failure-forensics
Skill1 starsChanged 9 months agoMITView on GitHub
Capture deterministic failure artifacts, reproducible commands, and fingerprints for Conflux tracks. Use when a track fails tests or gates and you need non-blocking forensics, dedupe-aware retries, or resolution memory updates.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- voyager67/AgentFieldkittheir own version, first seen Nov 8, 2026
- soysantana/skillstheir own version, first seen Nov 1, 2026
- cdeust/zetetic-team-subagentstheir own version, first seen Oct 25, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- cdeust/zetetic-team-subagents★ 8same name
- soysantana/skills★ 2same name
- voyager67/AgentFieldkit★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- chaos-fuzz-runnerSkill
- data-migration-safetySkill
- external-integration-reliabilitySkill
- harmonization-operatorSkill
- hud-control-opsSkill
- mcp-policy-opsSkill
- search-index-tuningSkill
- smoke-gate-runnerSkill
- sync-conflict-playbookSkill
- track-contract-authorSkill
- transaction-concurrency-guardSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill to create replayable failure evidence and update regression memory without changing runtime defaults.
- Distinctive: line 18
When fixed, record learning:
- Very specific: line 23
Write artifacts under .gemini_security/repros/....
- Distinctive: line 25
Keep this skill non-blocking: it records evidence and learning, but does not enforce policy.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Failure Forensics
Use this skill to create replayable failure evidence and update regression memory without changing runtime defaults.
Workflow
- Capture a failure bundle:
scripts/capture_failure.py --track-id <track> --stage <stage> --error-log-file <path> --repro-command "<cmd>"
- Review the output payload:
- fingerprint
- repro bundle path
- attempt counters from failure knowledge
- When fixed, record learning:
scripts/mark_resolution.py --track-id <track> --fingerprint <fp> --fix-commit <sha> --learning "<why it worked>"
Notes
- Write artifacts under
.gemini_security/repros/.... - Update
.gemini_security/failure_knowledge.json. - Keep this skill non-blocking: it records evidence and learning, but does not enforce policy.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.