@codewizard-dt/bootstrap 2.10.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.github/workflows/build.yml +88 -0
- package/.github/workflows/security.yml +24 -0
- package/.gitleaks.toml +15 -0
- package/README.md +472 -0
- package/bin/cli.js +47 -0
- package/lib/README.md +27 -0
- package/lib/hooks/README.md +316 -0
- package/lib/hooks/env-file-guard.js +45 -0
- package/lib/hooks/git-protected-ops-block.js +77 -0
- package/lib/hooks/lib/serena-languages.js +158 -0
- package/lib/hooks/lib/serena.js +787 -0
- package/lib/hooks/mv-absolute-path-block.js +53 -0
- package/lib/hooks/serena-bash-grep-block.js +501 -0
- package/lib/hooks/serena-edit-guard.js +74 -0
- package/lib/hooks/serena-first-glob-guard.js +94 -0
- package/lib/hooks/serena-first-guard.js +74 -0
- package/lib/hooks/serena-first-read-guard.js +167 -0
- package/lib/hooks/serena-pre-delegation.js +117 -0
- package/lib/hooks/serena-session-reset.js +45 -0
- package/lib/hooks/serena-usage-tracker.js +186 -0
- package/lib/hooks/serena-write-guard.js +58 -0
- package/lib/prompts/README.md +16 -0
- package/lib/prompts/migrate-wiki.md +111 -0
- package/lib/prompts/setup-deployment.md +322 -0
- package/lib/prompts/setup-design-system.md +162 -0
- package/lib/prompts/setup-strict-typechecks.md +139 -0
- package/lib/scripts/README.md +49 -0
- package/lib/scripts/bootstrap-serena.sh +145 -0
- package/lib/scripts/build-mcp-guide.sh +108 -0
- package/lib/scripts/install-global.sh +78 -0
- package/lib/scripts/install-mcps.sh +131 -0
- package/lib/scripts/lib.sh +154 -0
- package/lib/scripts/merge-gitignore.sh +65 -0
- package/lib/scripts/migrate-project.sh +273 -0
- package/lib/scripts/setup-deployment.sh +104 -0
- package/lib/scripts/setup-project.sh +55 -0
- package/lib/scripts/setup-runner.sh +99 -0
- package/lib/scripts/setup-strict-typechecks.sh +29 -0
- package/lib/scripts/startup.sh +42 -0
- package/lib/scripts/sync-wiki-scaffold.sh +104 -0
- package/lib/scripts/templates/CLAUDE-env-safety.md +3 -0
- package/lib/scripts/templates/CLAUDE-wiki.md +60 -0
- package/lib/scripts/templates/gitignore +136 -0
- package/lib/scripts/templates/guides/stubs/00-header.md +15 -0
- package/lib/scripts/templates/guides/stubs/brave-search.md +20 -0
- package/lib/scripts/templates/guides/stubs/context7.md +26 -0
- package/lib/scripts/templates/guides/stubs/playwright.md +26 -0
- package/lib/scripts/templates/guides/stubs/serena.md +219 -0
- package/lib/scripts/templates/wiki/conventions.md +100 -0
- package/lib/scripts/templates/wiki/dashboard.html +1733 -0
- package/lib/scripts/templates/wiki/hot.md +21 -0
- package/lib/scripts/templates/wiki/index.md +46 -0
- package/lib/scripts/templates/wiki/knowledge/concepts/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/components/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/organisations/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/people/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/tools/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/sources/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/log.md +14 -0
- package/lib/scripts/templates/wiki/work/bugs/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/bugs/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/bugs/index.md +12 -0
- package/lib/scripts/templates/wiki/work/bugs/lifecycle.md +39 -0
- package/lib/scripts/templates/wiki/work/decisions/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/decisions/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/decisions/index.md +12 -0
- package/lib/scripts/templates/wiki/work/decisions/lifecycle.md +42 -0
- package/lib/scripts/templates/wiki/work/requirements/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/requirements/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/requirements/index.md +12 -0
- package/lib/scripts/templates/wiki/work/requirements/lifecycle.md +34 -0
- package/lib/scripts/templates/wiki/work/roadmaps/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/roadmaps/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/roadmaps/index.md +12 -0
- package/lib/scripts/templates/wiki/work/roadmaps/lifecycle.md +32 -0
- package/lib/scripts/templates/wiki/work/tasks/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/tasks/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/tasks/index.md +12 -0
- package/lib/scripts/templates/wiki/work/tasks/lifecycle.md +39 -0
- package/lib/scripts/templates/wiki/work/uat/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/uat/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/uat/index.md +12 -0
- package/lib/scripts/templates/wiki/work/uat/lifecycle.md +48 -0
- package/lib/scripts/templates/wiki/work/uat/screenshots/.gitkeep +0 -0
- package/lib/scripts/update-project.sh +75 -0
- package/lib/scripts/wiki-dashboard-server.js +146 -0
- package/lib/skills/README.md +146 -0
- package/lib/skills/anti-slop/SKILL.md +183 -0
- package/lib/skills/bug-close/SKILL.md +136 -0
- package/lib/skills/bug-file/SKILL.md +114 -0
- package/lib/skills/bug-triage/SKILL.md +140 -0
- package/lib/skills/company-align/SKILL.md +203 -0
- package/lib/skills/debug-logs/SKILL.md +129 -0
- package/lib/skills/decision-create/SKILL.md +220 -0
- package/lib/skills/decision-finalize/SKILL.md +181 -0
- package/lib/skills/decision-next/SKILL.md +129 -0
- package/lib/skills/decision-walkthrough/SKILL.md +169 -0
- package/lib/skills/demo/SKILL.md +183 -0
- package/lib/skills/elevator-pitch/SKILL.md +125 -0
- package/lib/skills/eval-create/SKILL.md +344 -0
