pskoett/self-improvement-ci
skills/self-improvement-ci/SKILL.md
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.
$ install --global
skillsauthnpx skillsauth add pskoett/pskoett-ai-skills self-improvement-ciInstall 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 30, 2026, 10:44 AM6.2s1 file scanned
SKILL.md
- name:
- self-improvement-ci
- description:
- CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.
Self-Improvement CI
Install
gh skill install pskoett/pskoett-skills self-improvement-ci
Fallback using the Agent Skills CLI:
npx skills add pskoett/pskoett-skills/skills/self-improvement-ci
Purpose
Run self-improvement in CI without interactive chat loops:
- Inspect PR check results and CI failures
- Ingest learning candidates from
simplify-and-harden-ci - Deduplicate recurring patterns by stable
pattern_key - Emit promotion-ready suggestions for agent context/system prompts
Use self-improvement for interactive/local sessions.
Context Limitation (Important)
CI agents do not have peak task context from the original implementation session. Use this skill to aggregate recurring patterns across runs, not to infer nuanced one-off intent.
Implications:
- Favor stable
pattern_keyrecurrence signals over single-run conclusions - Require recurrence thresholds before promotion
- Route uncertain or high-impact recommendations to interactive review
Prerequisites
- GitHub Actions enabled for the repository
- GitHub CLI authenticated (
gh auth status) gh-awinstalled for authoring/validation:
gh extension install github/gh-aw
CI Contract
The CI skill must:
- Read only PR-scoped data (checks, workflow outcomes, existing learning entries)
- Avoid direct code modifications in CI
- Emit machine-readable learning output
- Recommend promotion only when recurrence thresholds are met
Output Schema
self_improvement_ci:
source:
pr_number: 123
commit_sha: "abc123"
candidates:
- pattern_key: "harden.input_validation"
source: "simplify-and-harden-ci"
recurrence_count: 3
first_seen: "2026-02-01"
last_seen: "2026-02-20"
severity: "high"
suggested_rule: "Validate and bound-check external inputs before use."
promotion_ready: true
summary:
candidates_total: 4
promotion_ready_total: 1
followup_required: true
Recurrence and Promotion Rules
- Track recurrence by
pattern_key - Default threshold for promotion:
recurrence_count >= 3- seen in
>= 2distinct tasks/runs - within a 30-day window
- Promotion targets:
CLAUDE.mdAGENTS.md.github/copilot-instructions.mdSOUL.md/TOOLS.mdwhen using openclaw workspace memory
Authoring Workflow (gh-aw)
Example-only templates live in references/workflow-example.md.
Keep examples outside .github/workflows until you explicitly decide to enable CI automation.
When ready:
- Copy the template into
.github/workflows/self-improvement-ci.md - Customize tool access, outputs, and policy thresholds
- Validate:
gh aw compile --validate --strict
- Trigger test run manually:
gh aw run self-improvement-ci --push
Integration with Other Skills
- Pair with
simplify-and-harden-cito ingestsimplify_and_harden.learning_loop.candidates - Feed promoted patterns back into
self-improvementmemory workflow for durable prevention rules
Related Skills
pskoett/self-healing
tools
VerifiedTrustedCommunity
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a `HEAL-` entry to `.learnings/HEALS.md` with proof. Use whenever a command, test, build, or lint fails or exits non-zero; on missing tooling, dependency/lockfile mismatch, wrong runtime version, venv or permission errors, port conflicts, dirty git state, or a missing `.env`; when the agent needs a helper or one-off script that doesn't exist yet; when an external API, tool, or MCP errors or rate-limits; or when a test flakes. Search `HEALS.md` by `Pattern-Key` first — most heals are recurrences, so increment `Recurrence-Count` instead of duplicating. Verify is mandatory: mark `pending-verify` honestly if sandboxed, `abandoned` if the fix can't be made to work. Pairs with `self-improvement` (which promotes recurring heals to durable memory) but owns the verify-before-persist discipline self-improvement doesn't.
199SKILL.mdUpdated Jun 2, 2026
pskoett/control-session-orchestrator
development
VerifiedTrustedCommunity
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app control session. Use this skill whenever the user asks to orchestrate agents, create or steer worker sessions, run a workflow-like effort, fan out audits/research/migrations, coordinate parallel implementation streams, monitor other project sessions, or compare this control-session pattern to Claude Code dynamic workflows. This skill is especially relevant when the current session can spawn persistent project sessions and those sessions can spawn their own subagents, creating a two-level orchestration hierarchy.
199SKILL.mdUpdated Jun 2, 2026
pskoett/self-healing
tools
VerifiedTrustedCommunity
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a `HEAL-` entry to `.learnings/HEALS.md` with proof. Use whenever a command, test, build, or lint fails or exits non-zero; on missing tooling, dependency/lockfile mismatch, wrong runtime version, venv or permission errors, port conflicts, dirty git state, or a missing `.env`; when the agent needs a helper or one-off script that doesn't exist yet; when an external API, tool, or MCP errors or rate-limits; or when a test flakes. Search `HEALS.md` by `Pattern-Key` first — most heals are recurrences, so increment `Recurrence-Count` instead of duplicating. Verify is mandatory: mark `pending-verify` honestly if sandboxed, `abandoned` if the fix can't be made to work. Pairs with `self-improvement` (which promotes recurring heals to durable memory) but owns the verify-before-persist discipline self-improvement doesn't.
199SKILL.mdUpdated Jun 2, 2026
pskoett/control-session-orchestrator
development
VerifiedTrustedCommunity
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app control session. Use this skill whenever the user asks to orchestrate agents, create or steer worker sessions, run a workflow-like effort, fan out audits/research/migrations, coordinate parallel implementation streams, monitor other project sessions, or compare this control-session pattern to Claude Code dynamic workflows. This skill is especially relevant when the current session can spawn persistent project sessions and those sessions can spawn their own subagents, creating a two-level orchestration hierarchy.
199SKILL.mdUpdated Jun 2, 2026