← Back to Skills Marketplace
Strategy Interview
by
Kevin Anderson
· GitHub ↗
· v1.0.3
· MIT-0
155
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install strategy-interview
Description
Use when the user wants to build or think through a strategy via guided conversation — for a company, product, team, career, or initiative. Triggers on "help...
Usage Guidance
This skill appears internally consistent and does what it says: guide a strategy interview and produce notes/drafts. Before installing or running it, consider: (1) run it in a dedicated or disposable project folder so the .beagle/strategy/ files don't mingle with other work; (2) review any generated files before sharing them externally; (3) if you allow autonomous agent invocation, be aware the agent may create or update local files automatically — restrict invocation or test interactively first if you prefer manual control; (4) no credentials or network calls are requested by the skill, so there is no hidden credential-exfiltration signal in the provided files. If you want higher assurance, run a controlled test conversation in an isolated directory and inspect .beagle/strategy/<subject-slug>/state.md and the produced notes/drafts.
Capability Tags
Capability Assessment
Purpose & Capability
Name, description, and included reference materials align with a guided strategy-interview assistant. The skill asks for no binaries, env vars, or external credentials — all consistent with a conversational interviewing tool that reads local reference files and writes notes/drafts.
Instruction Scope
SKILL.md confines runtime behavior to conversational interviewing, loading bundled reference files and writing interview artifacts (working notes and final drafts) into a .beagle/strategy/<subject-slug>/ folder and the user's working directory. It does not instruct network calls, secret access, or reading unrelated system files. The gating rules around when to generate final drafts are explicit and narrow the agent's discretion.
Install Mechanism
No install specification or external downloads; the skill is instruction-only and contains only markdown references. This is low-risk and proportionate for the task.
Credentials
The skill requests no environment variables, credentials, or config paths beyond writing its own .beagle workspace. There are no unrelated credential requests or surprising config access.
Persistence & Privilege
always:false (normal). The agent is allowed to invoke the skill autonomously (disable-model-invocation:false), and the SKILL.md instructs writing files into the user's workspace (.beagle/strategy/<subject-slug>/ and draft files in the current directory). This is coherent for the skill's purpose but means an autonomously-invoked run can create or update local files — users should be aware and control where the agent runs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install strategy-interview - After installation, invoke the skill by name or use
/strategy-interview - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Documentation updated in SKILL.md with no changes to logic or behavior
- Non-functional change: edits and clarifications to descriptive content only
- No impact on strategy interview phases, outputs, or workflow
v1.0.2
- Expanded description to clarify which scenarios trigger the skill and which are outside scope, including indirect requests like prioritization struggles.
- Updated language for more precise triggers and exclusions (e.g., clarified it does NOT review documents or run brainstorms).
- No changes to core framework, workflow, or lens handling.
- Documentation/description clarifications only; functionality unchanged.
v1.0.1
- Clarified and streamlined description wording, focusing on how and when to use the skill.
- Added clearer user triggers and guidance in the description (e.g., strategic planning, "help me figure out our direction").
- Explicitly notes this skill is not for standalone document reviews and refers users to "strategy-review" for that use case.
- No changes to the interview workflow or core strategy frameworks.
v1.0.0
strategy-interview 1.0.0
- Initial release introducing a guided strategy interview skill grounded in the kernel framework (diagnosis, guiding policy, coherent actions).
- Integrates complementary strategy lenses: Wardley mapping, Playing to Win choice cascade, and Blue Ocean value innovation, applied contextually during the interview.
- Detects and addresses common bad-strategy patterns: fluff, goals-as-strategy, laundry lists, and strategy by analogy.
- Enforces a clear four-phase interview workflow; restricts draft generation until core strategy elements are confirmed.
- Supports session resumption with persistent and working notes to accommodate multi-session interviews.
Metadata
Frequently Asked Questions
What is Strategy Interview?
Use when the user wants to build or think through a strategy via guided conversation — for a company, product, team, career, or initiative. Triggers on "help... It is an AI Agent Skill for Claude Code / OpenClaw, with 155 downloads so far.
How do I install Strategy Interview?
Run "/install strategy-interview" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Strategy Interview free?
Yes, Strategy Interview is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Strategy Interview support?
Strategy Interview is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Strategy Interview?
It is built and maintained by Kevin Anderson (@anderskev); the current version is v1.0.3.
More Skills