- package/lib/skills/eval-gap/SKILL.md +150 -0
- package/lib/skills/eval-run/SKILL.md +214 -0
- package/lib/skills/extract-feature/SKILL.md +344 -0
- package/lib/skills/flashcard/SKILL.md +513 -0
- package/lib/skills/frontend-taste/SKILL.md +184 -0
- package/lib/skills/gap-assess/SKILL.md +97 -0
- package/lib/skills/git-commit/SKILL.md +164 -0
- package/lib/skills/lint/SKILL.md +99 -0
- package/lib/skills/marp-slideshow/SKILL.md +212 -0
- package/lib/skills/mermaid-flowchart/SKILL.md +194 -0
- package/lib/skills/now/SKILL.md +36 -0
- package/lib/skills/port-feature/SKILL.md +315 -0
- package/lib/skills/power-mode/SKILL.md +184 -0
- package/lib/skills/primer/SKILL.md +84 -0
- package/lib/skills/project-readme/SKILL.md +166 -0
- package/lib/skills/req-compile/SKILL.md +131 -0
- package/lib/skills/req-create/SKILL.md +124 -0
- package/lib/skills/req-extract-decisions/SKILL.md +241 -0
- package/lib/skills/req-finalize/SKILL.md +251 -0
- package/lib/skills/req-retire/SKILL.md +185 -0
- package/lib/skills/req-update/SKILL.md +265 -0
- package/lib/skills/research/SKILL.md +250 -0
- package/lib/skills/research-company/SKILL.md +345 -0
- package/lib/skills/roadmap-add/SKILL.md +238 -0
- package/lib/skills/roadmap-create/SKILL.md +223 -0
- package/lib/skills/roadmap-next/SKILL.md +132 -0
- package/lib/skills/security-audit/SKILL.md +246 -0
- package/lib/skills/serena-config/SKILL.md +92 -0
- package/lib/skills/simplify/SKILL.md +227 -0
- package/lib/skills/tackle/SKILL.md +156 -0
- package/lib/skills/task-add/SKILL.md +208 -0
- package/lib/skills/task-audit/SKILL.md +294 -0
- package/lib/skills/task-trash/SKILL.md +115 -0
- package/lib/skills/task-update/SKILL.md +136 -0
- package/lib/skills/uat-auto/SKILL.md +69 -0
- package/lib/skills/uat-auto-plus/SKILL.md +115 -0
- package/lib/skills/uat-generate/SKILL.md +289 -0
- package/lib/skills/uat-skip/SKILL.md +169 -0
- package/lib/skills/uat-walk/SKILL.md +164 -0
- package/lib/skills/uat-walk/UAT-CORE.md +140 -0
- package/lib/skills/update-docs/SKILL.md +75 -0
- package/lib/skills/wiki-archive/SKILL.md +96 -0
- package/lib/skills/wiki-ingest/SKILL.md +139 -0
- package/lib/skills/wiki-lint/SKILL.md +131 -0
- package/lib/skills/wiki-query/SKILL.md +71 -0
- package/lib/skills/wiki-rotate-log/SKILL.md +90 -0
- package/lib/skills/wiki-tidy/SKILL.md +107 -0
- package/package.json +32 -0
- package/raw/.gitkeep +0 -0
- package/raw/design-principles.md +65 -0
- package/raw/guides/command-anti-patterns.md +79 -0
- package/raw/guides/deployment-strategy.md +448 -0
- package/raw/guides/evals-framework.md +452 -0
- package/raw/guides/mcp-tools.md +335 -0
- package/raw/guides/task-spec.md +79 -0
- package/raw/guides/type-checking-templates/README.md +112 -0
- package/raw/guides/type-checking-templates/eslint/eslint.config.ts +105 -0
- package/raw/guides/type-checking-templates/python/mypy.ini +69 -0
- package/raw/guides/type-checking-templates/python/pyproject.toml +164 -0
- package/raw/guides/type-checking-templates/python/pyrightconfig.json +67 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.app.jsonc +45 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.lib.jsonc +44 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.node-esm.jsonc +40 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.node.jsonc +34 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.vite-root.json +8 -0
- package/raw/harness-notes.md +20 -0
- package/raw/house-style/components/Badge.tsx +16 -0
- package/raw/house-style/components/Button.tsx +32 -0
- package/raw/house-style/components/Card.tsx +26 -0
- package/raw/house-style/components/Chip.tsx +57 -0
- package/raw/house-style/components/IconButton.tsx +67 -0
- package/raw/house-style/components/Modal.tsx +18 -0
- package/raw/house-style/components/Stepper.tsx +141 -0
- package/raw/house-style/components/icons.tsx +128 -0
- package/raw/house-style/preview/src/index.css +46 -0
- package/raw/house-style/tokens/tailwind.preset.ts +49 -0
- package/raw/house-style/tokens/tokens.json +62 -0
- package/raw/llm-wiki-2.md +162 -0
- package/raw/llm-wiki.md +75 -0
- package/raw/research/dark-mode-theme/index.md +85 -0
- package/raw/research/dark-mode-theme/sources.md +49 -0
- package/raw/research/serena-mcp-disconnect/index.md +81 -0
- package/raw/research/serena-mcp-disconnect/sources.md +87 -0
- package/raw/research/wiki-tooling-improvements/index.md +126 -0
- package/raw/research/wiki-tooling-improvements/sources.md +73 -0
- package/raw/software-factory-case-study.pdf +0 -0
|
@@ -0,0 +1,250 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: research
|
|
3
|
+
description: Deep research on a topic using codebase analysis, library docs, and web search — writes the report plus its primary sources to raw/research/<slug>/
|
|
4
|
+
category: researching
|
|
5
|
+
model: claude-sonnet-4-6
|
|
6
|
+
effort: high
|
|
7
|
+
argument-hint: <topic or question to research>
|
|
8
|
+
disable-model-invocation: false
|
|
9
|
+
user-invocable: true
|
|
10
|
+
---
|
|
11
|
+
**Prereqs:** obey `.docs/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
|
+
|
|
13
|
+
# Research
|
|
14
|
+
|
|
15
|
+
Perform comprehensive research on a topic by combining codebase analysis, library documentation, and web research. Produce actionable findings with implementation suggestions, and **persist the report together with its primary sources** as ground-truth files under `raw/research/<slug>/` so they can later be `/wiki-ingest`ed into the knowledge base.
