Superpowers Systematic Debugging
v1.0.0Enforce a four-phase debugging process—root cause investigation, pattern analysis, hypothesis testing, and evidence-based fix verification—for all bugs and f...
⭐ 0· 222·0 current·0 all-time
by@axelhu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill name/description and the SKILL.md all describe the same goal: enforcing a four-phase, evidence-driven debugging process. There are no unrelated environment variables, binaries, or config paths requested, so nothing requested is out-of-scope for a debugging-guidance skill.
Instruction Scope
The SKILL.md contains prescriptive runtime instructions for debugging (read stack traces, reproduce, check git diffs, track data flow, write failing tests, perform minimal tests). Those instructions stay within the debugging domain and do not instruct the agent to exfiltrate data or access unrelated secrets. Note: it references another skill ('superpowers-tdd') for writing failing tests — if you plan to use this skill, verify that referenced skill's behavior and permissions.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. Its guidance suggests examining repository state (git diffs, stack traces) which is appropriate for debugging and does not imply unnecessary credential access.
Persistence & Privilege
Flags: always=false (not forced), user-invocable=true, disable-model-invocation=false. Autonomous invocation is allowed by platform default but there are no other elevated persistence or cross-skill config modifications requested.
Assessment
This skill is coherent and low-risk: it only contains human-readable debugging rules and asks for no credentials or installs. Before enabling it, consider: (1) the skill is prescriptive — it will encourage the agent to refuse fixes until investigation is done, which might slow down quick patch workflows; (2) it references another skill (superpowers-tdd) — review that skill if you plan to use it; (3) autonomous invocation is permitted by default on the platform (disable-model-invocation can be set if you want to prevent the agent from calling skills without explicit user action). If those fit your workflow, the skill is reasonable to install.Like a lobster shell, security has layers — review code before you run it.
latestvk97703jbknjp3f9j5a3kn96tj583n1vr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.