Vibeguard Agent Skill
Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. Use when the user asks for guardrails, task contracts, risk scoring, or review templates.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/majiayu000/spellbook --skill vibeguardThe instruction itself
11 sections, as written by the authorVibeGuard
Lightweight VibeGuard for everyday use inside Spellbook.
This skill helps with three moments where AI-assisted work usually drifts:
- before implementation starts
- while review findings are being prioritized
- after regressions or avoidable mistakes happen
What This Skill Includes
- A task contract checklist for scoping work before coding
- A scoring matrix for prioritizing findings with evidence
- A weekly review template for regression and guardrail retrospectives
Hard Boundaries
This skill is intentionally lightweight.
It does:
- guide task kickoff
- structure review output
- make risk tradeoffs explicit
It does not:
- install hooks
- run guard scripts automatically
- patch global Claude or Codex configuration
- claim that full VibeGuard enforcement is active
If the user asks for automated interception, repo-level rules, or environment setup, escalate to the full VibeGuard repository and tooling.
When To Use It
Trigger this skill when the user asks for:
- anti-hallucination guardrails
- task startup checks
- review scoring or triage
- regression prevention
- retrospective templates
- "vibeguard" by name
Workflow
1. Start With The Task Contract
Open references/task-contract.yaml and confirm:
- goal
- source of truth
- acceptance criteria
- scope
Do not move into implementation until these are concrete.
2. Score Findings Before Acting
Open references/scoring-matrix.md and score each finding on:
- impact
- effort
- risk
- confidence
Use the score to separate urgent fixes from weak guesses.
3. Pick The Right Delivery Mode
- 1-2 files: implement directly once the contract is clear
- 3-5 files: write a short spec or step plan first
- 6+ files: produce a full design/spec and staged execution plan
4. Review The Failure, Not Just The Symptom
If something regressed, identify which defense failed:
- scope control
- source-of-truth validation
- verification depth
- review prioritization
- missing guardrail
Then capture the follow-up in references/review-template.md.
Expected Outputs
Depending on the request, produce one of these:
- a filled task contract
- a scored findings table with priorities
- a short regression review or weekly retrospective
Reference Files
references/task-contract.yaml- kickoff checklistreferences/scoring-matrix.md- prioritization modelreferences/review-template.md- retrospective template
Other skills for the same job
different authors, same section of the catalogue
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971 device risk management, ISO/IEC 17025 testing and calibration laboratories, and ISO 15189 medical laboratories. Use when organizing declared scope, controlled documents, risk-management files, scope of accreditation, traceability, CAPA, external-provider controls, or bounded local evidence manifests, and when separating ISO certification from laboratory accreditation, FDA QMSR inspection, CLIA certification, MDSAP, and EU MDR/IVDR evidence boundaries. Not for legal applicability, compliance, certification, or accreditation decisions; contains no clause text.
Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for designs with no formula — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Use this skill even when the request only mentions an effect size, alpha, or "80% power" without saying "power analysis" explicitly. For laying out the study (randomization, blocking, factorial/DOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis.
> reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this end-to-end", "plan and build", "break this into tasks", "grill me on this plan", "pick up this ticket", "run this migration".
Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
Senior Elite Software Engineer (15+) and Senior Product Designer. Full workflow with planning, architecture, TDD, clean code, and pixel-perfect UX validation.
Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflows.
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
How to use it
Take majiayu000/vibeguard from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.