|
|
16
|
+
|
|
17
|
+
---
|
|
18
|
+
|
|
19
|
+
**Research Topic**: $ARGUMENTS
|
|
20
|
+
|
|
21
|
+
---
|
|
22
|
+
|
|
23
|
+
## Phase 1: Understand the Research Question
|
|
24
|
+
|
|
25
|
+
1. **Parse the topic**: Extract the core question, scope, and any constraints from `$ARGUMENTS`
|
|
26
|
+
2. **Identify research dimensions**:
|
|
27
|
+
- What needs to be understood about the **current codebase**? (existing patterns, dependencies, relevant code)
|
|
28
|
+
- What **external knowledge** is needed? (libraries, best practices, architectural patterns)
|
|
29
|
+
- Are there **multiple possible approaches** to compare?
|
|
30
|
+
3. **Formulate specific research questions** — break the topic into 3-5 concrete questions to answer
|
|
31
|
+
4. **Derive a slug & output directory** — lowercase the topic, spaces → hyphens, strip special characters, and trim to a short stable identifier (e.g. "Choosing a job queue for the API" → `job-queue`). The output directory is `raw/research/<slug>/`. **A prior run's files are immutable ground truth — never overwrite or edit them.** Writing new files into `raw/` is allowed; if a target file (`index.md` / `sources.md`) already exists, write the next free numeric sibling instead — `index-2.md`, then `index-3.md`, and so on. **The new `-N` file must not repeat data already present in the prior file(s)** — read the existing report first and capture only what is new, changed, or contradicts it, cross-referencing the prior file for everything unchanged (e.g. `> Builds on [index.md](index.md); this update covers …`). Treat existing research as read-only context you may cite, not as a file to update in place.
|
|
32
|
+
|
|
33
|
+
> **Collect primary sources as you go.** Throughout Phases 2–3, keep a running register of every primary source you actually rely on — its type (codebase / Context7 / web), its locator (file path + symbol, library id, or URL), the date accessed, and the specific excerpt(s) or facts it contributed. You will write this register out in Phase 5. A "primary source" is the document you drew the claim from, not your paraphrase of it.
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Phase 2: Internal Research (Codebase Analysis)
|
|
38
|
+
|
|
39
|
+
Use MCP Serena to understand the current state of the codebase as it relates to the topic.
|
|
40
|
+
|
|
41
|
+
### 2a. Project Context
|
|
42
|
+
|
|
43
|
+
- Read Serena memories (`mcp__serena__list_memories` → `mcp__serena__read_memory`) for relevant project context
|
|
44
|
+
- Check `PROJECT_STATUS.md` and `CLAUDE.md` for constraints, conventions, and architectural decisions
|
|
45
|
+
- Review `wiki/work/tasks/` for any related active or completed tasks
|
|
46
|
+
|
|
47
|
+
### 2b. Code Exploration
|
|
48
|
+
|
|
49
|
+
- **Structure**: Use `mcp__serena__get_symbols_overview` on relevant files/directories to understand architecture
|
|
50
|
+
- **Dependencies**: Use `mcp__serena__search_for_pattern` to find imports, package usage, and existing integrations related to the topic
|
|
51
|
+
- **Patterns**: Use `mcp__serena__find_symbol` to locate relevant functions, classes, and components
|
|
52
|
+
- **Configuration**: Check `package.json`, config files, and environment setup for relevant dependencies and settings
|
|
53
|
+
|
|
54
|
+
### 2c. Identify Constraints
|
|
55
|
+
|
|
56
|
+
Document what already exists that any solution must work with:
|
|
57
|
+
- Existing dependencies and their versions
|
|
58
|
+
- Established patterns and conventions
|
|
59
|
+
- Integration points and data flow
|
|
60
|
+
- Testing approach and quality gates
|
|
61
|
+
|
|
62
|
+
---
|
|
63
|
+
|
|
64
|
+
## Phase 3: External Research (Library Docs & Web)
|
|
65
|
+
|
|
66
|
+
### 3a. Library Documentation (Context7 MCP)
|
|
67
|
+
|
|
68
|
+
For each relevant library or framework identified:
|
|
69
|
+
|
|
70
|
+
1. **Resolve the library**: `mcp__context7__resolve-library-id(libraryName="<library>")`
|
|
71
|
+
2. **Query specific topics**: `mcp__context7__query-docs(libraryId="<id>", query="<specific question>")`
|
|
72
|
+
3. **Repeat** with refined queries if initial results are insufficient
|
|
73
|
+
|
|
74
|
+
Use Context7 for:
