bigeasyfreeman/fix-bug
skills/fix-bug/SKILL.md
Orchestration skill for bug fixes and production issue repair. Investigate -> light brief -> targeted verification -> council -> PR.
testing
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add bigeasyfreeman/adlc fix-bugInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 1:21 PM113.0s1 file scanned
SKILL.md
- name:
- fix-bug
- description:
- Orchestration skill for bug fixes and production issue repair. Investigate -> light brief -> targeted verification -> council -> PR.
Fix Bug (Orchestration)
Overview
Chains the fix loop for bug fixes and production issue repair. It is lighter than build-feature and uses a bug-specific verifier contract instead of universal test ceremony.
When to Use
- A bug report or production error needs fixing
- A regression is confirmed in the test suite
- A failure has been reproduced and needs root-cause repair
The Sequence
Step 1: Investigate (systematic debugging)
Step 2: Light Brief (single task with verification_spec)
Step 3: Apply only the gates that the task class warrants
Step 4: LDD gate
Step 5: Bugfix verification discipline
Step 6: Definition of Done
Step 7: Light Council (3 personas, 1 round)
Step 8: PR with evidence
Step 1: Investigate
Use systematic-debugging to:
- trace the failure to its origin
- check recent changes and git blame
- build a root-cause hypothesis
- identify the smallest fix scope
Step 2: Light Brief
Create a single-task brief that includes:
- the bug description
- the observed failure
- the task classification:
bugfix - the
verification_spec - the regression expectation
Do not decompose into feature-style subwork unless the bug truly reveals a larger feature gap.
Step 3: Apply Only Relevant Gates
Use the brief's applicability decision, not a universal checklist.
- Security review only if the fix changes attack surface, auth, or data handling
- Observability only if the fix changes runtime paths or user-visible behavior
- Compatibility only if the fix changes interfaces or data formats
Step 4: LDD
Use ldd-enforcement before verification. Lint must pass before the bugfix verifier runs.
Step 5: Bugfix Verification Discipline
Use the primary verifier from verification_spec.
Bugfix rules:
- start with the smallest deterministic reproducer
- confirm the reproducer fails for the right reason
- make the minimum code change that fixes the failure
- re-run the primary verifier until it passes
- add regression coverage if the fix changes behavior
- run any secondary verifiers from the spec
Do not force the bug through a generic RED/GREEN/REFACTOR script. The verifier itself is the contract.
Step 6: Definition of Done
Use the DoD subset that applies to the task class and activated overlays.
Step 7: Light Council
Use eval-council in light mode with three personas:
- Skeptic: root cause vs symptom
- Operator: safe to deploy, rollback plan
- Security Auditor: only when the fix touches security-relevant surfaces
Step 8: PR
Include:
- reproduction steps
- root cause analysis
- verifier evidence
- regression guard evidence
- council verdict
- severity classification
Escalation
If three fix attempts fail:
- Capture what was tried
- Record the verifiers used and why they were insufficient
- Summarize root-cause hypotheses tested
- Escalate with the smallest clear next step
Related Skills
bigeasyfreeman/build-feature
development
VerifiedTrustedCommunity
Orchestration skill: chains the full ADLC Build Loop. PRD → Brief → Council → Scaffold → Codegen → LDD → TDD → Council → PR. Use when implementing a new feature end-to-end.
1SKILL.mdUpdated Apr 22, 2026
bigeasyfreeman/skills/helm-argocd-deployment
development
VerifiedTrustedCommunity
# Skill: Helm & ArgoCD Deployment > Validates Helm charts and generates ArgoCD Application manifests when the ADLC pipeline produces infrastructure or service code. Ensures every deployable artifact has correct chart structure, environment-specific values, and a GitOps-ready Application manifest before code review. --- ## Why This Exists Without deployment validation in the pipeline, common failures slip through to production: - **Helm charts fail `helm template`** because of missing values,
SKILL.mdUpdated May 5, 2026
bigeasyfreeman/verifier-semantic-judge
testing
VerifiedTrustedCommunity
Decide whether an intersecting verifier actually exercises the semantic change.
SKILL.mdUpdated Apr 23, 2026
bigeasyfreeman/skills/ux-flow-builder
development
VerifiedTrustedCommunity
# Skill: UX Flow Builder > Generates user flow diagrams (Mermaid) from PRD personas and screen specifications. Surfaces dead ends, missing screens, and disconnected flows before design or engineering starts. Helps PMs think in screens, not features. --- ## Trigger - Automatically during PRD Phase 4 (Personas & Flows) to visualize the user journey - On-demand when the PM says "show me the flow" or "map the user journey" - During PRD evaluation to verify screen connectivity --- ## Input ```
SKILL.mdUpdated Apr 23, 2026