1.6K skills · sorted by relevance
Investigate reproducible bugs by recreating symptoms, testing one possible cause at a time, and checking fixes in both a simplified test case and the original scenario. Retry limits keep unsuccessful fixes from continuing unchecked.
Review pull requests, branches, or uncommitted changes across eight areas, including security, correctness, and tests. Verify findings against the code, group problems by type, and assess whether the change needs redesign or smaller fixes.
Audit a specific web page using Google Search Console data and its live HTML. Assess content quality, search intent, readability, metadata, structured data, and internal links, then produce a scored SEO report with suggested fixes.
Investigate slow interactions and rendering using performance traces, which record execution events, alongside source code. Identify the responsible code, distinguish measurements from hypotheses, and guide fixes that preserve behavior, with tests and comparable recordings for verification.
pyfixest demeaner_backend="cupy64" (including its CPU fallback when cupy is absent) is NOT numerically identical to the default numba backend and does NOT drop fully-absorbed/collinear regressors the same way. Use when: (1) adding demeaner_backend="cupy64" to existing pf.feols/fepois calls changes the printed coefficient table, (2) a regression report suddenly gains rows with absurd estimates (e.g. coef 435.8, SE 7106) for controls absorbed by the fixed effects, (3) diffing outputs before/after a backend change, or (4) anything parses a pyfixest text report by line position.
The English summary is being prepared. Showing the original description.
Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle GPU. Use when: (1) a script looping dozens of pf.feols models on a 100k+ row panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x FE structures x domains). Root cause: per-model CPU-side single-threaded fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a small slice. Fix: shard the model grid across OS processes and/or use pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.
The English summary is being prepared. Showing the original description.
Learn project rules from accumulated fix patches in .unikit/code/patches/. Analyzes past mistakes, extracts prevention points, classifies each as a coding rule (→ RULES.md) or a per-skill workflow rule (→ skill-context), and proposes them for approval. Use when the user wants to turn past fixes into rules — "evolve", "evolve the rules", "learn from past mistakes", "learn from the fixes", "analyze the patches", "what rules should we add from recent fixes". Best run after several /unikit-fix sessions have left patches behind. This derives rules from accumulated patch history — to add a single rule by hand use /unikit-rules, and to promote mature RULES.md entries into the knowledge base use /unikit-memory migrate-rules.
The English summary is being prepared. Showing the original description.
Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.
The English summary is being prepared. Showing the original description.
Validates code fixes by running the code, checking compilation, verifying runtime behavior, and confirming fixes resolve the reported issue. Use when verifying that bug fixes actually work at runtime.
The English summary is being prepared. Showing the original description.
Iteratively detects and auto-fixes technical debt in a codebase using three quality criteria from debt-analysis references: conditional branch simplification, encapsulation, and separation of concerns. Applies fixes directly to code, runs existing tests to verify no regressions, re-analyzes, and loops until all high-severity issues are resolved or max iterations (5) reached. Use this skill when you want to automatically improve code quality with real code changes, reduce technical debt systematically, or clean up code to meet quality standards. Trigger on phrases like "fix technical debt", "clean up code quality", "refactor and fix issues", "improve code quality automatically", "apply debt fixes", "fix code problems", "eliminate debt".
The English summary is being prepared. Showing the original description.
Manage preparation, publication, recovery, and verification of OpenClaw beta, stable, and extended-stable releases. Track approved fixes carried into older release branches, required validation evidence, publication scope, and follow-up work through completion.
Investigate memory growth and out-of-memory failures in OpenClaw tests. Compare memory measurements and heap snapshots, records of objects held in memory, to distinguish cleanup leaks from retained test modules and verify targeted fixes.
Turn GitHub issues into pull requests, proposed code changes ready for review. Filter issues, avoid duplicate work, and assign background agents to implement fixes, run tests, and optionally address review comments.
Assign independent bugs or test failures to separate agents that work at the same time. Define each agent’s scope and expected report, then check for conflicting changes and run the full test suite before integrating fixes.
Investigate bugs, failing tests, and unexpected behavior using reproduction steps, logs, and recent changes. Follow a structured process to identify the root cause, test a specific explanation, and verify the resulting fix.
Develop Spring Boot features and fixes by writing tests before implementation. Guides unit, web, persistence, and integration testing with JUnit 5, Mockito, MockMvc, and Testcontainers, plus JaCoCo measurement of how much code tests cover.
Assess whether an application is ready for production using local files and authorized evidence. Reviews authentication, data, payments, and operations, then reports release blockers, prioritized fixes, and a readiness score without uploading repository contents to an external audit service.
Coordinate feature work, bug fixes, refactoring, and MVP development through shared phases scaled to the change. Related operation skills use this workflow to delegate research, planning, test-first implementation, review, and commits with human approval checkpoints.
Test an authorized web application, map its exposed pages and inputs, and verify suspected vulnerabilities with reproducible evidence. Produce a security report covering confirmed findings, their impact, reproduction steps, and suggested fixes.
Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.
Delegate implementation, bug fixes, and pull request reviews to Blackbox AI through the Hermes terminal. Run tasks across multiple AI models, evaluate their outputs, monitor longer jobs, and resume work from saved checkpoints.
Guides delegation of coding tasks to Claude Code CLI through Hermes. Covers one-shot runs and ongoing interactive sessions for feature work, bug fixes, refactoring, and reviews, with controls for tool permissions, execution limits, and structured results.
Audit an entire code repository or a selected folder for bugs, security risks, load problems, missing tests, slow paths, and excess code. Get up to 20 prioritized findings explaining concrete problems, minimal fixes, and consequences.
Fix Python type checking failures found locally or in CI, the automated checks run on code changes. It identifies affected files, applies targeted fixes to type declarations and checks, then reruns validation.