|
|
75
|
+
- API syntax and usage patterns
|
|
76
|
+
- Configuration options
|
|
77
|
+
- Migration guides and version-specific features
|
|
78
|
+
- Known limitations and edge cases
|
|
79
|
+
|
|
80
|
+
### 3b. Web Research (Brave Search MCP)
|
|
81
|
+
|
|
82
|
+
**NOTE**: Brave Search supports up to 50 requests per second — parallel searches are allowed.
|
|
83
|
+
|
|
84
|
+
Use Brave Search for:
|
|
85
|
+
- Best practices and recommended approaches (e.g., `"<topic> best practices 2025"`)
|
|
86
|
+
- Common pitfalls and failure modes (e.g., `"<topic> common mistakes"`)
|
|
87
|
+
- Comparison of alternative solutions (e.g., `"<library A> vs <library B>"`)
|
|
88
|
+
- Community recommendations and real-world experience (e.g., `"<topic> production experience"`)
|
|
89
|
+
- Performance benchmarks and scalability considerations
|
|
90
|
+
|
|
91
|
+
### 3c. Package Discovery
|
|
92
|
+
|
|
93
|
+
When the research involves choosing packages or tools:
|
|
94
|
+
|
|
95
|
+
1. **Search for candidates**: Use Brave Search to find popular options (e.g., `"best <category> library for <framework> 2025"`)
|
|
96
|
+
2. **Evaluate each candidate** against these criteria:
|
|
97
|
+
- Maintenance status (last release, open issues, bus factor)
|
|
98
|
+
- Community adoption (npm downloads, GitHub stars, Stack Overflow presence)
|
|
99
|
+
- Bundle size and performance impact
|
|
100
|
+
- TypeScript support and type quality
|
|
101
|
+
- Compatibility with existing stack
|
|
102
|
+
3. **Check documentation**: Use Context7 to verify API quality and completeness for top candidates
|
|
103
|
+
|
|
104
|
+
---
|
|
105
|
+
|
|
106
|
+
## Phase 4: Synthesis & Recommendations
|
|
107
|
+
|
|
108
|
+
### 4a. Summarize Findings
|
|
109
|
+
|
|
110
|
+
Present a clear, structured summary:
|
|
111
|
+
|
|
112
|
+
1. **Current State**: What exists in the codebase today relevant to this topic
|
|
113
|
+
2. **Key Findings**: Most important discoveries from research (with sources)
|
|
114
|
+
3. **Constraints**: What any solution must account for
|
|
115
|
+
|
|
116
|
+
### 4b. Solution Comparison (if multiple approaches exist)
|
|
117
|
+
|
|
118
|
+
For each viable approach, present:
|
|
119
|
+
|
|
120
|
+
| Criteria | Option A | Option B | Option C |
|
|
121
|
+
|----------|----------|----------|----------|
|
|
122
|
+
| **Approach** | Brief description | Brief description | Brief description |
|
|
123
|
+
| **Pros** | Key advantages | Key advantages | Key advantages |
|
|
124
|
+
| **Cons** | Key drawbacks | Key drawbacks | Key drawbacks |
|
|
125
|
+
| **Complexity** | Low/Medium/High | Low/Medium/High | Low/Medium/High |
|
|
126
|
+
| **Dependencies** | New deps needed | New deps needed | New deps needed |
|
|
127
|
+
| **Codebase fit** | How well it fits | How well it fits | How well it fits |
|
|
128
|
+
| **Maintenance** | Ongoing cost | Ongoing cost | Ongoing cost |
|
|
129
|
+
|
|
130
|
+
### 4c. Recommendation
|
|
131
|
+
|
|
132
|
+
- **Recommended approach**: State which option you recommend and why
|
|
133
|
+
- **Implementation outline**: High-level steps to implement the recommended approach
|
|
134
|
+
- **Risks and mitigations**: What could go wrong and how to handle it
|
|
135
|
+
- **Alternative if constraints change**: Note when a different option would become preferable
|
|
136
|
+
|
|
137
|
+
### 4d. Next Steps
|
|
138
|
+
|
|
139
|
+
Suggest concrete next steps:
|
|
140
|
+
- If the user wants to proceed: `To create a task: /task-add <description based on findings>`
|
|
141
|
+
- If more research is needed: Identify specific areas that need deeper investigation
|
|
142
|
+
- If a decision is needed: Frame the decision clearly with the trade-offs
|
|
143
|
+
|
|
144
|
+
---
|
|
145
|
+
|
|
146
|
+
## Phase 5: Write Output Files
|
|
147
|
+
|
|
148
|
+
The synthesis from Phase 4 is the **report**; the register from the Phase 1 callout is the **primary sources**. Persist both under `raw/research/<slug>/` using the **Write tool** (do not rely only on the chat transcript). Create the directory if it does not exist. Write two files — and honor the Phase 1 no-overwrite rule: if `index.md` or `sources.md` already exists, write `index-2.md` / `sources-2.md` (then `-3`, …) carrying only non-redundant new/changed content with a cross-reference back to the prior file.
|
|
149
|
+
|
|
150
|
+
### `index.md` — the research report
|
|
151
|
+
|
|
152
|
+
```
|
|
153
|
+
---
|
|
154
|
+
topic: <the research question, verbatim>
|
|
155
|
+
slug: <slug>
|
|
156
|
+
researched: <YYYY-MM-DD>
|
|
157
|
+
sources: [./sources.md]
|
|
158
|
+
---
|
|
159
|
+
|
|
160
|
+
# Research: <Topic>
|
|
161
|
+
|
|
162
|
+
> One-paragraph executive summary — the answer and the recommendation in brief.
|
|
163
|
+
|
|
164
|
+
## Research Questions
|
|
165
|
+
- <the 3–5 concrete questions from Phase 1>
|
|
166
|
+
|
|
167
|
+
## Current State (Codebase)
|
|
168
|
+
<what exists today relevant to the topic — cite file paths + symbols>
|
|
169
|
+
|
|
170
|
+
## Key Findings
|
|
171
|
+
<most important discoveries, each with an inline citation to a source id in sources.md, e.g. [S3]>
|
|
172
|
+
|
|
173
|
+
## Constraints
|
|
174
|
+
<what any solution must account for>
|
|
175
|
+
|
|
176
|
+
## Solution Comparison
|
|
177
|
+
<the Phase 4b table, if multiple approaches exist — omit if not applicable>
|
|
178
|
+
|
|
179
|
+
## Recommendation
|
|
180
|
+
<recommended approach and why; implementation outline; risks & mitigations>
|
|
181
|
+
|
|
182
|
+
## Next Steps
|
|
183
|
+
<the Phase 4d suggestions>
|
|
184
|
+
```
|
|
185
|
+
|
|
186
|
+
### `sources.md` — the primary-source register
|
|
187
|
+
|
|
188
|
+
Every source you actually relied on, one row per source, with a stable id (`S1`, `S2`, …) that the report cites. Keep the excerpt to the specific fact you used — enough to verify the claim without re-fetching.
