematically verifies work, checks for completeness, and ensures results match the original request before marking a task as done. It is designed for use when a response feels "good enough," after complex multi-step operations, or to counter patterns of rushing. It enforces thoroughness by having the AI review its own output against commitments, preventing corner-cutting.

快速安装

Claude Code

推荐
主要方式
npx skills add pjt222/agent-almanac -a claude-code
插件命令备选方式
/plugin add https://github.com/pjt222/agent-almanac
Git 克隆备选方式
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/conscientiousness

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Conscientiousness

Systematic thoroughness + diligence → ensure completeness, verify results, follow through every commitment, finish tasks to standard deserved.

Use When

  • Before marking task complete → final verification pass
  • Res feels "good enough" but task deserves better
  • Post complex multi-step op where steps may have drifted
  • User req has multi parts + each needs verification
  • Before submitting code, docs, or any deliverable for user review
  • Self-monitoring detects pattern of cutting corners / rushing

In

  • Required: Task / deliverable to verify (from conv context)
  • Optional: Original user req (compare vs. what delivered)
  • Optional: Any checklist / acceptance criteria from user
  • Optional: Prior commitments during session (things promised but not checked)

Do

Step 1: Reconstruct Full Commitment

Before checking work → re-establish exactly what was committed.

  1. Re-read user's original req carefully → not interpreted version, actual words
  2. List every explicit req mentioned
  3. List every implicit commitment made during session:
    • "I'll also update the tests" — was this done?
    • "Let me fix that too" — was this completed?
    • "I'll check for edge cases" — were they checked?
  4. Note any acceptance criteria from user
  5. Compare commitment list vs. what actually delivered

Full commitment list — explicit reqs + implicit promises — w/ prelim match vs. deliverables.

If err: Original req no longer in context (compressed) → reconstruct from what remains + acknowledge gaps to user.

Step 2: Verify Completeness

Check every committed item addressed.

Completeness Matrix:
+---------------------+------------------+------------------+
| Commitment          | Status           | Evidence         |
+---------------------+------------------+------------------+
| [Requirement 1]     | Done / Partial / | [How verified]   |
|                     | Missing          |                  |
+---------------------+------------------+------------------+
| [Requirement 2]     | Done / Partial / | [How verified]   |
|                     | Missing          |                  |
+---------------------+------------------+------------------+
| [Promise 1]         | Done / Partial / | [How verified]   |
|                     | Missing          |                  |
+---------------------+------------------+------------------+
  1. Each item → valid. w/ evidence, not memory, actual verification:
    • Code changes: re-read file to confirm change exists
    • Test results: re-run or ref actual out
    • Docs: re-read to confirm accuracy
  2. Mark each: Done (full complete), Partial (started, incomplete), Missing (not addressed)
  3. Partial + Missing → note what remains

Every commitment has verified status. No item unchecked.

If err: Verification reveals missed items → address immediately vs. note for later. Conscientiousness = completing now, not intending to complete.

Step 3: Verify Correctness

Completeness necessary but not sufficient → what was done must also be right.

  1. Each completed item → check:
    • Accuracy: Does it do what it should? Values correct?
    • Consistency: Aligns w/ rest of work? No contradictions?
    • Edge cases: Boundary conditions considered?
    • Integration: Works w/ surrounding context?
  2. Code: would this survive code review? Obvious improvements?
  3. Docs: accurate, clear, free of errs?
  4. Multi-step processes: out of each step correctly feeds next?

Each deliverable complete + correct. Errs caught before user sees them.

If err: Errs found → fix immediately. Don't present work w/ known errs, even if minor.

Step 4: Verify Presentation

Final check: deliverable presented in way serving user?

  1. Clarity: User can understand w/o re-reading multi times?
  2. Organization: Res structured logically? Related items grouped?
  3. Conciseness: Unnecessary padding / repetition?
  4. Actionability: User knows what to do next?
  5. Honesty: Limitations / caveats clearly stated?

Deliverable complete, correct, well-presented.

If err: Presentation poor despite correct content → restructure. Good work poorly presented = conscientiousness failure.

Check

  • Original req re-read (not recalled from memory)
  • Every explicit req verified w/ evidence
  • Every implicit promise tracked + verified
  • Correctness checked beyond mere completeness
  • Edge cases considered where relevant
  • Deliverable clearly presented + actionable

Traps

  • Verification theater: Going through motions of checking w/o actually re-reading / re-verifying. Check must use evidence, not memory.
  • Partial conscientiousness: Checking main deliverable but ignoring side commitments ("I'll also..."). Every promise counts.
  • Perfectionism masquerading as diligence: Endless polishing delays delivery. Conscientiousness = meeting committed standard, not exceeding indefinitely.
  • Conscientiousness fatigue: Becoming less thorough as session progresses. Last task deserves same diligence as first.
  • Skip for simple tasks: Assuming simple tasks don't need verification. Simple tasks w/ errs more embarrassing than complex w/ errs.

  • honesty-humility — conscientiousness verifies completeness; honesty-humility ensures transparent reporting of what was + wasn't achieved
  • heal — subsystem assessment overlaps w/ self-verification; conscientiousness focuses on deliverable quality
  • vishnu-bhaga — preservation of working state complements conscientiousness in maintaining quality
  • observe — sustained neutral observation supports verification process
  • intrinsic — genuine engagement (not compliance) drives thorough exec naturally

GitHub 仓库

pjt222/agent-almanac
路径: i18n/caveman-ultra/skills/conscientiousness
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

相关推荐技能

llamaguard

其他

LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。

查看技能

cost-optimization

其他

这个Claude Skill帮助开发者优化云成本,通过资源调整、标记策略和预留实例来降低AWS、Azure和GCP的开支。它适用于减少云支出、分析基础设施成本或实施成本治理策略的场景。关键功能包括提供成本可视化、资源规模调整指导和定价模型优化建议。

查看技能

quantizing-models-bitsandbytes

其他

这个Skill使用bitsandbytes库量化大语言模型,能在GPU内存有限时通过8位或4位量化减少50-75%内存占用,同时保持精度损失最小。它支持INT8、NF4、FP4等多种量化格式,可与HuggingFace Transformers无缝集成,适用于需要部署更大模型或加速推理的场景。还提供QLoRA训练和8位优化器支持,让开发者能轻松实现高效模型压缩。

查看技能

dispatching-parallel-agents

其他

该Skill用于并行处理3个以上无依赖关系的独立故障,可为每个问题域分派专属Claude代理同时执行调查修复。它通过并发处理多个独立问题显著提升故障排查效率,特别适用于测试文件、子系统等无共享状态的场景。

查看技能