BC deep-research-forge
深度研究与决策分析 skill。用于系统研究一个产品、公司、人物、概念、技术、赛道或文化现象，先选择研究方法论组合，再建立研究问题、证据账本、正式状态层级和结论级引用映射，动态组合时间轴、竞品截面、用户选择、生态地图、因果机制、反方证据、场景推演和决策模块；复杂研究可启用多 Agent 并行执行，把来源搜证、时间线、竞品截面、反方证据和决策综合拆成并行研究小队，最后输出研究报告、决策简报、复盘评分或可复用研究资产。用户会说“研究一下”“深度分析”“竞品分析”“帮我搞懂”“横纵分析”“做个 deep research”“多 agent 并行研究”“这个公司/产品/概念是什么来头”“值不值得关注/投入/学习/跟进”等。
深度研究与决策分析 skill。用于系统研究一个产品、公司、人物、概念、技术、赛道或文化现象，先选择研究方法论组合，再建立研究问题、证据账本、正式状态层级和结论级引用映射，动态组合时间轴、竞品截面、用户选择、生态地图、因果机制、反方证据、场景推演和决策模块；复杂研究可启用多 Agent…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityassets/research-envelope-template.md:188Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### 5. 反方证据（Red Team Dissent）
-
low Risky intent
intent-offensive-securityreferences/dynamic-output-composer.md:22Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `decision-brief` | decision question, verdict, evidence, risk, reversal conditions | competitive matrix, monitoring, red team |
Files scanned: 78. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "archetype"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 130 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1622 tokens
- 100Running it twice. No mutating operations
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 311: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 130 items
- +4Reference files are cited in the instructions (10 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.