2.6K skills · sorted by relevance
Review open GitHub issues and pull requests against project templates and contribution guidelines. Get a report on missing information and compliance, with options to apply recommended labels or close incomplete submissions with an explanatory comment.
Turn completed case intake into a demand letter draft for payment, contract breaches, or other claims. Review confidentiality and admission risks, refine the wording, and produce a Word document with a checklist for follow-up after sending.
Manage Google Tasks through gog: view task lists, add or update tasks, mark work complete, and remove entries. The workflow includes explicit account selection and checks before changes.
Run repeated, independent security audits of a repository or selected directory with Codex Security. It combines validated findings into a report that records the reviewed scope, exclusions, and any incomplete coverage.
Learn the complete OpenSpec workflow through a small task in an actual codebase. The agent explains each stage while creating a proposal, specifications, design, and tasks, then implements the change and archives its records.
Archive several OpenSpec changes together after reviewing their documents, task completion, and specification conflicts. The agent checks actual code to decide which specification updates to apply, asks for confirmation, and reports successes, skipped changes, and failures.
Turn completed experiment analyses into an internal research report that explains findings, figures, limitations, and next actions. Reports connect evidence to decisions and can be saved locally or written into a linked Obsidian project.
Check citations in LaTeX and Quarto manuscripts against a bibliography file. Find missing references, unused entries, and likely citation key typos, then flag incomplete fields, author formatting problems, and character encoding issues.
Turn completed analyses, research plans, and literature reviews into an academic manuscript. The skill proposes an outline for approval, drafts sections around existing tables and figures, and arranges a review of arguments and supporting evidence.
Clean up completed research folders by identifying temporary and intermediate files for confirmed removal. Preserve papers, final findings, screening history, and methodology records, then check that essential files remain intact and report the space recovered.
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
The English summary is being prepared. Showing the original description.
Guides systematic review of processing documentation for completeness against GDPR Articles 5, 13-14, 24, 28, and 30. Activate when auditing documentation or preparing for inspections. Keywords: documentation review, processing records, completeness, privacy notices, RoPA.
The English summary is being prepared. Showing the original description.
Automatically complete partial code snippets while satisfying semantic constraints including variable types, invariants, pre/post-conditions, interface contracts, and expected input/output behavior. Use when users provide incomplete code with specific requirements like "complete this function that takes a list and returns sorted unique elements" or "fill in this method body that must maintain the invariant that x stays positive" or "implement this interface method with these type constraints." Produces compilable, executable code with tests and a constraint satisfaction report.
The English summary is being prepared. Showing the original description.
Closes a completed development branch by checking the final diff and proof, presenting merge, pull-request, keep, or discard options, and cleaning up only after the user or repository workflow chooses a path. Use when feature work is complete and the branch must be integrated or retired. Not for claiming a feature is complete before verification.
The English summary is being prepared. Showing the original description.
Validate a completed plugin refactor against its task evidence, baseline assessment, documentation, and current validators. Use after implement-refactor or when deciding whether refactoring is complete.
The English summary is being prepared. Showing the original description.
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
The English summary is being prepared. Showing the original description.
The sprint completeness oracle — a mechanical, exit-code-driven check that every feature in a sprint manifest is provably complete across three dimensions (a done-record reference, resolvable edge tests, and a resolvable wiring test). Fails loud with a per-feature gap list naming the missing dimension. Read-only. Use to gate a sprint before it is called done (Slice A of the sprint-mode epic), or any time you want a completeness reading.
The English summary is being prepared. Showing the original description.
Expert-level mathematical logic knowledge. Use when working with propositional logic, first-order logic, proof theory, model theory, computability theory, Godel incompleteness theorems, set theory, type theory, or formal verification. Also use when the user mentions 'formal proof', 'Godel', 'incompleteness', 'Turing machine', 'decidability', 'Zermelo-Fraenkel', 'axiom of choice', 'model theory', 'completeness theorem', 'computability', 'formal language', or 'type theory'.
The English summary is being prepared. Showing the original description.
Author a completed-spec fixture — a seeded intent graph plus a believable four-phase interview transcript — for a brunch feature, so it can feed any downstream tooling that consumes a completed spec or dogfood the UI. Use when you need a real completed specification in .brunch/brunch.db for testing or demo: pick a feature from memory/SPEC.md (or a free description), choose a stress profile (coverage|clean), and produce a registered scenario seed + an interview-questions doc that match exactly.
The English summary is being prepared. Showing the original description.
Operational guide for integrating the NV oOS Complete purchase flow (vendor checkout API client) into standalone WordPress plugins — docs-hub 0.5.3 (stack added in PR #6963, shipped 0.5.2 → 0.5.3) and nvoos-content-graph 1.0.10 (live). Covers the vendor API contract (session/verify/health, nvoos-oos-complete product, 424/502 error passthrough), the five-class client stack (config, vendor client, license store, installer, REST controller), the purchase-modal JS/CSS port recipe (class-prefix rename, keep-the-JS-identical trick), wp.org commerce compliance (External Services disclosure, WPORG-REVIEW-COMMERCE-NOTES.md, js.stripe.com service exception), and the checkout test conventions (direct controller calls, pi_ fixture rules, zero-HTTP assertions). Use when adding the Get NV oOS Complete upsell/checkout to a plugin, porting the commerce stack to a new standalone plugin, extending the purchase flow, or debugging a checkout integration.
The English summary is being prepared. Showing the original description.
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
The English summary is being prepared. Showing the original description.
Generate the success criteria for a task or question, then review work against them. Given a task, goal, or open-ended question, decompose it into scenarios, evaluation perspectives, and fine-grained weighted YES/NO criteria using the Recursive Expansion Tree (RET) method; if work is supplied, score it criterion-by-criterion and surface what is missing or could be better. Use when asked to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done or completeness checklist, create an evaluation rubric or grading criteria, score or grade answers to a question, set up an LLM-as-judge rubric, or when the user mentions self-review, completeness check, success criteria, evaluation criteria, scoring rubric, Qworld, or the RET algorithm.
The English summary is being prepared. Showing the original description.
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
The English summary is being prepared. Showing the original description.
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
The English summary is being prepared. Showing the original description.