|
|
189
|
+
|
|
190
|
+
```
|
|
191
|
+
---
|
|
192
|
+
topic: <the research question, verbatim>
|
|
193
|
+
slug: <slug>
|
|
194
|
+
researched: <YYYY-MM-DD>
|
|
195
|
+
---
|
|
196
|
+
|
|
197
|
+
# Primary Sources — <Topic>
|
|
198
|
+
|
|
199
|
+
| ID | Type | Locator | Accessed | What it contributed |
|
|
200
|
+
|----|------|---------|----------|---------------------|
|
|
201
|
+
| S1 | codebase | `path/to/file.ts::SymbolName` | <YYYY-MM-DD> | <fact drawn from it> |
|
|
202
|
+
| S2 | context7 | `<library-id>` — "<query>" | <YYYY-MM-DD> | <fact / API detail> |
|
|
203
|
+
| S3 | web | <full URL> | <YYYY-MM-DD> | <fact, with a short quoted excerpt> |
|
|
204
|
+
|
|
205
|
+
## Excerpts
|
|
206
|
+
|
|
207
|
+
### S3 — <source title>
|
|
208
|
+
<URL>
|
|
209
|
+
> <verbatim quoted excerpt that supports the cited claim>
|
|
210
|
+
```
|
|
211
|
+
|
|
212
|
+
Rules for this phase:
|
|
213
|
+
- **One source per row** — never collapse multiple URLs into one row.
|
|
214
|
+
- **Only sources you actually used** — do not pad the register with searches that produced nothing.
|
|
215
|
+
- **Quote, don't paraphrase, in the Excerpts section** — the excerpt is the ground-truth evidence.
|
|
216
|
+
- **Never fabricate a source or excerpt.** If a claim has no real source, mark it *(inference — no primary source)* in the report instead of inventing one.
|
|
217
|
+
|
|
218
|
+
---
|
|
219
|
+
|
|
220
|
+
## Phase 6: Confirm & Suggest Next Steps
|
|
221
|
+
|
|
222
|
+
After writing the files, tell the user:
|
|
223
|
+
- The paths written (`raw/research/<slug>/index.md` and `raw/research/<slug>/sources.md`)
|
|
224
|
+
- A 2–4 bullet summary of the recommendation
|
|
225
|
+
- That the report is now a `raw/` ground-truth source: **"Run `/wiki-ingest raw/research/<slug>/index.md` to synthesize this research into the knowledge base."**
|
|
226
|
+
- Any follow-on `/task-add` or `/decision-create` suggested by the findings
|
|
227
|
+
|
|
228
|
+
---
|
|
229
|
+
|
|
230
|
+
## Research Quality Standards
|
|
231
|
+
|
|
232
|
+
- **Cite sources**: Note whether information came from codebase analysis, Context7 docs, or web search
|
|
233
|
+
- **Distinguish fact from opinion**: Clearly separate what the code shows from what best practices suggest
|
|
234
|
+
- **Stay current**: Prefer recent sources (2024-2025) over older ones
|
|
235
|
+
- **Be specific**: Include version numbers, specific API calls, and concrete examples
|
|
236
|
+
- **Acknowledge gaps**: If something couldn't be determined, say so rather than guessing
|
|
237
|
+
|
|
238
|
+
---
|
|
239
|
+
|
|
240
|
+
## CRITICAL Rules
|
|
241
|
+
|
|
242
|
+
1) **Brave Search rate limit**: 50 requests/second — parallel searches are allowed
|
|
243
|
+
2) **Use Context7 for library docs**: Do NOT use Brave Search for library API documentation
|
|
244
|
+
3) **Use Serena for code**: Do NOT use Read, Grep, or Glob on code files
|
|
245
|
+
4) **Maximum 3 sub-processes at a time** if delegating research steps
|
|
246
|
+
5) **ALWAYS terminate processes when done**
|
|
247
|
+
6) **Always write the output files** to `raw/research/<slug>/` (`index.md` + `sources.md`) with the **Write tool** — the report is not done until it is persisted as a ground-truth source
|
|
248
|
+
7) **Never overwrite `raw/` files**: if a target already exists, write `<name>-2.md` / `-3.md` instead, carrying only non-redundant new/changed data with a cross-reference to the prior file
|
|
249
|
+
8) **No fabricated sources**: every row in `sources.md` is a source you actually consulted; mark unsupported claims as inferences rather than inventing citations
|
|
250
|
+
9) **`raw/research/` is the only `raw/` path this skill may write to** — never modify or delete anything elsewhere under `raw/`
|
|
@@ -0,0 +1,345 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: research-company
|
|
3
|
+
description: Comprehensive company research — mission, operations, leadership, products/services deep-dive, and ~5 years of recent news
|
|
4
|
+
category: researching
|
|
5
|
+
model: claude-sonnet-4-6
|
|
6
|
+
effort: high
|
|
7
|
+
argument-hint: <company name> [URL]
|
|
8
|
+
disable-model-invocation: false
|
|
9
|
+
user-invocable: true
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
# Research Company
|
|
13
|
+
|
|
14
|
+
Perform comprehensive research on a company using web search and news sources. Write findings as structured markdown files under `raw/companies/<slug>/`.
|
|
15
|
+
|
|
16
|
+
---
|
|
17
|
+
|
|
18
|
+
**Company**: $ARGUMENTS
|
|
19
|
+
|
|
20
|
+
---
|
|
21
|
+
|
|
22
|
+
## Phase 1: Parse Input
|
|
23
|
+
|
|
24
|
+
Extract from `$ARGUMENTS`:
|
|
25
|
+
- **Company name** — canonical name to use in searches
|
|
26
|
+
- **URL** (if provided) — use as a primary source for official information
|
|
27
|
+
- **Research focus** (if any) — e.g. "focus on engineering culture" or "hiring context"
|
|
28
|
+
|
|
29
|
+
Derive a **slug** from the company name: lowercase, spaces → hyphens, no special characters (e.g. "Acme Corp" → `acme-corp`).
|
|
30
|
+
|
|
31
|
+
The output directory is: `raw/companies/<slug>/`
|
|
32
|
+
|
|
33
|
+
If a URL was provided, fetch it first via WebFetch to extract mission, products, and leadership directly from the source.
