135 skills · sorted by relevance
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.
Dry-run one cycle of a sales agent workflow without calling language models. Validate the template and agent types, check budget reservations, generate agent prompts, and record a structured status summary for downstream automation.
Review multi-step forms to find information users must enter more than once. Suggest automatic filling, reuse options, and preserving data between steps, while explaining relevant accessibility requirements and exceptions for security or validity.
Simulate peer review through five perspectives covering journal fit, methods, subject expertise, interdisciplinary implications, and counterarguments. Receive separate review reports, an editorial decision, and a revision roadmap, or check whether revisions address earlier comments.
Assess scientific claims by examining study design, statistics, bias, and evidence quality. Use structured appraisal frameworks to identify supported conclusions, explain uncertainties, and propose practical improvements with concerns traced to specific evidence.
Work with geographic points, lines, and areas in Python using GeoPandas. Guidance and local audit tools help check coordinate systems, geometry validity, spatial join matches, and export settings before trusting or sharing analysis results.
Use COBRApy to model metabolic networks and calculate possible reaction flows under defined constraints. Compare gene knockouts, nutrient conditions, and production limits, while checking model validity and keeping computational predictions separate from experimental findings.
Plan and review fluid simulations with FluidSim, from solver selection and resource estimates to output analysis and restart checks. Examine numerical accuracy through grid and time-step comparisons, conservation checks, and explicit limits on computing resources.
Retrieve public evidence and linked publications for a supported genetic variant, or look up gene–disease relationships. Preserve sources, conflicting assertions, and explicit search outcomes so qualified professionals can review the findings.
Evaluate scientific manuscripts or excerpts through three independent mock reviewer reports and a combined assessment. Identify strengths, evidence gaps, major concerns, and minor corrections to guide revisions before submission.
Configure OMX alerts for session events through Discord, Telegram, Slack, OpenClaw, or custom integrations. Choose notification events, adjust detail and idle intervals, and check configuration validity and delivery with the required tests.
Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.
Check whether OpenShell issues and pull requests fit the project, then track review feedback and automated checks. State labels show what needs attention and when a pull request is ready for maintainer approval or a merge decision.
Review an authorized security issue in its private workflow. Check the affected code, assess whether the report is valid, explain severity and attack prerequisites, and propose a remediation plan with focused tests.
Coordinate CAD and source assets through conversion to USD, a 3D scene format, material and physics assignment, and SimReady checks. Produce stage reports, with preview rendering and validated delivery packages when requested.
Audit Claude Code instruction rules in .claude/rules/ and ~/.claude/rules/: frontmatter, paths glob validity against real files, symlink load status, and day-to-day usefulness, then update rules with the user. Use for first-time rules setup, rules that apply too often or never, or periodic rules hygiene. Not for Codex .rules command-approval files.
The English summary is being prepared. Showing the original description.
Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented rules, then reviews hooks one by one. Use when setting up hooks, debugging a hook that never fires, never blocks, or hangs the agent, or doing a periodic hooks hygiene pass. Not for writing a new hook from scratch.
The English summary is being prepared. Showing the original description.
Analyze PR review comments from a GitHub PR URL. Fetch review comments, verify each finding against the actual codebase, assess validity (correct/incorrect/partial), present a structured summary with recommended actions, and optionally reply to each comment on GitHub. Use when given a PR review URL or when asked to check/analyze PR feedback.
The English summary is being prepared. Showing the original description.
Hunt SAML / SSO attacks. Patterns: XML Signature Wrapping (XSW) — modify Assertion while keeping Signature valid by relocating signed element, comment injection in NameID (admin@target.com<!--evil-->@attacker.com → some parsers see admin@target.com), signature stripping (remove Signature element entirely, server should reject but doesn't), key confusion (signed by attacker's IdP, accepted by SP), audience-restriction not validated, replay attack (same Assertion accepted twice within validity window). Tools: SAML Raider Burp extension, samlmagic, manual XML manipulation. Detection: any /saml endpoint, /Shibboleth.sso, /sso/saml/, Microsoft ADFS endpoints. Validate: account takeover via altered NameID, admin role injection via altered AttributeStatement. Use when hunting SSO flows, when SAML AssertionConsumerService is reachable, when chaining IdP-trust to SP-impersonation.
The English summary is being prepared. Showing the original description.
Causal inference design audit for the sewage-house-prices project. Runs a 4-phase review (claim identification, design validity, inference, polish) covering hedonic pricing, repeat sales, long difference, DiD/event studies, upstream/downstream, and dry spill strategies. This skill should be used when asked to "check the econometrics", "audit the identification", "review the strategy", or when verifying that code matches the stated design.
The English summary is being prepared. Showing the original description.
Agent D4 - Measurement Instrument Developer - Scale construction and psychometric validation. Covers item development, validity evidence, and reliability testing for social science research.
The English summary is being prepared. Showing the original description.
Econometrics skill for instrumental variables and treatment effect estimation. Activates when the user asks about: "instrumental variables", "IV estimation", "2SLS", "two-stage least squares", "endogeneity", "weak instruments", "first stage", "Sargan test", "overidentification", "propensity score matching", "PSM", "average treatment effect", "ATT", "LATE", "local average treatment effect", "endogenous regressor", "instrument validity", "工具变量", "两阶段最小二乘", "内生性", "弱工具变量", "倾向得分匹配", "平均处理效应", "处理效应", "局部平均处理效应"
The English summary is being prepared. Showing the original description.
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
The English summary is being prepared. Showing the original description.
Starter: interpret a council run's verdict artifacts — quorum, dissent, cross-lab validity, and what to do next
The English summary is being prepared. Showing the original description.