seismic-sense
From the author
Toph's seismic sense for read-only investigation. She cannot see, so she feels every vibration in the ground and reports exactly what is there. Use for how, /how, "how does X work", "where does Y live", "where should this live", "which package owns this", "is this the right layer", "are we sure", code walkthroughs before a change, and onboarding mental models of a subsystem. Produces a cited explanation or a recommendation, never a code change. Use past-lives for why a thing was built this way.
Install
npx skills add tmcfarlane/team-avatar --skill seismic-sense -a claude-code
Installs to .claude/skills/seismic-sense/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 83
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- lie-detectortmcfarlane/team-avatarToph's lie detector for multi-model adversarial review. She feels a heartbeat through the ground and knows when someone is lying, so a change that only claims to work does not fool her. Use for interrogate, /interrogate, adversarial review, multi-model review, "challenge this", "stress test this code", "find blind spots", "tear this apart", or a contested design before it ships. Several reviewers on different models challenge the change independently, and the lead sorts their findings into act on, consider, noted, and dismissed. Never applies changes.Testing★ 111
- past-livestmcfarlane/team-avatarAang consulting his past lives (Roku, Kyoshi) for why things were decided. Use for why, /why, "why does X work this way", "why did we pick Y", design rationale, the history behind a regression, postmortem context, or where a threshold number came from. Queries every evidence source in parallel (source control, issue tracker, long-form docs, team chat, infrastructure observability, error tracking, analytics warehouse) and returns a cited, confidence-tiered answer. Use seismic-sense for how code works at runtime.DevOps★ 111
- howmichael-denyer/pstack-claudeUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.Planning★ 3.6K
- systematic-debuggingnahid-sparktales/agent-dispatcherFind the cause of a failure by evidence — reproduce it, read what the system actually did, form hypotheses that predict something you have not looked at yet, bisect to the smallest failing case, fix where all callers route through, then re-run the original reproduction. Use when something is broken and the cause is not yet known, when a previous fix did not hold, or when an edit is about to be made because the code "looks wrong". Not for an outage still burning (mitigate first), not for a cause already established that only needs implementing, and not a licence to skip reading the stack trace.Engineering★ 59
- metalbendingtmcfarlane/team-avatarToph's metalbending for a strict code quality review. Everyone said metal could not be bent, until Toph felt the specks of earth still trapped inside it and bent the whole thing through them. Use to find the impurities in a rigid-looking structure, such as spaghetti conditionals, files sprawling past 1000 lines, wrappers that buy nothing, and logic in the wrong layer, and to push for the code judo move that makes the change dramatically simpler. Use for thermo-nuclear code quality review, /thermo-nuclear-code-quality-review, deep code quality audit, maintainability review, or "how could this be simpler".Planning★ 111
- situational-awarenesszero-lab-ai/skillsAssesses a freshly compromised host quietly before acting — who/where/what's here/what's watching/what's around — using local reads and living-off-the-land so the SOC never sees the recon. Use right after gaining a foothold, before privilege escalation or lateral movement, or when deciding whether an enumeration command is quiet enough to run.Other★ 283
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in