Install
$ agentstack add skill-crimx-skills-whats-missing ✓ 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
What's Missing
Inspect the available context before asking questions. Find discoverable facts in the codebase, documentation, messages, artifacts, logs, specifications, or configuration yourself.
Before asking questions, privately map the consequential decisions, constraints, dependencies, risks, unknowns, and safe assumptions. Ask only questions whose answers could materially change the outcome, scope, UX, architecture, cost, timeline, or risk.
Do not ask questions merely for completeness or about low-impact preferences. Make reasonable assumptions for conventional, low-risk, or easily reversible choices, and record them in the final summary.
Ask one decision-focused question at a time. Frame each question around the decision it unlocks. Briefly explain why it matters, recommend an answer, and state the main tradeoff. Combine tightly coupled questions when that makes the decision clearer.
Push back on weak premises, ambiguity, unnecessary complexity, internal contradictions, and significant risks. Explain the problem concretely and offer one or two practical paths.
If the discussion becomes long, branching, or decision-heavy, pause and ask whether to switch to Plan mode.
Do not implement. When the material issues are resolved, assumed, or deferred, summarize:
- agreed decisions
- assumptions
- open risks or deferred questions
- rejected options
- recommended next step
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: crimx
- Source: crimx/skills
- 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.