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Phase 2: Core Company Profile
|
|
38
|
+
|
|
39
|
+
**NOTE**: Brave Search supports up to **50 requests per second** — parallel searches are allowed.
|
|
40
|
+
|
|
41
|
+
Search sequentially for each of the following. Use the company name (and domain if known) in queries.
|
|
42
|
+
|
|
43
|
+
### 2a. Mission & Overview
|
|
44
|
+
- Query: `"<company name>" mission vision what does <company> do`
|
|
45
|
+
- Extract: founding year, HQ, employee count, mission statement, core value proposition
|
|
46
|
+
|
|
47
|
+
### 2b. Products & Services
|
|
48
|
+
- Query: `"<company name>" products services offerings 2024 2026`
|
|
49
|
+
- Extract: product lines, key features, target customers/market, pricing model if public
|
|
50
|
+
|
|
51
|
+
### 2c. Business Model & Market Position
|
|
52
|
+
- Query: `"<company name>" business model revenue customers market`
|
|
53
|
+
- Extract: revenue model (SaaS/marketplace/services/etc.), key customers, market segment, competitive moat
|
|
54
|
+
|
|
55
|
+
### 2d. Leadership & Key People
|
|
56
|
+
- Query: `"<company name>" CEO leadership team executives founders`
|
|
57
|
+
- Extract: CEO, CTO, founders, notable board members, leadership changes in last 2 years
|
|
58
|
+
|
|
59
|
+
### 2e. Company Size & Growth
|
|
60
|
+
- Query: `"<company name>" employees headcount growth funding valuation`
|
|
61
|
+
- Extract: headcount, funding rounds (amounts, investors, dates), valuation if known, growth trajectory
|
|
62
|
+
|
|
63
|
+
---
|
|
64
|
+
|
|
65
|
+
## Phase 2f: Products & Services Deep Dive
|
|
66
|
+
|
|
67
|
+
Dig into the product/service portfolio in detail. Up to 50 req/sec, parallel OK.
|
|
68
|
+
|
|
69
|
+
### 2f-i. Product Catalogue
|
|
70
|
+
- Query: `"<company name>" products features pricing tiers plans`
|
|
71
|
+
- Extract: full list of named products/plans, what each does, who it targets, and public pricing tiers or price signals (e.g. "starts at $X/month", "custom enterprise pricing")
|
|
72
|
+
|
|
73
|
+
### 2f-ii. Platform & Integration Ecosystem
|
|
74
|
+
- Query: `"<company name>" integrations API platform partners ecosystem`
|
|
75
|
+
- Extract: key integrations (native and marketplace), API availability, developer platform features, SDK or webhook support
|
|
76
|
+
|
|
77
|
+
### 2f-iii. Customer Use Cases & Case Studies
|
|
78
|
+
- Query: `"<company name>" case study customer success how customers use`
|
|
79
|
+
- Extract: 3–5 named customer examples or verticals, the problem solved, measurable outcomes if stated
|
|
80
|
+
|
|
81
|
+
### 2f-iv. Recent Product Changes & Roadmap Signals
|
|
82
|
+
- Query: `"<company name>" product launch update new feature changelog 2024 2026`
|
|
83
|
+
- Query: `"<company name>" roadmap upcoming release beta 2026`
|
|
84
|
+
- Extract: notable launches in the last 18 months, deprecations, and any publicly telegraphed roadmap direction
|
|
85
|
+
|
|
86
|
+
### 2f-v. Free Tier, Trial & GTM Motion
|
|
87
|
+
- Query: `"<company name>" free trial freemium self-serve enterprise sales`
|
|
88
|
+
- Extract: whether there is a free/trial tier, self-serve vs. sales-led GTM, typical deal size signals if public
|
|
89
|
+
|
|
90
|
+
---
|
|
91
|
+
|
|
92
|
+
## Phase 3: Recent News (last ~5 years, 2021–2026)
|
|
93
|
+
|
|
94
|
+
Search year-band by year-band to avoid recency bias. Up to 50 req/sec, parallel OK.
|
|
95
|
+
|
|
96
|
+
### 3a. Major Announcements & Milestones
|
|
97
|
+
- Query: `"<company name>" announcement milestone launch 2023 2024 2026`
|
|
98
|
+
- Query: `"<company name>" news 2021 2022`
|
|
99
|
+
|
|
100
|
+
### 3b. Funding, M&A, Partnerships
|
|
101
|
+
- Query: `"<company name>" funding acquisition merger partnership`
|
|
102
|
+
- Extract: rounds, acqui-hires, strategic partnerships, IPO status
|
|
103
|
+
|
|
104
|
+
### 3c. Product / Strategy Shifts
|
|
105
|
+
- Query: `"<company name>" pivot strategy product change rebrand`
|
|
106
|
+
|
|
107
|
+
### 3d. Challenges & Controversies (if any)
|
|
108
|
+
- Query: `"<company name>" layoffs lawsuit controversy regulation problem`
|
|
109
|
+
- Report factually; skip this section entirely if nothing material surfaces
|
|
110
|
+
|
|
111
|
+
### 3e. Competitive Landscape
|
|
112
|
+
- Query: `"<company name>" competitors alternatives vs market`
|
|
113
|
+
- Extract: top 3–5 named competitors, how the company differentiates
|
|
114
|
+
|
|
115
|
+
---
|
|
116
|
+
|
|
117
|
+
## Phase 4: Engineering & Culture (optional — include if relevant)
|
|
118
|
+
|
|
119
|
+
Include this phase if the research context suggests hiring, partnering, or technical evaluation.
