dmitryprg-ai/fix-last-task
.cursor/skills/fix-last-task/SKILL.md
Analyze and fix issues in the last completed task — find missed problems, fix errors, perform session review. Use when user reports errors after task was marked as done, when completion report had high confidence but result has issues, or when AI missed obvious problems.
$ install --global
skillsauthnpx skillsauth add dmitryprg-ai/cursor-develop-autorules fix-last-taskInstall 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 17, 2026, 2:10 AM6.3s2 files scanned
SKILL.md
- name:
- fix-last-task
- description:
- Analyze and fix issues in the last completed task — find missed problems, fix errors, perform session review. Use when user reports errors after task was marked as done, when completion report had high confidence but result has issues, or when AI missed obvious problems.
Fix Last Task Protocol
Principle: ANALYZE FAILURE BEFORE FIXING.
When to Apply
- AI declared task complete, but user found errors
- Challenge protocol or Cross-check were not performed properly
- Completion report had high confidence but result is wrong
Workflow (7 Phases — ALL MANDATORY)
Phase 1: ANALYZE FAILURE
- Restore original request (exact quote)
- List what was done vs what was expected
- Re-run Challenge protocol from
core-master.mdc(Cross-check + 4 questions) - List all missed issues
Phase 2: ROOT CAUSE ANALYSIS
Apply 5 Whys from _base-5wh.mdc — dig at least 5 levels to find why the issues were missed.
Phase 3: PLAN
Create TODO list — one item per missed issue, starting with critical ones.
Phase 4: FIX
For each TODO:
- Mark in_progress
- Apply fix
- Cross-check: open file, read changes, verify
- Mark completed
- Report confidence change:
[before]% → [after]% — [reason]
Phase 5: VERIFY
Apply Cross-check (open every changed file) + Final Challenge (4 questions).
Phase 6: SESSION REVIEW
Apply session-review skill fully. Record improvement to .cursor/data/improvements-backlog.md.
Phase 7: COMPLETION REPORT
Full DONE block with: issues found, fixes applied, root cause, improvement recorded, final confidence.
FORBIDDEN
- Skipping any Phase
- Fixing without Cross-check
- Not recording improvement in backlog
- Declaring done without re-running Challenge
- Making excuses instead of analyzing
Templates
For detailed analysis and review templates, see templates.md.
Related Skills
dmitryprg-ai/techdebt-scan
development
VerifiedTrustedCommunity
Scan codebase for technical debt and fix safely with TDD. Use to find oversized files, duplicated code, code smells, and refactor safely. Workflow - SCAN, TEST CASES, REFACTOR, VERIFY. Keywords - techdebt, tech debt, duplicates, code quality audit.
8SKILL.mdUpdated Apr 17, 2026
dmitryprg-ai/tdd-workflow
development
VerifiedTrustedCommunity
Test-Driven Development workflow with strict Red-Green-Refactor cycle. Use when developing features with TDD, writing tests before code, or when test-driven approach is needed. MANDATORY order - test cases table BEFORE code, failing tests BEFORE implementation.
8SKILL.mdUpdated Apr 17, 2026
dmitryprg-ai/session-review
testing
VerifiedTrustedCommunity
Review work session quality and capture improvements. Use at end of session, after large tasks, after series of errors, or when user asks for session review, retrospective, lessons learned. Records improvements to backlog.
8SKILL.mdUpdated Apr 17, 2026
dmitryprg-ai/research
data-ai
VerifiedTrustedCommunity
Analyze data, investigate datasets, work with CSV/parquet/pandas/dataframes. Use when analyzing data, exploring datasets, running experiments, or when user mentions data, analysis, parquet, csv, pandas, dataframe, statistics, investigation.
8SKILL.mdUpdated Apr 17, 2026