steelmorgan/quick-fix
framework_eng/skills/framework-meta/quick-fix/SKILL.md
MUST use WHEN the task is classified as simple (< 20 lines, 1 file, no new metadata objects, no architectural decisions). Provides a short cycle of 3 steps with a guard on the self path and mandatory verify.
$ install --global
skillsauthnpx skillsauth add steelmorgan/1c-agent-based-dev-framework quick-fixInstall 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: Jun 13, 2026, 5:52 AM101.9s1 file scanned
SKILL.md
- name:
- quick-fix
- description:
- MUST use WHEN the task is classified as simple (< 20 lines, 1 file, no new metadata objects, no architectural decisions). Provides a short cycle of 3 steps with a guard on the self path and mandatory verify.
- alwaysApply:
- false
Skill: Quick Fix (short-cycle)
Three steps without cross-review. One file, < 20 lines, no architectural decisions, no new features, no new metadata objects.
When it applies
The Lead (main flow) has classified the task as simple (see orchestrator profile, Layer 1) and chosen the short cycle. In the short cycle, the Lead may execute it personally or delegate one subagent under the guard below.
Self-path guard (MUST, otherwise slippery slope)
self execution is the only mode where the main flow has no cross-review. Therefore the boundaries are strict and are checked BEFORE any modification starts.
- self is allowed ONLY within the bounds:
< 20 lines, 1 file, no new metadata objects, no architectural decisions; - exceeding any criterion → mandatory transition to full cycle (delegation), self is forbidden;
- the verify step (step 3) is mandatory EVEN for self — the only compensation for the absence of cross-review.
Steps
1. Find (Explorer → Economy)
navigate_symbol + get_call_graph → path to the module, dependencies, confirm that the change is localized
(confirmation of the guard boundaries: one file, no architectural links).
2. Fix (Developer → Mid)
The minimum necessary change according to coding-standards. No "improvements" beyond the task scope.
3. Verify (Developer → Mid) — REQUIRED, including for self
get_diagnostics— quick check of the changed filerun_tests— if there are tests for the modulecheck_syntax— final check before commit
Escalation to full cycle
| Situation | Action | |----------|----------| | Tests fail after the change | Fix or escalate to full | | Multiple modules / architecture / review / > 20 lines / new metadata object | full cycle |
Escalation protocol: record the state → the orchestrator itself raises the phase prompt.
The orchestration discipline and the phase form are already durable in its profile (framework/subagents/orchestrator.md,
Layer 2); it reads the detailed phase mechanics from framework/workflows/full-cycle.md upon entering the phase.
This is NOT "handing off to an external document" and NOT starting another session — the Lead simply puts on the hat
of the full-cycle orchestrator and proceeds with Phase 1 (or Phase 3, if the spec already exists).
depends_on:
- framework/subagents/orchestrator.md
- framework/workflows/full-cycle.md
- framework/subagents/explorer.md
- framework/subagents/developer-code.md
- framework/skills/bsl-practices/coding-standards/SKILL.md
- framework/skills/tool-usage/code-analysis/syntax-checking/SKILL.md
- framework/skills/tool-usage/v8-runner/SKILL.md
Related Skills
steelmorgan/source-of-truth
testing
VerifiedTrustedCommunity
MUST use BEFORE making a judgment about the cause of a conflict, a test failure, or an artifact dispute. Defines the end-to-end verification method L1→L6 and the classification of the first broken link.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/skill-learning
development
VerifiedTrustedCommunity
MUST use AFTER a work cycle with ≥2 iterations (wrote → error → fixed → success). Provides the retrospective procedure and the format for recording practice/anti-patterns in references/learned-patterns.md or {project}/.context/learned-patterns.md.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/rlm-workflow
tools
VerifiedTrustedCommunity
MUST use WHEN you are writing reusable knowledge into RLM (pattern / architectural decision / stable domain fact) OR reading it before a non-trivial task/solution in the domain. Provides the breakdown of native-push vs RLM-pull, tools for writing and reading RLM, H-MEM levels, and hygiene.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/git-workflow
development
VerifiedTrustedCommunity
MUST use WHEN the orchestrator creates a task branch, commits a phase, merges a task, or rolls back changes. Provides branch strategy, phase commit format, squash-merge, and a ban on file deletion.
69SKILL.mdUpdated Jun 13, 2026