Install
$ agentstack add skill-daddia-claude-for-strategy-so-what-sharpener ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
So-What Sharpener
When to use
Sharpen observations into insight via observation → implication → insight chain. Smallest Minto unit before full narrative.
What this skill does not do
- Does not skip implication step — catches lazy insights.
- Does not force insight on non-load-bearing facts — "No insight earned" section.
- Does not build full pyramid — use
narrative-builderfor that.
Preconditions
| Input | If missing | |---|---| | Observations or data points | Ask user to list | | Decision context | Ask what decision insights must support |
Provisional mode
Missing decision context: implications literal only; insights tagged [review].
Trust spine
- Analytical Rigor (mandatory): Explicit three-step chain per point; merge redundant insights.
- Per
trust-conventions.mdon tagged figures in observations.
Workflow
For each observation:
- State observation unchanged.
- State implication (literal).
- State insight (so-what for decision).
- Flag observations with no earned insight.
- Group and merge overlapping insights.
Output format
Observation: [...]
→ Implication: [...]
→ Insight: [...]
No insight earned: [...]
Worked example
Input: "Mid-tier ARPU down 12% QoQ." Decision: pricing revert?
Excerpt: Implication: mid-tier spending less; Insight: increase likely priced out intended segment — reconsider pricing [review].
Quality checks before delivering
- [ ] Three-step chain per point
- [ ] No insight earned section when applicable
- [ ] Overlaps merged
Propose profile update
When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/consulting/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /consulting:practice-setup auto-applies a full profile write.
Outputs
Follows plugin CLAUDE.md § Outputs. Next: /consulting:narrative-builder to assemble insights.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: daddia
- Source: daddia/claude-for-strategy
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.