一键导入
code-review
// Structured code review skill. Use when asked to "review this code", "review this PR", "check this diff", or when acting as a Hydra reviewer. Runs a multi-pass review with specialist focus areas and confidence-gated findings.
// Structured code review skill. Use when asked to "review this code", "review this PR", "check this diff", or when acting as a Hydra reviewer. Runs a multi-pass review with specialist focus areas and confidence-gated findings.
QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.
Use when starting work in a TermCanvas-managed repo to route between direct work, Hydra, or a narrow TermCanvas skill.
Use when a task should run through Hydra's Lead-driven workflow for multi-agent orchestration, or when an existing workflow must be inspected or cleaned up.
Adversarial review skill. Use when the user wants to stress-test an idea, argument, proposal, or opinion from multiple independent angles. Spawns parallel Hydra workers with orthogonal analytical methodologies.
Security audit skill. Use when asked to "audit security", "check for vulnerabilities", "security review", "pentest", or when evaluating code that handles auth, user input, secrets, or external data. Runs a phased scan covering OWASP Top 10 and STRIDE threat modeling.
Systematic debugging skill. Use when encountering a bug, test failure, unexpected behavior, or when asked to "investigate", "debug", "diagnose", or "figure out why". Enforces root-cause-first discipline with structured hypothesis tracking.
| name | code-review |
| description | Structured code review skill. Use when asked to "review this code", "review this PR", "check this diff", or when acting as a Hydra reviewer. Runs a multi-pass review with specialist focus areas and confidence-gated findings. |
Structured multi-pass review. Read the full diff before commenting on anything.
git diff <base>..HEADgit diff --cachedRead the diff line by line. Flag only real issues:
Always check:
Never flag:
Based on the change type, apply the relevant specialist lens:
If the diff touches tests:
expect(true).toBe(true))?If the diff touches data access:
If the diff touches auth/security:
security-audit skill to the changed codeIf the diff touches UI:
For each finding, assign a confidence level:
Report format per finding:
[severity] file:line — description
Confidence: N/10
Suggestion: specific fix