Install
$ agentstack add skill-npbuilds-skill-library-problem-reframing ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Problem Reframing — Director
Most problems arrive pre-framed, and the frame is usually invisible to the person who set it. This director realizes six-eyes' Phase 4 (Reframe): it rotates the formulation through alternative frames, inverts it to surface failure preconditions, rotates the centered stakeholder, and grounds the work in the cognitive science of framing effects. The output is 2–3 genuinely different formulations the orchestrator can choose among.
Reframing is where wicked and contested problems earn their keep — a better frame often dissolves the difficulty that decomposition alone could not.
Routing Table
| Child skill | Use when | Output | |---|---|---| | frame-rotator | You need 2–3 alternative formulations (IDEO "How Might We", Polya specialize/generalize) | Alternative problem statements | | inversion-tool | You want to surface preconditions for success by asking what would guarantee failure (Munger) | Inverted failure modes → negated success conditions | | stakeholder-rotator | You need to surface whose interests the current framing centers and whose it hides | A stakeholder map with the invisible parties named | | kahneman-framing | You need the conceptual basis for framing effects, attribute substitution, or the Einstellung effect | Reference: framing/substitution/fixedness |
Routing Logic
- Start with
frame-rotatorto generate alternatives; pullkahneman-framingto name the
cognitive trap the original frame fell into.
- Run
inversion-toolfor high-stakes or "we've been stuck on this" statements. - Run
stakeholder-rotatorwhenever the problem touches multiple parties — it calls
philosophy/ethics/values-excavator cross-domain to surface hidden interests.
- Hand the candidate frames back to
six-eyes; if the reframe itself is contested, the
orchestrator escalates to the philosophy dialectic skills.
Scope Boundaries
- In scope: generating and grounding alternative formulations.
- Out of scope: scoring the resulting statement (→
statement-audit), shaping it for an
audience (→ statement-compression).
- Escalate to
six-eyeswhen reframing reveals the problem is wicked enough to warrant a
full deep-lane pass.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: npbuilds
- Source: npbuilds/skill-library
- License: MIT
- Homepage: https://skill-library-prod.web.app/
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.