|
|
120
|
+
|
|
121
|
+
- Query: `"<company name>" engineering blog tech stack open source`
|
|
122
|
+
- Query: `"<company name>" culture values glassdoor employee review`
|
|
123
|
+
- Query: `"<company name>" engineering team size remote hybrid`
|
|
124
|
+
|
|
125
|
+
---
|
|
126
|
+
|
|
127
|
+
## Phase 5: Write Output Files
|
|
128
|
+
|
|
129
|
+
Create the directory `raw/companies/<slug>/` and write the following files. Omit any file whose section has no reliable data — never fabricate content.
|
|
130
|
+
|
|
131
|
+
**Never overwrite an existing `raw/` file.** Writing new files into `raw/` is allowed, but if a target file (e.g. `overview.md`) already exists from a prior run, write the next free numeric sibling instead — `overview-2.md`, then `overview-3.md`, and so on. The existing file is immutable ground truth; leave it untouched. **The new `-N` file must not repeat data already present in the prior file(s)** — read the existing file first and capture only what is new, changed, or newly contradicted, cross-referencing the prior file for everything unchanged (e.g. `> Unchanged since [overview.md](overview.md); this update covers …`). In `index.md`, list both the original and any `-N` files so the profile stays navigable.
|
|
132
|
+
|
|
133
|
+
### `index.md` — master summary & navigation
|
|
134
|
+
```
|
|
135
|
+
---
|
|
136
|
+
company: <Company Name>
|
|
137
|
+
slug: <slug>
|
|
138
|
+
researched: <YYYY-MM-DD>
|
|
139
|
+
url: <official URL if known>
|
|
140
|
+
---
|
|
141
|
+
|
|
142
|
+
# <Company Name>
|
|
143
|
+
|
|
144
|
+
> One-sentence description.
|
|
145
|
+
|
|
146
|
+
## Files in this profile
|
|
147
|
+
|
|
148
|
+
| File | Contents |
|
|
149
|
+
|------|----------|
|
|
150
|
+
| [overview.md](overview.md) | Mission, products, business model, size & funding |
|
|
151
|
+
| [products.md](products.md) | Product/service deep-dive — catalogue, pricing, integrations, use cases, roadmap |
|
|
152
|
+
| [leadership.md](leadership.md) | Executives, founders, board |
|
|
153
|
+
| [news.md](news.md) | Chronological news 2021–2026 |
|
|
154
|
+
| [competitive.md](competitive.md) | Competitors and differentiation |
|
|
155
|
+
| [culture.md](culture.md) | Engineering culture and tech stack *(if researched)* |
|
|
156
|
+
|
|
157
|
+
## Quick Summary
|
|
158
|
+
|
|
159
|
+
<3–5 bullet highlights>
|
|
160
|
+
```
|
|
161
|
+
|
|
162
|
+
### `overview.md` — mission, products, business model, size & funding
|
|
163
|
+
```
|
|
164
|
+
---
|
|
165
|
+
company: <Company Name>
|
|
166
|
+
section: overview
|
|
167
|
+
---
|
|
168
|
+
|
|
169
|
+
# <Company Name> — Overview
|
|
170
|
+
|
|
171
|
+
## Mission & Values
|
|
172
|
+
- Mission statement (quoted or paraphrased with source)
|
|
173
|
+
- Core values (if public)
|
|
174
|
+
|
|
175
|
+
## Products & Services
|
|
176
|
+
- **<Product>**: brief description
|
|
177
|
+
- ...
|
|
178
|
+
|
|
179
|
+
## Business Model
|
|
180
|
+
- Revenue model: ...
|
|
181
|
+
- Key customer segments: ...
|
|
182
|
+
- Competitive moat: ...
|
|
183
|
+
|
|
184
|
+
## Size & Funding
|
|
185
|
+
- Founded: YYYY HQ: <city>
|
|
186
|
+
- Employees: ~N *(source, date)*
|
|
187
|
+
- Total funding: $X Latest round: Series X ($Y, Month YYYY)
|
|
188
|
+
- Key investors: ...
|
|
189
|
+
- Valuation / ARR: ... *(if public)*
|
|
190
|
+
```
|
|
191
|
+
|
|
192
|
+
### `products.md` — product/service deep-dive
|
|
193
|
+
```
|
|
194
|
+
---
|
|
195
|
+
company: <Company Name>
|
|
196
|
+
section: products
|
|
197
|
+
---
|
|
198
|
+
|
|
199
|
+
# <Company Name> — Products & Services
|
|
200
|
+
|
|
201
|
+
## Product Catalogue
|
|
202
|
+
|
|
203
|
+
| Product / Plan | Description | Target Customer | Pricing |
|
|
204
|
+
|----------------|-------------|-----------------|---------|
|
|
205
|
+
| ... | ... | ... | ... |
|
|
206
|
+
|
|
207
|
+
## Platform & Integrations
|
|
208
|
+
- **Native integrations**: ...
|
|
209
|
+
- **API / SDK**: ...
|
|
210
|
+
- **Marketplace / ecosystem**: ...
|
|
211
|
+
|
|
212
|
+
## Customer Use Cases
|
|
213
|
+
|
|
214
|
+
| Customer / Vertical | Problem Solved | Outcome |
|
|
215
|
+
|---------------------|----------------|---------|
|
|
216
|
+
| ... | ... | ... |
|
|
217
|
+
|
|
218
|
+
## Recent Product Launches & Changes *(last 18 months)*
|
|
219
|
+
- **<Mon YYYY>**: <feature/launch> — [source](<url>)
|
|
220
|
+
- ...
|
|
221
|
+
|
|
222
|
+
## Roadmap Signals
|
|
223
|
+
- ... *(publicly announced or inferred from blog/conference)*
|
|
224
|
+
|
|
225
|
+
## GTM Motion
|
|
226
|
+
- Free tier / trial: ...
