{"skill":{"slug":"gaasher-blue-team","name":"blue-team","description":"Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing pytest/JUnit tests) — and wants the target patched until those failures are closed without breaking what already works. It points straight at the failed cases (normalize any source with tools/ingest.py), fixes one root-cause class per iteration, and re-checks with tools/verify.py — oracle mode against a red-team oracle, or tests mode against the test suite — keeping a patch only if it closes a class while nothing that passed before regresses, else reverting; loops until every class is closed (dry) or the budget runs out, then opens a pull request with the patch set. The defensive fixer half of a find→fix setup. Not for discovering new failures (that is red-team), and not for editing the oracle, tests, or holdout that define ground truth.","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/blue-team"},"recommended_command":"npx skills add gaasher/Agent-Loop-Skills --skill blue-team","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-blue-team","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"blue-team\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/blue-team. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing pytest/JUnit tests) — and wants the target patched until those failures are closed without breaking what already works. It points straight at the failed cases (normalize any source with tools/ingest.py), fixes one root-cause class per iteration, and re-checks with tools/verify.py — oracle mode against a red-team oracle, or tests mode against the test suite — keeping a patch only if it closes a class while nothing that passed before regresses, else reverting; loops until every class is closed (dry) or the budget runs out, then opens a pull request with the patch set. The defensive fixer half of a find→fix setup. Not for discovering new failures (that is red-team), and not for editing the oracle, tests, or holdout that define ground truth. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-blue-team\",\"task\":\"Install blue-team\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"blue-team\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/blue-team. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing pytest/JUnit tests) — and wants the target patched until those failures are closed without breaking what already works. It points straight at the failed cases (normalize any source with tools/ingest.py), fixes one root-cause class per iteration, and re-checks with tools/verify.py — oracle mode against a red-team oracle, or tests mode against the test suite — keeping a patch only if it closes a class while nothing that passed before regresses, else reverting; loops until every class is closed (dry) or the budget runs out, then opens a pull request with the patch set. The defensive fixer half of a find→fix setup. Not for discovering new failures (that is red-team), and not for editing the oracle, tests, or holdout that define ground truth. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-blue-team\",\"task\":\"Install blue-team\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"blue-team\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/blue-team into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing pytest/JUnit tests) — and wants the target patched until those failures are closed without breaking what already works. It points straight at the failed cases (normalize any source with tools/ingest.py), fixes one root-cause class per iteration, and re-checks with tools/verify.py — oracle mode against a red-team oracle, or tests mode against the test suite — keeping a patch only if it closes a class while nothing that passed before regresses, else reverting; loops until every class is closed (dry) or the budget runs out, then opens a pull request with the patch set. The defensive fixer half of a find→fix setup. Not for discovering new failures (that is red-team), and not for editing the oracle, tests, or holdout that define ground truth. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-blue-team\",\"task\":\"Install blue-team\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"install_receipt":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"event_id is unique; retries update the same receipt","count_rule":"verified installs require install_used=true and outcome=success","example":{"event_id":"install_<unique-id>","skill_slug":"gaasher-blue-team","task":"Install blue-team","agent":"codex","outcome":"success","install_used":true}},"safety_gate":{"tier":"blocked","label":"Blocked for auto-install","badge":"BLOCKED","auto_install_policy":"block","auto_install_allowed":false,"human_review_required":true,"blocked":true,"recommended_action":"Do not auto-install. Inspect the source, dependencies, and permission surface first.","reasons":["Metadata combines secrets access with shell or command execution","High-risk permission hints: Shell or command execution, Secrets or environment access"]},"agent_prompt":"Install the \"blue-team\" agent skill only after reviewing the OpenAgentSkill profile and source repository. Safety gate: Blocked for auto-install (block). Start with https://www.openagentskill.com/skills/gaasher-blue-team, inspect the trust and audit notes, then use the recommended install handoff: npx skills add gaasher/Agent-Loop-Skills --skill blue-team. After installation, summarize changed files, required setup, and a minimal verification result before using the skill for real work. Report the verified result to https://www.openagentskill.com/api/agent/outcome using a unique event_id, skill_slug=gaasher-blue-team, install_used=true, and outcome=success or failed.","safety_checklist":["Safety gate: Blocked for auto-install. Policy: block.","Do not auto-install. Inspect the source, dependencies, and permission surface first.","Review the repository and license before running third-party code.","Prefer a sandbox or isolated project when testing a new skill.","Start with the recommended command, then inspect generated files before committing changes.","Do not execute external side effects, payments, account changes, or credentialed actions without explicit user approval."],"verification_steps":["Open the skill documentation or SKILL.md and identify required setup.","Run the smallest safe example for the target task.","Confirm outputs match the task before allowing broader agent use.","Record any missing credentials, policy risks, or manual approvals needed."],"do_not_auto_install_when":["The repository or license cannot be reviewed.","The skill requires broad credentials or production account access.","The task involves regulated, private, or high-impact data without user approval."],"urls":{"web":"https://www.openagentskill.com/skills/gaasher-blue-team","api":"https://www.openagentskill.com/api/agent/skills/gaasher-blue-team","install_api":"https://www.openagentskill.com/api/skills/gaasher-blue-team/install","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/blue-team"},"meta":{"agent_friendly":true,"api_version":"1.0","generated_at":"2026-09-08T12:18:06.278Z"}}