|
|
227
|
+
- Self-serve vs. sales-led: ...
|
|
228
|
+
- Typical deal size signals: ...
|
|
229
|
+
```
|
|
230
|
+
|
|
231
|
+
### `leadership.md` — executives, founders, board
|
|
232
|
+
```
|
|
233
|
+
---
|
|
234
|
+
company: <Company Name>
|
|
235
|
+
section: leadership
|
|
236
|
+
---
|
|
237
|
+
|
|
238
|
+
# <Company Name> — Leadership
|
|
239
|
+
|
|
240
|
+
| Name | Role | Notes |
|
|
241
|
+
|------|------|-------|
|
|
242
|
+
| ... | CEO | ... |
|
|
243
|
+
|
|
244
|
+
## Recent Changes
|
|
245
|
+
- <Date>: <name> joined/departed as <role>
|
|
246
|
+
```
|
|
247
|
+
|
|
248
|
+
### `news.md` — chronological news 2021–2026
|
|
249
|
+
```
|
|
250
|
+
---
|
|
251
|
+
company: <Company Name>
|
|
252
|
+
section: news
|
|
253
|
+
period: 2021–2026
|
|
254
|
+
---
|
|
255
|
+
|
|
256
|
+
# <Company Name> — News & Developments (2021–2026)
|
|
257
|
+
|
|
258
|
+
## 2026
|
|
259
|
+
- **<Mon YYYY>**: <event> — [source](<url>)
|
|
260
|
+
|
|
261
|
+
## 2024
|
|
262
|
+
- ...
|
|
263
|
+
|
|
264
|
+
## 2023
|
|
265
|
+
- ...
|
|
266
|
+
|
|
267
|
+
## 2022
|
|
268
|
+
- ...
|
|
269
|
+
|
|
270
|
+
## 2021
|
|
271
|
+
- ...
|
|
272
|
+
|
|
273
|
+
## 2021
|
|
274
|
+
- ...
|
|
275
|
+
```
|
|
276
|
+
|
|
277
|
+
### `competitive.md` — competitive landscape
|
|
278
|
+
```
|
|
279
|
+
---
|
|
280
|
+
company: <Company Name>
|
|
281
|
+
section: competitive
|
|
282
|
+
---
|
|
283
|
+
|
|
284
|
+
# <Company Name> — Competitive Landscape
|
|
285
|
+
|
|
286
|
+
## Main Competitors
|
|
287
|
+
|
|
288
|
+
| Company | How they compare |
|
|
289
|
+
|---------|-----------------|
|
|
290
|
+
| ... | ... |
|
|
291
|
+
|
|
292
|
+
## Differentiators
|
|
293
|
+
- ...
|
|
294
|
+
|
|
295
|
+
## Market Position
|
|
296
|
+
- ...
|
|
297
|
+
```
|
|
298
|
+
|
|
299
|
+
### `culture.md` — engineering culture & tech stack *(write only if Phase 4 was researched)*
|
|
300
|
+
```
|
|
301
|
+
---
|
|
302
|
+
company: <Company Name>
|
|
303
|
+
section: culture
|
|
304
|
+
---
|
|
305
|
+
|
|
306
|
+
# <Company Name> — Engineering & Culture
|
|
307
|
+
|
|
308
|
+
## Tech Stack
|
|
309
|
+
- ...
|
|
310
|
+
|
|
311
|
+
## Engineering Culture
|
|
312
|
+
- ...
|
|
313
|
+
|
|
314
|
+
## Work Style
|
|
315
|
+
- Remote / hybrid / in-office: ...
|
|
316
|
+
- Notable perks or policies: ...
|
|
317
|
+
|
|
318
|
+
## Employee Sentiment *(Glassdoor / public reviews)*
|
|
319
|
+
- ...
|
|
320
|
+
```
|
|
321
|
+
|
|
322
|
+
---
|
|
323
|
+
|
|
324
|
+
## Phase 6: Confirm & Suggest Next Steps
|
|
325
|
+
|
|
326
|
+
After writing the files, tell the user:
|
|
327
|
+
- Which files were written (list paths under `raw/companies/<slug>/`)
|
|
328
|
+
- Any sections skipped due to insufficient data
|
|
329
|
+
- Suggested follow-on actions based on context:
|
|
330
|
+
- **Ingest into the wiki**: "Run `/wiki-ingest raw/companies/<slug>/index.md` to synthesize this profile into the knowledge base" — the profile is now a `raw/` ground-truth source
|
|
331
|
+
- **Hiring prep**: "Run `/research-company <name> focus on engineering culture` to deepen culture.md"
|
|
332
|
+
- **Partnership/sales**: flag key decision-makers and recent strategic priorities from `leadership.md` and `news.md`
|
|
333
|
+
- **Competitive analysis**: offer to run research on the top competitors surfaced in `competitive.md`
|
|
334
|
+
|
|
335
|
+
---
|
|
336
|
+
|
|
337
|
+
## CRITICAL Rules
|
|
338
|
+
|
|
339
|
+
1. **Brave Search rate limit**: 50 requests/second — parallel searches are allowed
|
|
340
|
+
2. **Cite every claim**: include source URL inline where possible
|
|
341
|
+
3. **Flag uncertainty**: if a figure (headcount, valuation) is estimated or unverified, mark it *(estimated)* or *(unverified)*
|
|
342
|
+
4. **No hallucination**: omit entire sections/files rather than inventing plausible-sounding details
|
|
343
|
+
5. **Recency over quantity**: prefer sources from the last 3 years; flag anything older than 2022 as potentially outdated
|
|
344
|
+
6. **Use Write tool** for all output files — do not print the file contents inline to the conversation
|
|
345
|
+
7. **Never overwrite `raw/` files**: if a target already exists, write `<name>-2.md` / `-3.md` instead, and include only non-redundant new/changed data with a cross-reference to the prior file
|